Home U.S. Coin Forum

CAC vs the rest...

245

Comments

  • ProofCollectionProofCollection Posts: 6,162 ✭✭✭✭✭
    edited July 5, 2024 9:30AM

    @MFeld said:

    @ProofCollection said:

    @Carterofmars said:
    Silly question but if CACG is the most stringent, isn't it better to get coins graded by them?

    IMO they're not "more stringent," they use a different standard altogether which among other things, fails to recognize the "C" part of the grading spectrum. It all depends what standard you want to be applied.

    In failing to recognize C quality coins for given grade levels and grading them a point lower with a plus, they are grading more stringently.

    I guess you can say that but when you boil it down, they're just using a different measuring stick with the lines drawing in a different place than PCGS and NGC. You can call it 'more strict' I just call it 'different' because I haven't stopped recognizing 'C' coins.

    @MFeld said:

    @Carterofmars said:
    Silly question but if CACG is the most stringent, isn't it better to get coins graded by them?

    If by “get”, you meant “buy”, it depends upon what you have to pay for the coins. And if you meant submit for grading, it depends upon what you’ll be able to obtain for the coins. Grades shouldn’t be looked at in a vacuum.

    Buy the coin, not the holder. Pay what you think it's worth.

  • MoldnutMoldnut Posts: 3,100 ✭✭✭✭

    I probably have equal amounts of coins in both PCGS and NGC that I think, “That was a little bit of a gift.”
    IMO, on low grade 16-D dimes, I think PCGS is looser. Just put them in the holder that you like.

    Derek

    EAC 6024
  • CarterofmarsCarterofmars Posts: 75 ✭✭✭

    @coinbuf said:

    There are multiple considerations to be considered before you make a decision on a grading service, not the least of which is why you want to send coins to a grading firm at all.

    Reason- to get the most accurate grade possible for my coin. I want the slab to reflect reality.

  • GoldminersGoldminers Posts: 4,008 ✭✭✭✭✭

    @Carterofmars said:

    @coinbuf said:

    There are multiple considerations to be considered before you make a decision on a grading service, not the least of which is why you want to send coins to a grading firm at all.

    Reason- to get the most accurate grade possible for my coin. I want the slab to reflect reality.

    Coin grading can be subjective, and there are sometimes discrepancies between different grading services. Additionally, the cost of professional grading, and even potential inconsistencies due to human error are common concerns.

    Reality doesn't really exist until we measure it. Since some coins crossover and others do not, your expectation of reality and consistency in grading your coins is a fantasy. Consider taking a grading class and reread all the advice you have already been given.

  • ProofCollectionProofCollection Posts: 6,162 ✭✭✭✭✭

    @Goldminers said:

    @Carterofmars said:

    @coinbuf said:

    There are multiple considerations to be considered before you make a decision on a grading service, not the least of which is why you want to send coins to a grading firm at all.

    Reason- to get the most accurate grade possible for my coin. I want the slab to reflect reality.

    Coin grading can be subjective, and there are sometimes discrepancies between different grading services. Additionally, the cost of professional grading, and even potential inconsistencies due to human error are common concerns.

    Reality doesn't really exist until we measure it. Since some coins crossover and others do not, your expectation of reality and consistency in grading your coins is a fantasy. Consider taking a grading class and reread all the advice you have already been given.

    Right, but you realize the top 3 grading companies all use different rulers right? So how can you say one is more accurate than another? All us collectors can do is recognize the differences and buy the coin (not the holder). The best we can ask for from grading companies is consistency.

  • coinbufcoinbuf Posts: 11,305 ✭✭✭✭✭

    @Carterofmars said:

    @coinbuf said:

    There are multiple considerations to be considered before you make a decision on a grading service, not the least of which is why you want to send coins to a grading firm at all.

    Reason- to get the most accurate grade possible for my coin. I want the slab to reflect reality.

    Accuracy is a myth, what is accurate today may not be tomorrow. Until the human element can be eliminated from grading there will always be inaccuracy. In my biased and subjective opinion CACG is the best (meaning most accurate with minimal market grading) at this current moment in time, but what I see as reality may be fantasy to another.

    My Lincoln Registry
    My Collection of Old Holders

    Never a slave to one plastic brand will I ever be.
  • CarterofmarsCarterofmars Posts: 75 ✭✭✭

    @Goldminers said:

    @Carterofmars said:

    @coinbuf said:

    Coin grading can be subjective, and there are sometimes discrepancies between different grading services. Additionally, the cost of professional grading, and even potential inconsistencies due to human error are common concerns.

    Reality doesn't really exist until we measure it. Since some coins crossover and others do not, your expectation of reality and consistency in grading your coins is a fantasy. Consider taking a grading class and reread all the advice you have already been given.

    Well, if accuracy and expecting a slab to reflect the reality of the coins condition within is a fantasy, why bother having coins graded at all.

    Inherent problems abound my friend.

  • CarterofmarsCarterofmars Posts: 75 ✭✭✭

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    Until the human element can be eliminated from grading there will always be inaccuracy.

    What about the use of AI in grading? If an algorithm could be developed that would assign a grade, then have a committee of say three to five people evaluate that grade assignment, would that suffice?

  • Jacques_LoungecoqueJacques_Loungecoque Posts: 733 ✭✭✭✭✭

    @Carterofmars said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    Until the human element can be eliminated from grading there will always be inaccuracy.

