VintageComics

I've got you. Too late now, but I'll copy your posts from the ASM #252 thread into here tomorrow. You have made some incredibly salient points about AI and are pretty much the only reasonable voice in the entire discussion. Thank you.

Not sure why this is the case. If someone can build one AI that can do this job, they can build a million of them. Could probably get every book currently waiting at CGC graded in a lazy afternoon. So you want to "build a million machines" that don't exist yet? This sounds economically feasible? Or are you going to have 1000s of graders flipping pages for these photo-imaging machines so that the books can be scanned and graded? So we'll pay people to stand around and just flip pages? Or load them into robotic machines that flip pages? I can't believe some of the ducking (pun intended) ideas some people come up with without thinking them through. I guess we can do it this way:

4 times the headache, 4 times the quality control problems, 4 times the opportunity for something to go wrong, 4 times the hassle.

I personally have stated many times that AI can do aspects of grading, but grading an entire comic is not going to happen anytime soon for a zillion different reasons, but the primary one being that you need to intersect the following i) handling the actual comic book is complex ii) time constraints - sure, if I had an hour to feed all my info into a computer I may be able to get a reasonably accurate grade, or grade range but you need this done in seconds iii) cost constraints - how do you build something this complex, in a space that doesn't take too much room, is cost effective and accurate iv) you will ALWAYS need some level of human interaction throughout the grading process, whether it's from receiving packages, to unpackaging, to laying them down on an assembly line, to removing them from Mylars, to grading them (flipping through all pages) to putting them back into Mylars, etc. so where does the human stop and the AI start and visa versa? v) you need to TEACH the AI to learn along the way (or from past experience) - that's a stall every time you find a new problem to solve, and this happens daily when grading 1000's of books a day. For example, there are things that happen in the grading process EVERY DAY when weird defects, or a crossover of defects happen that need actual human conversation to make a decision. This will stall the grading process and needs to be learned and it happens daily. vi) you'd need to make AI changes every time a new defect or variant is discovered - new learning curve ---------------------------------------- The way I see it the variables are myriad and not easy to solve. Humans do this sort of learning very quickly. I just don't see AI grading books accurately, in a cost effective and timely manner anytime soon. Thoughts?

I started a new thread for the AI / grading discussion. You're welcome.

...so as not to distract from the other thread. Have at it!

Seriously. It's like asking if AI can make a tricycle reach the moon. I mean, maybe. If Buzz Aldrin is commandeering.

How do you know it's an MJ insert and not someone's nudie pics that they hid in there?

So you're going to put your ASM #1, Hulk #181 or Action #1 into that machine and let it flip pages? How do you get the book out of a Mylar? How do you get the book into the machine? How do you get it off the machine? How do you get it to encapsulation? I don't think some people think anything they're saying through. Or maybe they just can't. This conversation is ridiculous.

What was the timeline on that? I don't think this is Dylan, but that public discussion could have given people reading the threads ideas to exploit that avenue.

Again, most people don't seem to grasp ALL the factors involved in grading a book. AI isn't a magic wand. If you want AI to do one thing, it's relatively easy. If you want it to do 2 things, it becomes far more complex. If you want it to do 3 or 10 things, it's complexity multiplies incredibly. Now factor in physical movement. Do you know how much it would cost to build ONE ROBOT to pick up a book, hold it and turn pages without damaging a book? Millions? Now try to build a system that will do ALL of that, be accurate and make it cost effective. Like I have been saying, by the time they do that we'll all be half human, have implants making us cyborgs (I'm not talking hearing aids and hip replacements) and who knows if comics will even be a thing. It's one thing to dream. It's an entirely different thing to do. Again, I CAN see AI doing mundane tasks like, say, zeroing in cover grades into a certain range, or giving page quality opinions, or weighing books for missing components, but to put it all together in one effective package?

Grading is FAR more than just page quality. Not everyone is incapable of comprehending real possibilities and separating them from improbable ones. Using AI for various aspects of grading? I've already said I wouldn't be surprised if it was happening but there is no way AI is grading books without human involvement any time soon.That's spaceage thinking that is just fairy tale stuff for the foreseeable future. By the time this happens, we'll only be half human. And THAT is the point I'm making.

I don't think most average people can think in terms of complex systems. Just like examining a 2D painting is different for AI, putting a metal fender in place on an assembly line is different than picking up a comic book, turning the pages and assessing them all. You might eventually be able to make it happen in the distant future with NASA type tech, but by then all human labor will have been replaced. I think the challenge is in the complexity of how fine of a handling touch is needed, complicated by the the diverse methods of analysis AND cost structure to make it viable. These are all going to be obstacles and making them all work together? You can do one thing well, but tying all of those things together is space age stuff.

