{"as_of":"2026-07-22T05:19:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:86ba4dc0bc232743d9cecd0a0a83ee074aae9b8c5235d91bd638d5782cc9e43a","coverage":[{"denominator":55,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":55,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-08T04:13:28.233483Z","state":"measured"},{"denominator":55,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":55,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-07-21T06:31:05.380196+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2604.25065/citation-record","integrity":"/paper/2604.25065/integrity","json":"/paper/2604.25065/citation-record.json","paper":"/paper/2604.25065"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The lateral occipital complex and its role in object recognition","venue":null,"work_id":"ef429a2b-b790-4dbe-9636-edb08d1c974e","year":2001},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:408078222a71959298ee8dd0d2f1900785c23b2556bcfef191b01692ac04517e","observation_id":"a42bc898-d83d-4873-84d0-a37a215df5dd","resolution":{"observed_at":"2026-05-26T21:13:04.900338Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Recognition-by-components: A theory of human image understanding","venue":null,"work_id":"0d4d22c7-7b72-4883-8e03-32a4c4cfe831","year":1987},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:a2735e87c0f782b71d270ac3e79e8114c6425adec60ad9bfe1a93a8a633b219b","observation_id":"581c332d-816f-4692-8113-fef32e68d6b9","resolution":{"observed_at":"2026-05-26T21:13:04.889835Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Surface versus edge-based determinants of visual recognition","venue":null,"work_id":"1fd660e1-7b4a-42d1-a342-87b41416f66e","year":1988},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:b2c1920dc1b8fbb34eb9532738e46d72b2dec13e610d0c23f4340fadf8591395","observation_id":"1d68229d-b960-4d09-ac52-7706d5e99aee","resolution":{"observed_at":"2026-05-26T21:13:04.882632Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Visual intelligence: How we create what we see","venue":null,"work_id":"ea8fb0d2-a78f-454f-a3e7-b2a7b3fd26b0","year":1998},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:c405f32852467fa33cdb8e98ea320159918b28b51ee03e6955cf51cf90fd23b0","observation_id":"671120e8-1a78-475f-ae8d-752a2b806873","resolution":{"observed_at":"2026-05-26T21:13:04.885904Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Representation of Perceived Object Shape by the Human Lateral Occipital Complex","venue":null,"work_id":"472afaef-dca5-4779-87a8-093d14818ea2","year":2001},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:9fae47b99601d48fcc264f71b72ebf6216a0da9bfb976994ea871c1d84f81daf","observation_id":"850c4646-d7d3-43d5-af2c-445698759ba9","resolution":{"observed_at":"2026-05-26T21:13:04.876408Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"ImageNet: A large-scale hierarchical image database","venue":null,"work_id":"08af446c-b4a1-4ade-9d87-b2d753230d5a","year":2009},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:e3c51fb964f52b5e92547ced5220ec3a9a4a03a863704696778d5d2eaf70eb2c","observation_id":"22e54a17-f409-43fb-a825-4cf79a338be3","resolution":{"observed_at":"2026-05-26T21:13:04.862565Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.12231","last_updated":"2022-11-09T23:15:15Z","snapshot_observed_at":"2026-07-06T07:17:58.362513Z","submitted_at":"2018-11-29T15:04:05Z","title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","version":3},"cited_work":{"arxiv_id":"1811.12231","doi":"10.48550/arxiv.1811.12231","metadata_source":"pith","pith_arxiv_id":"1811.12231","snapshot_observed_at":"2026-07-10T09:26:59.505384Z","title":"Geirhos, P","venue":"cs.CV","work_id":"2d9e320f-8442-4895-b3f6-f360bd2b2289","year":2018},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"cited_paper":"/paper/1811.12231","citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:38d8f79d7cca0540d65b709826efd12299f1404617fdbd7c8213ddff1633593c","observation_id":"a8e2bd4d-d1dd-430f-b214-056c7e9d5663","resolution":{"observed_at":"2026-05-11T21:51:11.399305Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-18T17:51:20.879103+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-18T17:51:20.879103+00:00","source":"openalex_status_cache"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1904.00760","last_updated":"2019-03-20T16:37:17Z","snapshot_observed_at":"2026-07-06T07:43:00.418471Z","submitted_at":"2019-03-20T16:37:17Z","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","version":1},"cited_work":{"arxiv_id":"1904.00760","doi":null,"metadata_source":"pith","pith_arxiv_id":"1904.00760","snapshot_observed_at":"2026-07-10T20:17:33.752248Z","title":"Approximating