    What about the use of AI in grading? If an algorithm could be developed that would assign a grade, then have a committee of say three to five people evaluate that grade assignment, would that suffice?

    Wouldn’t having a committee of 3-5 people review the robot’s decision pretty much duplicate the grading system as it already exists at P, N, or C?

    Having fun while switching things up and focusing on a next level PCGS slabbed 1950+ type set, while still looking for great examples for the 7070.

  • CarterofmarsCarterofmars Posts: 75 ✭✭✭
    edited July 5, 2024 5:08PM

    @Jacques_Loungecoque said:

    @Carterofmars said:

    @coinbuf said:

    Wouldn’t having a committee of 3-5 people review the robot’s decision pretty much duplicate the grading system as it already exists at P, N, or C?

    No, it wouldn't, IMO. The baseline would be the grade AI assigned. The three or five simply vote yay or nay.

  • Cougar1978Cougar1978 Posts: 8,228 ✭✭✭✭✭
    edited July 5, 2024 5:11PM

    @Carterofmars said:
    Where is it advisable to send a collection for grading today?

    PCGS by far.

    They handle both coins and currency too. Their inventory app is a superior analytical and research platform. Can even have photos of the coin downloaded to it. Their market report is fantastic plus it has their grading standards which I have studied and highlighted.

    Coins & Currency
  • CarterofmarsCarterofmars Posts: 75 ✭✭✭

    @Cougar1978 said:

    @Carterofmars said:
    Where is it advisable to send a collection for grading today?

    PCGS by far.

    They handle both coins and currency too. Their inventory app is a superior analytical and research platform. Can even have photos of the coin downloaded to it. Their market report is fantastic plus it has their grading standards which I have studied and highlighted.

    How about the accuracy of pcgs vs cacg?

  • CarterofmarsCarterofmars Posts: 75 ✭✭✭
    edited July 5, 2024 5:32PM

    Interesting exchange with AI. I asked AI, a robust version, to evaluate this coin using ANA grading Standards i fed into the AI engine.

    For the record, several in another post suggested this coin would grade MS 63.

    Remember, this is just for FUN.

    **For the Obverse **

    Based on the provided criteria and the image of the 1918 Illinois Centennial coin, here's an assessment of its grade:

    Uncirculated Coins:

    • Contact Marks: There are some noticeable contact marks on Lincoln's profile and the fields surrounding it, but they are not overly distracting.
    • Hairlines: There are some hairlines visible, particularly in the fields, suggesting some handling or light wear.
    • Luster: The luster is present but not fully original or very strong, indicating some impairment.
    • Eye Appeal: The overall eye appeal is decent, though the contact marks and hairlines do detract slightly.

    Circulated Coins:

    • Wear: There is minimal to no wear on the high points of the design, suggesting this coin may not have seen much circulation if any.
    • Luster: The luster is somewhat impaired but still present.
    • Contact Marks: There are noticeable contact marks, especially on the obverse.
    • Eye Appeal: The coin maintains good detail and is generally attractive despite the contact marks and hairlines.

    Considering these observations, the coin likely falls into the Mint State (MS) range. Given the visible marks and slightly impaired luster, it would be graded as follows:

    • MS-64: This grade fits due to the several small contact marks, some of which are in prime focal areas, and the somewhat impaired luster. The overall eye appeal is still quite attractive, fitting the description of an MS-64 coin.
    • MS-63: This could also be considered due to the presence of noticeable contact marks and light hairlines, with luster slightly impaired. The coin is attractive overall but does not have the pristine qualities of higher grades.

    Based on the visible marks and the level of luster, an MS-63 grade seems appropriate for this coin. It shows characteristics of a slightly impaired luster with numerous small contact marks and good overall eye appeal.

    For the Reverse

    Evaluating the reverse of the 1918 Illinois Centennial coin based on the provided image and grading criteria:

    Uncirculated Coins:

    • Contact Marks: There are some contact marks visible on the fields and the eagle's wings. While these are not overly distracting, they are noticeable.
    • Hairlines: Hairlines are visible, particularly in the fields and near the text, suggesting some handling or light wear.
    • Luster: The luster is present but impaired, with some areas appearing duller than others.
    • Eye Appeal: The overall eye appeal is decent but is diminished by the visible contact marks and hairlines.

    Circulated Coins:

    • Wear: Minimal wear is evident, indicating that the coin may not have seen significant circulation.
    • Luster: The luster is somewhat impaired but still present in certain areas.
    • Contact Marks: Noticeable contact marks are visible, particularly on the fields and the eagle's body and wings.
    • Eye Appeal: The coin maintains good detail and is generally attractive despite the marks and hairlines.

    Considering these observations, the reverse side of the coin likely falls into the Mint State (MS) range. Given the visible marks and somewhat impaired luster, it would be graded as follows:

    • MS-64: Fits due to the several small contact marks, some of which are in prime focal areas, and the somewhat impaired luster. The overall eye appeal is quite attractive despite the marks.
    • MS-63: This grade is also possible due to the presence of noticeable contact marks and light hairlines, with luster slightly impaired. The coin is attractive overall but does not have the pristine qualities of higher grades.

    Based on the visible marks and the level of luster, an MS-63 grade seems appropriate for the reverse of this coin. It shows characteristics of slightly impaired luster with numerous small contact marks and good overall eye appeal.

  • Cougar1978Cougar1978 Posts: 8,228 ✭✭✭✭✭
    edited July 5, 2024 5:39PM

    I don’t care about CACG nor am I a major investor in their material. What do you think about the mass, brightness of the Sun vs Proxima Centauri?