Why do you keep tagging me? I'm as surprised as you are that nobody has addressed this. Not much anyone can do.

oh? https://www.cnn.com/2023/12/21/style/raphael-madonna-della-rosa-ai-scli-intl-scn/index.html yeah, while CGC is busy ignoring this thread, someone is thinking about how they can grade more,faster using AI. MCS will probably get their first because they are innovation minded but the first grading company to figure this out will disrupt the market in a way that poses the single biggest threat to CGC's dominance, much more than this little embarrassing thread. It's not a question of IF AI will will do grading of collectibles, but when. 3D objects objects are not an issue. That's been fairly routine for a decade. The last guy at CGC that might still have a job in 10 years, ironically enough as it pertains to this thread, is the mook reholdering books. I don't think you understand what goes into grading a comic book. Identifying 2 dimensional details like art shapes and brush strokes from the article you linked is one thing. Assessing a 3 dimensional object is something entirely different. How do you get AI to examine 30 or 60 pages? How do you get AI to FEEL the pages? Smell the pages? Assess how the entire book FEELS? These are all factors in grading a book. It's NOT just a matter of counting spine ticks. You'd need to get things like radiology, weigh scales and all sorts of other things in the process. Now you need to make it cost effective and efficient because you can't spend 5 mins on a book. There's just too much, multi-dimensional, human involvement in grading a book from what I can envision.

The old wells were sealed on 4 sides. 2 vertical seals all the way from top to bottom, and two horizontal seals above and below the book. The vertical sealings (along the longest part of the inner well) went all the way from the top to the bottom of the inner holder, and that seal was used to also partially seal the label to the inner wells. The idea being, if you removed the label, a little paper was torn off by the seal showing it was tampered with. The problem was that it wasn't always effective and so part of the problem they tried to address with the Gen 3 design, was to eliminate label tampering as well as book tampering.

This reeks of the late 80's when the whored out Punisher and Wolverine in literally EVERYTHING to make a buck.

Sorry, yes. I was in Seattle July 2016. Just typing too fast. Weird that the software wouldn't allow me to edit this post for a while. I kept getting a notification saying it was too old to edit?

All the way up until the Gen 3 holders started in late 2016. They used to partially seal to the inner well (or were supposed to) and part of the reason for the Gen 3 redesign was to make label swapping harder. I think one root problem to all of this is that the outer clam shell isn't always sealed as well as it could be. MOST of the books I've cracked make it impossible to not notice it's been tampered with, but I have heard and read of reports where this hasn't always been the case.

Thanks. I knew it was late 2016 or early 2017, but I couldn't remember exactly. I know I saw them first in Seattle and I just checked my records, and you're right. I was in Seattle July 2017 a month after the release so that's where I saw them first. I think it was Greg Reece's booth to be specific. He had an early Atlas I wanted. Sorry. That is pretty funny in hindsight. I thought you were serious and I get annoyed by people who worry about Newton rings. Strangely, to my recollection I don't remember anyone complaining about Newton rings to myself.

No I didn't. I specifically was addressing the discussion and the problems only associated with the label and outer shell because that's what people were discussing.

Perhaps not. I'm not sure how the changes took place 100% or what exactly was melded together in the inner well with regards to the top and bottom of the case. Never cracked a slab to really look. They definitely had some slab changes around that time that may have been when the change transpired I guess. Was my best guess on that timeframe. For the latest, Gen 3 holder, the label sits by itself in a cavity at the top part of the holder very snugly and even bends over the inside of the holder to make the top of the label visible from the top. The inner well sits by itself in a cavity in the bottom part of the holder. There is a formed demarcation, or an edge between the two that actually separates the top from the bottom, or the label at the top from the inner well at the bottom. The two don't even touch each other. The bottom of the label rests on that edge in the top cavity, the top of the inner holder bumps against that edge in the lower cavity. They are completely separated in different cavities. EDIT: The tiny bit of movement is entirely irrelevant. It's like complaining that someone has a few hairs out of place. You have to have a millimeter of play / tolerance between the outer and inner labels so that they don't bind.

They stopped sealing the certification label inside the inner well when they changed to this newest outer case roughly circa early 2017? These newest cases (I call them Gen 3) initially had the "creep engine" problem, but shortly after that problem, the solution was to use the older (previous Gen 2) style inner well structure, but they needed to cut the top off it off those older wells to fit inside the latest style outer holders. The newer style holders had no room in the design for the taller, older inner well with the label at the top, because the label already had a designated area within the newest outer holder. The label AND outer holder were redesigned for 2 specific reasons: 1) to both replace the top label sticker (which always used to come off over time and annoy people) so this is why the new CGC label folds over the top of the book and is visible from outside and 2) to prevent swapping labels out between books the way some of the older inner labels used to allow. The entire design rested on the premise that the outer case was the final deterrent and that any tampering would be clearly evident. I am fairly certain that the inner well is roughly the same or similar design that has been used from the previous Gen 2 cases.

Funnily enough, I've met him more than once and IIRC, he kinda looked like that.

What I am having trouble understanding is how someone gets SO MANY REHOLDERS without anyone raising an eyebrow internally. I mean, I reholder books. Everyone does, but it's usually like 1 in 100 or or 1 in 1000 or something similar due to a cracked slab or whatever, but not almost every book. Either: 1) They're either a very high volume submitter and not every book is a reholder, so he just 'salts' them into submissions once in a while or 2) They've found a way to reseal the slabs and reholder them for another reason other than slab damage (like a scratch on the slab or newton rings) so that the book doesn't get inspected at all.