CNNs with Bag-of-local-Features models works surprisingly well on ImageNet","venue":"cs.CV","work_id":"1b2c70f4-798f-4271-a6df-2185bb4014f3","year":2019},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"cited_paper":"/paper/1904.00760","citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:65186200b79e043272931251a52fcb045a5977a408a1b59eb84fc119df4d1a35","observation_id":"110019b2-e68d-45f0-bb05-48f1b997b6b1","resolution":{"observed_at":"2026-05-11T21:51:11.388426Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Deep convolutional networks do not classify based on global object shape","venue":null,"work_id":"7ebe0add-831a-42ec-9fa9-9fe8d512baa1","year":2018},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:8762178c260cd3f78f6b057cc76dcb005704a948be717702a7b07bbcef6b80f4","observation_id":"3b61a593-ee01-44ea-b41e-0fb56b6da7f9","resolution":{"observed_at":"2026-05-26T21:13:04.866156Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shape- Biased Learning by Thinking Inside the Box","venue":null,"work_id":"50b159a2-3590-4a12-bfeb-182765adac87","year":2024},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:2e8dc9710c96978d70f03eac40d441cebe6e85b8f108b7af1f73d46c97684b6e","observation_id":"9b4b12e3-9da1-4bc5-bc48-6f1e13404633","resolution":{"observed_at":"2026-05-26T21:13:04.869891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Are Vision Language Models Texture or Shape Biased and Can We Steer Them?","venue":null,"work_id":"dd763e17-a6de-4e72-aa7c-333fd8b282c3","year":2024},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:a0e44b249b6f87306ba393db403b753209d3045371850d8c14b9f8ef7435142d","observation_id":"7599d851-5707-48ce-8c9c-d0c90dfab804","resolution":{"observed_at":"2026-05-26T21:13:04.873016Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emergence of Shape Bias in Convolutional Neural Networks through Activation Sparsity","venue":null,"work_id":"5445b4c0-e7a7-42df-889f-d4f6808f852c","year":null},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:340378c9d6c763aba5a9a78108c455ea9733a47a74316f684b587268b16fcb0f","observation_id":"beeca131-4e2d-49ed-902a-92b74af613de","resolution":{"observed_at":"2026-05-26T21:13:04.879339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Assessing Shape Bias Property of Convolutional Neural Networks","venue":null,"work_id":"b69ae19f-0e53-4675-adeb-7ffd0b5d1add","year":2018},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:afedc28ead19166042b3270b7c6be06d93b70849a1a52f8d7ee8485a090d1613","observation_id":"6114dc8a-bd71-4a68-a79e-73bca27acd06","resolution":{"observed_at":"2026-05-26T21:13:04.896806Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shape or Texture: Understanding Discriminative Features in CNNs","venue":null,"work_id":"a31dc5ec-88da-4fc5-9d85-d4c075c001bc","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:8ff271bfe3ceab85f9e6ca527afe6cc5fbcecbee5160593cec457b60b5e07349","observation_id":"57791100-e1e2-4fa9-a4cf-a60785fad774","resolution":{"observed_at":"2026-05-26T21:13:04.903735Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Teaching deep networks to see shape: Lessons from a simplified visual world","venue":null,"work_id":"701dd586-291f-4020-aaad-74930e9e7250","year":2024},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:c15acca26c79ec42e67c12a48fb7b7bc1ae0ebceaddc41bc86e32afaf43a5b64","observation_id":"aa470b7a-9cd2-414e-8ade-8d2099968e18","resolution":{"observed_at":"2026-05-26T21:13:04.942947Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Hidden in Plain Sight: Evaluating Abstract Shape Recognition in Vision-Language Models","venue":null,"work_id":"5aea7e7f-3164-4189-ab13-5e3019ff5868","year":null},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:59bd95f15ed4e4d0cbe735f09f8113560efb81bcd03d1844a1fae0146b6bb675","observation_id":"d2fcde97-d611-444c-bc3c-1c3012733a61","resolution":{"observed_at":"2026-05-26T21:13:04.849051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Does enhanced shape bias improve neural