    Coins & Currency
  • CarterofmarsCarterofmars Posts: 75 ✭✭✭

    For the record, several in another post suggested this coin would grade MS 63.

  • ProofCollectionProofCollection Posts: 6,162 ✭✭✭✭✭

    @Carterofmars said:

    @Cougar1978 said:

    @Carterofmars said:
    Where is it advisable to send a collection for grading today?

    PCGS by far.

    They handle both coins and currency too. Their inventory app is a superior analytical and research platform. Can even have photos of the coin downloaded to it. Their market report is fantastic plus it has their grading standards which I have studied and highlighted.

    How about the accuracy of pcgs vs cacg?

    Accuracy to which standard? PCGS and CACG use different standards.

  • CarterofmarsCarterofmars Posts: 75 ✭✭✭

    @ProofCollection said:

    Accuracy to which standard? PCGS and CACG use different standards.

    That's THE problem wouldn't you say?

  • Jacques_LoungecoqueJacques_Loungecoque Posts: 733 ✭✭✭✭✭

    @Carterofmars said:

    @Cougar1978 said:

    @Carterofmars said:
    Where is it advisable to send a collection for grading today?

    PCGS by far.

    They handle both coins and currency too. Their inventory app is a superior analytical and research platform. Can even have photos of the coin downloaded to it. Their market report is fantastic plus it has their grading standards which I have studied and highlighted.

    How about the accuracy of pcgs vs cacg?

    PCGS has been considered the gold standard of accuracy for pretty much ever. NGC a close second, (IMHO - but this is easily a whole ‘nother argument). CAC comes along with much “tighter” and “stricter” grading criteria. Does this strictness equate to a higher level of accuracy?

    It’s really up to the individual to make their assessments. The market, based on prices realized, has given CAC either higher or equivalent values to PCGS in most series. Such the same as PCGS over NGC, again - depending on series, etc…. Therefore, it could be construed that the market identifies CAC as more accurate.

    There has always seemed to be a pendulum swinging amongst TPGs. Things get tight, things get loose. Often at different times for different companies, amongst different series, and for different lengths of time. I believe CAC is more often too tight. I also believe PCGS is often too tight at times. NGC seems more consistent over time to me, but many believe that’s a loose consistency - I disagree about that.

    If one follows the adage of buying the coin, not the holder, then most issues come pre-worked out. If you like a coin and you feel strongly that it’s “X” grade, then you can decide its value to you, regardless of the holder. The problem lies in when it comes time to sell that coin. Were you accurate and consistent with the market? You’ll find out one way or the other.

    I really, truly, 100% believe the very best thing you can have at the moment is an NGC or PCGS coin with the CAC sticker. That way you have a coin graded by world class graders, and seconded by another set of world class graders. Unless and until PCGS and NGC start stickering CAC or each other’s coins, that’s as good as it’s gonna get. If I ran NGC or PCGS we’d already be stickering. But, I sure as hell don’t. 🤣

    Having fun while switching things up and focusing on a next level PCGS slabbed 1950+ type set, while still looking for great examples for the 7070.

  • Cougar1978Cougar1978 Posts: 8,228 ✭✭✭✭✭
    edited July 5, 2024 5:58PM

    Years ago a dorm friend flunked his 1st test in corp finance horribly under DR A / dropped the class before the deadline, avoiding flunking out. He took the corp finc class under DR B in Summer school and made a B. Which one would you want going on your transcript?

    Coins & Currency
  • CarterofmarsCarterofmars Posts: 75 ✭✭✭
    edited July 5, 2024 6:00PM

    Consider this. Again, I asked AI to grade a coin. See the results. Again, this is just for FUN.


    Based on the provided images of the 1935 Texas Centennial Half Dollar coin, here is an assessment using the grading criteria:

    Observations:

    Obverse:

    • Contact Marks: There are some noticeable contact marks, especially on the fields and the eagle's body.
    • Hairlines: There are hairlines visible, particularly in the fields, suggesting some handling or light wear.
    • Luster: The luster appears to be present but not as strong and vibrant as a higher grade might show.
    • Eye Appeal: The overall eye appeal is still relatively good, but the contact marks and hairlines do detract slightly.

    Reverse:

    • Contact Marks: There are several contact marks visible, especially in the fields and on the figures.
    • Hairlines: Hairlines are visible, indicating some handling or light wear.
    • Luster: The luster is somewhat impaired, with some areas appearing duller than others.
    • Eye Appeal: The coin maintains good detail and is generally attractive despite the visible marks and hairlines.

    Grading:

    Considering these observations, the coin likely falls into the Mint State (MS) range. Given the visible marks, hairlines, and somewhat impaired luster, it would be graded as follows:

    • MS-63: This grade fits due to the presence of noticeable contact marks and hairlines, with luster slightly impaired. The coin is attractive overall but does not have the pristine qualities of higher grades.
    • MS-64: This could also be considered due to the several small contact marks and the somewhat impaired luster. The overall eye appeal is still quite attractive despite the marks.

    Final Grade:

    Based on the visible marks and the level of luster, an MS-63 grade seems appropriate for this coin. It shows characteristics of slightly impaired luster with numerous small contact marks and good overall eye appeal. The presence of hairlines and contact marks does impact its grade, keeping it from achieving higher Mint State grades like MS-64 or above.

  • ProofCollectionProofCollection Posts: 6,162 ✭✭✭✭✭

    @Carterofmars said:

    @ProofCollection said:

    Accuracy to which standard? PCGS and CACG use different standards.

    That's THE problem wouldn't you say?

    Problem for who?
    I buy the coin, not the holder. I could purchase gas in Liters or Gallons and do the math conversion just fine. Is it convenient when everyone sells gas in gallons? A little, but if a station opened up down the street selling gas by the liter I don't see that a problem. I can see why the math-challenged might despise a company choosing a different standard by which to do business, but it's not a big deal if you understand what the differences are.

  • CarterofmarsCarterofmars Posts: 75 ✭✭✭
    edited July 5, 2024 6:28PM

    .

  • Manifest_DestinyManifest_Destiny Posts: 6,896 ✭✭✭✭✭

    @MFeld said:

    @ProofCollection said:

    @Carterofmars said:
    Silly question but if CACG is the most stringent, isn't it better to get coins graded by them?

    IMO they're not "more stringent," they use a different standard altogether which among other things, fails to recognize the "C" part of the grading spectrum. It all depends what standard you want to be applied.

    In failing to recognize C quality coins for given grade levels and grading them a point lower with a plus, they are grading more stringently.

    I think the "C" coins end up in details grade holders. Most "C" coins probably fall into the "market acceptable" category.

  • hummingbird_coinshummingbird_coins Posts: 1,138 ✭✭✭✭✭

    @Jacques_Loungecoque said:
    The market, based on prices realized, has given CAC either higher or equivalent values to PCGS in most series. Such the same as PCGS over NGC, again - depending on series, etc…. Therefore, it could be construed that the market identifies CAC as more accurate.

    Or, rather than paying more for a CAC graded coin because they think CAC is more accurate, people are paying more because of the stricter CAC grading, and they believe it is a grade above what CAC called it.

    Young Numismatist • My Toned Coins
    Life is roadblocks. Don't let nothing stop you, 'cause we ain't stopping. - DJ Khaled

  • DisneyFanDisneyFan Posts: 2,069 ✭✭✭✭✭

    @Carterofmars said:
    Interesting exchange with AI. I asked AI, a robust version, to evaluate this coin using ANA grading Standards i fed into the AI engine.

    Very interesting. You must have had a lot of fun asking AI.

    The thing to remember is "grading" is more than just a number grade for a coin. The CACG website lists about 20 reasons why a coin could be in a "details" holder and additional reasons why it could be "body bagged." In the case of the later, a coin could have PVC or even be counterfeit. Many of these concerns could not be evaluated by having a picture. The AI category of Luster is an example where it would be difficult for AI to be precise as a coin can be considered not cleaned by grading services; but, declared over dipped by CAC/CACG.

    Finally, no grading service is 100% accurate. Obviously human errors are made from time to time.

  • MFeldMFeld Posts: 13,514 ✭✭✭✭✭

    @Manifest_Destiny said:

    @MFeld said:

    @ProofCollection said:

    @Carterofmars said:
    Silly question but if CACG is the most stringent, isn't it better to get coins graded by them?

    IMO they're not "more stringent," they use a different standard altogether which among other things, fails to recognize the "C" part of the grading spectrum. It all depends what standard you want to be applied.

    In failing to recognize C quality coins for given grade levels and grading them a point lower with a plus, they are grading more stringently.

    I think the "C" coins end up in details grade holders. Most "C" coins probably fall into the "market acceptable" category.

    I think not. By definition (from CAC) C coins are low end for the assigned grade. And that’s not the same thing as a problem/details grade coin.

    Mark Feld* of Heritage Auctions*Unless otherwise noted, my posts here represent my personal opinions.

  • TwoSides2aCoinTwoSides2aCoin Posts: 44,294 ✭✭✭✭✭
    edited July 5, 2024 9:17PM

    @Carterofmars said:

    @ProofCollection said:

    Accuracy to which standard? PCGS and CACG use different standards.

    That's THE problem wouldn't you say?

    Actually when there is more than one standard, then there’s no standard. That’s how and why JA put CAC into motion and why he is not entertaining coins in PCI, ANACS, ICG or a few other TPG holders who also have/had “standards”.

    accuracy , subjectivity ? Standards or Standard ?
    Seems there’s only hope or little hope.

  • shishshish Posts: 1,152 ✭✭✭✭✭

    Sure, ideally there would be a universal grading standard. However, perhaps the best we can hope for is that each company consistently adheres to their grading standard. This requires that numismatists have a good understanding of each companies grading standards which in many cases are not well defined or do not accurately describe their grading standards.

    For example, companies having a written definition that states all mint state coins have no trace of wear. These companies then publicly state that coins with slight wear on the high points and good field luster will be graded mint state 60-62.

    I'm convinced that history proves that accurate and consistent grading to a well defined standard can be achieved. Currently my experience has shown that CAC is the primer grading company. There are millions of properly graded coins in other TPG holders, I recommend evaluating each coin on its merits.

    Liberty Seated and Trade Dollar Specialist
  • Cougar1978Cougar1978 Posts: 8,228 ✭✭✭✭✭
    edited July 6, 2024 5:50AM

    Anybody got a good rebound (upgrade) going the other way / CACG to other TPG? Share your rips.

    Coins & Currency
  • PeakRaritiesPeakRarities Posts: 3,700 ✭✭✭✭✭

    @Cougar1978 said:
    Anybody got a good rebound (upgrade) going the other way / CACG to other TPG? Share your rips.

    One of the few coins I’ve submitted to them, an 1836 2.50 classic head.

    Bought it in a p61 cac holder, cracked it out and sent in raw and it came back CACG 62.

    Founder- Peak Rarities
    Website
    Instagram
    Facebook

  • Manifest_DestinyManifest_Destiny Posts: 6,896 ✭✭✭✭✭

    @ProofCollection said:

    @Manifest_Destiny said:

    @MFeld said:

    @ProofCollection said:

    @Carterofmars said:
    Silly question but if CACG is the most stringent, isn't it better to get coins graded by them?

    IMO they're not "more stringent," they use a different standard altogether which among other things, fails to recognize the "C" part of the grading spectrum. It all depends what standard you want to be applied.

    In failing to recognize C quality coins for given grade levels and grading them a point lower with a plus, they are grading more stringently.

    I think the "C" coins end up in details grade holders. Most "C" coins probably fall into the "market acceptable" category.

    No, please listen to some JA interviews where he clearly describes C coins as those at the bottom ~1/3 of a coin grade. Details coins are coins with defects. Falling into the bottom portion of a given coin grade is not a defect.

    @MFeld said:

    @Manifest_Destiny said:

    @MFeld said:

    @ProofCollection said:

    @Carterofmars said:
    Silly question but if CACG is the most stringent, isn't it better to get coins graded by them?

    IMO they're not "more stringent," they use a different standard altogether which among other things, fails to recognize the "C" part of the grading spectrum. It all depends what standard you want to be applied.

    In failing to recognize C quality coins for given grade levels and grading them a point lower with a plus, they are grading more stringently.

    I think the "C" coins end up in details grade holders. Most "C" coins probably fall into the "market acceptable" category.

    I think not. By definition (from CAC) C coins are low end for the assigned grade. And that’s not the same thing as a problem/details grade coin.

    I think you're missing my point. Example: There's a PCGS AU50 coin that's been dipped, but market acceptable. If you send it in to CAC, they won't sticker it because it's a "C" coin. If you send it in to CACG, they will grade it "AU details" rather than XF45+ because they "don't grade "C" coins" as was mentioned up thread. So, to reiterate, my point is that PCGS/NGC "C" coins end up in CACG details holders rather than being assigned the next grade down.

    You can argue whether or not that actually happens to every single "C" coin, but I bet it happens to the PCGS/NGC "market acceptable" "C" coins.

  • shishshish Posts: 1,152 ✭✭✭✭✭

    I'm sure that this does occur, however, making broad general statements is not precise enough to help understand a TPG's grading standards or their consistency.

    For example in your example it all depends on the severity of the dipping.

    I recommend evaluating each coin on its merits.

    Liberty Seated and Trade Dollar Specialist
  • Manifest_DestinyManifest_Destiny Posts: 6,896 ✭✭✭✭✭

    @shish said:
    I'm sure that this does occur, however, making broad general statements is not precise enough to help understand a TPG's grading standards or their consistency.

    For example in your example it all depends on the severity of the dipping.

    I recommend evaluating each coin on its merits.

    The "broad general statement" that was made (not by me) was that "CACG doesn't grade "C" coins". I was just providing my reasoning as to how that may be true.

    So, CACG does grade "C" coins by bumping them down a grade, or they grade them as "details".

    You can argue how much of each, which I'm sure is based on evaluating each coin.

  • CrepidoderaCrepidodera Posts: 363 ✭✭✭✭✭

    Don,

    I agree, the vast majority of "C" coins are put in details holders.

    Doug

  • coinbufcoinbuf Posts: 11,305 ✭✭✭✭✭

    @Carterofmars said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    Until the human element can be eliminated from grading there will always be inaccuracy.

    What about the use of AI in grading? If an algorithm could be developed that would assign a grade, then have a committee of say three to five people evaluate that grade assignment, would that suffice?

    Perhaps in the future AI will reach a point that it might be useful, I can especially see it being used for new modern mint releases where every coin is almost identical to the next like the ASE coins. But older coinage is different, it takes more than just counting the number of marks which is what AI can do. Adding a committee to review the AI results just adds back the subjective human element and thus negates using any sort of computer grading.

    And in fact there have been several attempts to use computers to grade coins, one was showcased here on this forum just in the last year or two. But so far while interesting experiments those attempts have fallen short and have not been able to achieve any meaningful grading success, at least not yet.

    My Lincoln Registry
    My Collection of Old Holders

    Never a slave to one plastic brand will I ever be.
  • Cougar1978Cougar1978 Posts: 8,228 ✭✭✭✭✭
    edited July 6, 2024 9:19AM

    So get the CACG details C coin and submit elsewhere else get straight grade bump up? I would pass on that op it might get details again.

    Pretty sure a lot of players buying CACG they feel under graded doing grade bump up special ops somewhere else on high potential stuff. Then if sell from table on bourse - TD. Then if they do enough them practice makes perfect.

    Am concerned it could get like the rattler angle, nicer ones getting picked off for upgrades elsewhere.

    Coins & Currency
  • MFeldMFeld Posts: 13,514 ✭✭✭✭✭

    @breakdown said:
    I think there are a few categories of coins that fail to sticker and some people get these categories mixed up. C coins should end up in straight grade holders. Coins that are deemed over graded by CAC should also. The third category -
    problem coins - get detail holders.

    In other words, a C coin is not a problem coin. That’s my understanding anyway.

    That’s the way John Albanese has explained it for years. I think I’ll go with his analysis, rather than that of others who predict that most C coins will receive detail grades.

    Mark Feld* of Heritage Auctions*Unless otherwise noted, my posts here represent my personal opinions.

  • PeakRaritiesPeakRarities Posts: 3,700 ✭✭✭✭✭

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    Until the human element can be eliminated from grading there will always be inaccuracy.

    What about the use of AI in grading? If an algorithm could be developed that would assign a grade, then have a committee of say three to five people evaluate that grade assignment, would that suffice?

    Perhaps in the future AI will reach a point that it might be useful, I can especially see it being used for new modern mint releases where every coin is almost identical to the next like the ASE coins. But older coinage is different, it takes more than just counting the number of marks which is what AI can do. Adding a committee to review the AI results just adds back the subjective human element and thus negates using any sort of computer grading.

    And in fact there have been several attempts to use computers to grade coins, one was showcased here on this forum just in the last year or two. But so far while interesting experiments those attempts have fallen short and have not been able to achieve any meaningful grading success, at least not yet.

    You’ve only seen the beginning, AI in its infancy. Give it 5-10 years and I’d bet that we won’t believe our eyes. When someone integrates depth mapping with a computer that can rotate the coin under different light sources, it’s game over. It will take a lot of data and a lot of money, but it will be done before our lifetime.

    Founder- Peak Rarities
    Website
    Instagram
    Facebook

  • lermishlermish Posts: 2,921 ✭✭✭✭✭

    @DeplorableDan said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    Until the human element can be eliminated from grading there will always be inaccuracy.

    What about the use of AI in grading? If an algorithm could be developed that would assign a grade, then have a committee of say three to five people evaluate that grade assignment, would that suffice?

    Perhaps in the future AI will reach a point that it might be useful, I can especially see it being used for new modern mint releases where every coin is almost identical to the next like the ASE coins. But older coinage is different, it takes more than just counting the number of marks which is what AI can do. Adding a committee to review the AI results just adds back the subjective human element and thus negates using any sort of computer grading.

    And in fact there have been several attempts to use computers to grade coins, one was showcased here on this forum just in the last year or two. But so far while interesting experiments those attempts have fallen short and have not been able to achieve any meaningful grading success, at least not yet.

    You’ve only seen the beginning, AI in its infancy. Give it 5-10 years and I’d bet that we won’t believe our eyes. When someone integrates depth mapping with a computer that can rotate the coin under different light sources, it’s game over. It will take a lot of data and a lot of money, but it will be done before our lifetime.

    The technology will for sure exist but here's the question. Given the Witter Box thread we all acknowledge, happily or not, that our TPG Private Equity overlords make the vast amount of their money from moderns. A human would probably still be required to handle the coins, even moderns.

    Why would they spend the money to implement this system? Where is the incremental profit?

  • Manifest_DestinyManifest_Destiny Posts: 6,896 ✭✭✭✭✭

    @MFeld said:

    @breakdown said:
    I think there are a few categories of coins that fail to sticker and some people get these categories mixed up. C coins should end up in straight grade holders. Coins that are deemed over graded by CAC should also. The third category -
    problem coins - get detail holders.

    In other words, a C coin is not a problem coin. That’s my understanding anyway.

    That’s the way John Albanese has explained it for years. I think I’ll go with his analysis, rather than that of others who predict that most C coins will receive detail grades.

    CAC and CACG are using the A,B,C system. They don't mention a 4th category, so where do straight graded PCGS/NGC coins end up when they get details graded by CACG. They had to be "C" coins. There's no other explanation unless there's a secret 4th category that CAC/CACG doesn't publicly acknowledge. It can't be both ways.

  • oih82w8oih82w8 Posts: 12,213 ✭✭✭✭✭

    @jmlanzaf said:

    @PerryHall said:
    This is a good question to ask Heather or one of the other forum moderators.

    They recommended NGC to me.

    First thing I thought of...

    "I can't take it anymore, I just can't fight it.
    Eastern Airlines thanked me for flying United."

    Rodney Dangerfield

    oih82w8 = Oh I Hate To Wait _defectus patientia_aka...Dr. Defecto - Curator of RMO's

    BST transactions: dbldie55, jayPem, 78saen, UltraHighRelief, nibanny, liefgold, FallGuy, lkeigwin, mbogoman, Sandman70gt, keets, joeykoins, ianrussell (@GC), EagleEye, ThePennyLady, GRANDAM, Ilikecolor, Gluggo, okiedude, Voyageur, LJenkins11, fastfreddie, ms70, pursuitofliberty, ZoidMeister,Coin Finder, GotTheBug, edwardjulio, Coinnmore, Nickpatton, Namvet69,...
  • PeakRaritiesPeakRarities Posts: 3,700 ✭✭✭✭✭
    edited July 6, 2024 9:56AM

    @lermish said:

    @DeplorableDan said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    Until the human element can be eliminated from grading there will always be inaccuracy.

    What about the use of AI in grading? If an algorithm could be developed that would assign a grade, then have a committee of say three to five people evaluate that grade assignment, would that suffice?

    Perhaps in the future AI will reach a point that it might be useful, I can especially see it being used for new modern mint releases where every coin is almost identical to the next like the ASE coins. But older coinage is different, it takes more than just counting the number of marks which is what AI can do. Adding a committee to review the AI results just adds back the subjective human element and thus negates using any sort of computer grading.

    And in fact there have been several attempts to use computers to grade coins, one was showcased here on this forum just in the last year or two. But so far while interesting experiments those attempts have fallen short and have not been able to achieve any meaningful grading success, at least not yet.

    You’ve only seen the beginning, AI in its infancy. Give it 5-10 years and I’d bet that we won’t believe our eyes. When someone integrates depth mapping with a computer that can rotate the coin under different light sources, it’s game over. It will take a lot of data and a lot of money, but it will be done before our lifetime.

    The technology will for sure exist but here's the question. Given the Witter Box thread we all acknowledge, happily or not, that our TPG Private Equity overlords make the vast amount of their money from moderns. A human would probably still be required to handle the coins, even moderns.

    Why would they spend the money to implement this system? Where is the incremental profit?

    If Modern grading could be done by 1 computer with an initial investment of 1-2 million dollars, and replace a large number of humans who need to make at least 60k a year, I believe it could be very profitable long term.

    The thing is, if an independent startup comes up with the technology, the big TPGs would either have to buy them or squash them. The first company that introduces AI grading can promote and market it as "The final and accurate grade", so possibly all previously graded moderns and classic coins would have potential for re grading. I expect PCGS or NGC to implement the technology first, considering they have substantial resources to buy out the competition. OR they might decide that it would NOT be profitable long term, and they would buy the entity just to dissolve it and keep the technology from being used.

    Founder- Peak Rarities
    Website
    Instagram
    Facebook

  • CarterofmarsCarterofmars Posts: 75 ✭✭✭

    @DeplorableDan said:

    @lermish said:

    @DeplorableDan said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    Until the human element can be eliminated from grading there will always be inaccuracy.

    What about the use of AI in grading? If an algorithm could be developed that would assign a grade, then have a committee of say three to five people evaluate that grade assignment, would that suffice?

    Perhaps in the future AI will reach a point that it might be useful, I can especially see it being used for new modern mint releases where every coin is almost identical to the next like the ASE coins. But older coinage is different, it takes more than just counting the number of marks which is what AI can do. Adding a committee to review the AI results just adds back the subjective human element and thus negates using any sort of computer grading.

    And in fact there have been several attempts to use computers to grade coins, one was showcased here on this forum just in the last year or two. But so far while interesting experiments those attempts have fallen short and have not been able to achieve any meaningful grading success, at least not yet.

    You’ve only seen the beginning, AI in its infancy. Give it 5-10 years and I’d bet that we won’t believe our eyes. When someone integrates depth mapping with a computer that can rotate the coin under different light sources, it’s game over. It will take a lot of data and a lot of money, but it will be done before our lifetime.

    The technology will for sure exist but here's the question. Given the Witter Box thread we all acknowledge, happily or not, that our TPG Private Equity overlords make the vast amount of their money from moderns. A human would probably still be required to handle the coins, even moderns.

    Why would they spend the money to implement this system? Where is the incremental profit?

    If Modern grading could be done by 1 computer with an initial investment of 1-2 million dollars, and replace a large number of humans who need to make at least 60k a year, I believe it could be very profitable long term.

    The thing is, if an independent startup comes up with the technology, the big TPGs would either have to buy them or squash them. The first company that introduces AI grading can promote and market it as "The final and accurate grade", so possibly all previously graded moderns and classic coins would have potential for re grading. I expect PCGS or NGC to implement the technology first, considering they have substantial resources to buy out the competition. OR they might decide that it would NOT be profitable long term, and they would buy the entity just to dissolve it and keep the technology from being used.

    It's inevitable. It will be done in our life time and a lot sooner than most may anticipate.

    As I stated earlier, the way I envision it is AI assigning a grade after analysis of 1 clock to 12 o'clock photos of both obverse and reverse. Then 3 or 5 very senior human graders vote the grade assignment up or down.

    This makes the most sense to my thinking.

  • MFeldMFeld Posts: 13,514 ✭✭✭✭✭

    @Manifest_Destiny said:

    @MFeld said:

    @breakdown said:
    I think there are a few categories of coins that fail to sticker and some people get these categories mixed up. C coins should end up in straight grade holders. Coins that are deemed over graded by CAC should also. The third category -
    problem coins - get detail holders.

    In other words, a C coin is not a problem coin. That’s my understanding anyway.

    That’s the way John Albanese has explained it for years. I think I’ll go with his analysis, rather than that of others who predict that most C coins will receive detail grades.

    CAC and CACG are using the A,B,C system. They don't mention a 4th category, so where do straight graded PCGS/NGC coins end up when they get details graded by CACG. They had to be "C" coins. There's no other explanation unless there's a secret 4th category that CAC/CACG doesn't publicly acknowledge. It can't be both ways.

    @Manifest_Destiny said:

    @MFeld said:

    @breakdown said:
    I think there are a few categories of coins that fail to sticker and some people get these categories mixed up. C coins should end up in straight grade holders. Coins that are deemed over graded by CAC should also. The third category -
    problem coins - get detail holders.

    In other words, a C coin is not a problem coin. That’s my understanding anyway.

    That’s the way John Albanese has explained it for years. I think I’ll go with his analysis, rather than that of others who predict that most C coins will receive detail grades.

    CAC and CACG are using the A,B,C system. They don't mention a 4th category, so where do straight graded PCGS/NGC coins end up when they get details graded by CACG. They had to be "C" coins. There's no other explanation unless there's a secret 4th category that CAC/CACG doesn't publicly acknowledge. It can't be both ways.

    It’s not very complicated or mysterious. Formerly straight graded NGC and PCGS that failed to sticker at CAC were in their opinion, either:
    1) straight-grade worthy but of C quality
    2) straight-grade worthy but overgraded (as in deserving of a lower numerical grade)
    3) problem coins that should have received detail grades. This category would be your “4th category”.

    So coins that receive detail-grades at CACG need not have been C quality coins in the eyes of CAC. They would have fallen into group 3 above, not group 1. Problem coins aren’t a subset of the C quality coin group, as you’ve mistakenly categorized them.

    Again, according to John Albanese, most C quality coins will be straight graded by CACG, but at the next numerical grade down with a plus.

    Mark Feld* of Heritage Auctions*Unless otherwise noted, my posts here represent my personal opinions.

  • jmlanzafjmlanzaf Posts: 34,248 ✭✭✭✭✭

    @Manifest_Destiny said:

    @MFeld said:

    @breakdown said:
    I think there are a few categories of coins that fail to sticker and some people get these categories mixed up. C coins should end up in straight grade holders. Coins that are deemed over graded by CAC should also. The third category -
    problem coins - get detail holders.

    In other words, a C coin is not a problem coin. That’s my understanding anyway.

    That’s the way John Albanese has explained it for years. I think I’ll go with his analysis, rather than that of others who predict that most C coins will receive detail grades.

    CAC and CACG are using the A,B,C system. They don't mention a 4th category, so where do straight graded PCGS/NGC coins end up when they get details graded by CACG. They had to be "C" coins. There's no other explanation unless there's a secret 4th category that CAC/CACG doesn't publicly acknowledge. It can't be both ways.

  • lermishlermish Posts: 2,921 ✭✭✭✭✭
    edited July 6, 2024 10:50AM

    @Carterofmars said:

    @DeplorableDan said:

    @lermish said:

    @DeplorableDan said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    @Carterofmars said:

    @coinbuf said:

    Until the human element can be eliminated from grading there will always be inaccuracy.

    What about the use of AI in grading? If an algorithm could be developed that would assign a grade, then have a committee of say three to five people evaluate that grade assignment, would that suffice?

    Perhaps in the future AI will reach a point that it might be useful, I can especially see it being used for new modern mint releases where every coin is almost identical to the next like the ASE coins. But older coinage is different, it takes more than just counting the number of marks which is what AI can do. Adding a committee to review the AI results just adds back the subjective human element and thus negates using any sort of computer grading.

    And in fact there have been several attempts to use computers to grade coins, one was showcased here on this forum just in the last year or two. But so far while interesting experiments those attempts have fallen short and have not been able to achieve any meaningful grading success, at least not yet.

    You’ve only seen the beginning, AI in its infancy. Give it 5-10 years and I’d bet that we won’t believe our eyes. When someone integrates depth mapping with a computer that can rotate the coin under different light sources, it’s game over. It will take a lot of data and a lot of money, but it will be done before our lifetime.

    The technology will for sure exist but here's the question. Given the Witter Box thread we all acknowledge, happily or not, that our TPG Private Equity overlords make the vast amount of their money from moderns. A human would probably still be required to handle the coins, even moderns.

    Why would they spend the money to implement this system? Where is the incremental profit?

    If Modern grading could be done by 1 computer with an initial investment of 1-2 million dollars, and replace a large number of humans who need to make at least 60k a year, I believe it could be very profitable long term.

    The thing is, if an independent startup comes up with the technology, the big TPGs would either have to buy them or squash them. The first company that introduces AI grading can promote and market it as "The final and accurate grade", so possibly all previously graded moderns and classic coins would have potential for re grading. I expect PCGS or NGC to implement the technology first, considering they have substantial resources to buy out the competition. OR they might decide that it would NOT be profitable long term, and they would buy the entity just to dissolve it and keep the technology from being used.

    It's inevitable. It will be done in our life time and a lot sooner than most may anticipate.

    As I stated earlier, the way I envision it is AI assigning a grade after analysis of 1 clock to 12 o'clock photos of both obverse and reverse. Then 3 or 5 very senior human graders vote the grade assignment up or down.

    This makes the most sense to my thinking.

    I don't think the grading portion is really the issue. I'm confident that if coin grading was a priority for AI developers they would have a very workable model by the end of the year.

    The actual physical handling of the coins must be done by humans. Under no circumstances is any coin grading firm paying for surgical robots to handle coins. Especially for moderns, which is the overwhelming majority of subs and revenue, the grading is fairly trivial and since a person is handling the coin anyway can't they just as easily say 69 or 70?

    And then for the classics, is the AI grading by photos? Who is taking the photos, loading the coin into the device, removing the coin, etc? There are so many other fixed costs besides the graders' salaries to consider. I don't think it's anywhere near as easy as buying some software or a competitor and plugging it in.

    EDIT: And this is why we've seen poor customer service, slow turnaround times, bad photos, extra slow servers that are down all the time, etc. The fixed infrastructure can't be removed, so where else to generate extra profit? The top line is nearly maxed out (which is one of the reasons for mystery boxes, etc) so they sharpen their pencil on the "expendables"

Leave a Comment

BoldItalicStrikethroughOrdered listUnordered list
Emoji
Image
Align leftAlign centerAlign rightToggle HTML viewToggle full pageToggle lights
Drop image/file