network robustness to common corruptions?","venue":null,"work_id":"7f31cf25-964b-4f41-ae89-90dd03bea0f2","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:981568997d36d407d02af0da1c00854bbb8acfd786526cfd326222d4366fd3dd","observation_id":"2cb7a19f-cbea-46a8-a19c-dfc0004f32a0","resolution":{"observed_at":"2026-05-26T21:13:04.859032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Can Biases in ImageNet Models Explain Generalization?","venue":null,"work_id":"cf401682-339c-4f8e-8293-17d3f4ca13e8","year":null},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:84ea7b19764c747db34c4788a4db3c19c26c899b0d12977e7124168b7114904f","observation_id":"ad5cdea0-3b46-453d-adf3-0347e72f53e6","resolution":{"observed_at":"2026-05-26T21:13:04.852195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Columbia Object Image Library (COIL-100)","venue":null,"work_id":"a67314df-d668-4f0b-9548-dd89c052a0c9","year":null},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:9f3fdb9a453a77f0554be10ba2608d687b240c095c8d84d7c961338d41eae1bc","observation_id":"185171f8-f73e-4b84-a3b4-cb3c1f5eaa86","resolution":{"observed_at":"2026-05-26T21:13:04.839074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning methods for generic object recognition with invariance to pose and lighting","venue":null,"work_id":"73bfe89f-81ed-4d9a-b57f-716cf90f2f4f","year":2004},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:17f03e7c98f78d46524a92b149ca4858dd477e2359e8ebbd414c1f3fd51fbeae","observation_id":"cccf97e6-c166-424b-8360-54978f4fe279","resolution":{"observed_at":"2026-05-26T21:13:04.845486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A large-scale hierarchical multi- view RGB-D object dataset","venue":null,"work_id":"143828e9-e8fe-4945-8feb-2edeb390b848","year":2011},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:c2bcfb8990d5748aa533437826444aefc9f370a2844985e46cafabdcfe03df22","observation_id":"6255b4dd-7f7e-4eb9-b91e-ca8440a49799","resolution":{"observed_at":"2026-05-26T21:13:04.829044Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"BigBIRD: A large-scale 3D database of object instances","venue":null,"work_id":"0ce0b915-6f31-4052-8d8a-8678dec608a1","year":2014},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:2af3b7b21f6874afdaed4fedbf949b807fa95c04ae6e145025f33fc1362ae552","observation_id":"b7a7c559-cd0b-49d0-b073-2f31e62c2cad","resolution":{"observed_at":"2026-05-26T21:13:04.825616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"iLab-20M: A Large-Scale Controlled Object Dataset to Investigate Deep Learning","venue":null,"work_id":"7d4fa148-04cd-4297-a6f9-bd3e983759d3","year":2016},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:c91326f2e0db9710f553d2e850dbd9ed7ffb52c4491585b243c188c9f617664d","observation_id":"184865e2-49b3-4423-8bb6-fd37f24ea7d4","resolution":{"observed_at":"2026-05-26T21:13:04.815257Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"CORe50: A New Dataset and Benchmark for Continuous Object Recognition","venue":null,"work_id":"0f112b16-19a7-498e-a9de-2a4d9046175b","year":2017},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:5893e0edb048a37770f9fe2161a6a38dcec321f3a42447ea7f61e8a34722f2ba","observation_id":"fe1f345c-064b-4e3c-8b3e-0f05eabe6548","resolution":{"observed_at":"2026-05-26T21:13:04.818848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Objectron: A Large Scale Dataset of Object-Centric Videos in the Wild with Pose Annotations","venue":null,"work_id":"48d54cb4-a13a-4c84-a8d2-c9706c2cd190","year":2020},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:dffcf3b082fad48e754feba760ed82ce7af1392bf4ec92f0ea886d13bcc974bc","observation_id":"ff4ca511-38af-4cd2-83fc-f128a8de7c04","resolution":{"observed_at":"2026-05-26T21:13:04.822248Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Common Objects in 3D: Large-Scale Learning and Evaluation of Real-life 3D Category Reconstruction","venue":null,"work_id":"9767ca79-1e70-43c8-b717-c3295e4a539f","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:59f2cf26738970ba4dd1d6c3b8f6d95be96f08e28cf4fbba159aec5145226f03","observation_id":"dee2bcb5-60b7-4ded-8066-1c73755cb7a6","resolution":{"observed_at":"2026-05-26T21:13:04.832434Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"PUG: Photorealistic and Semantically Controllable Synthetic Data for Representation Learning","venue":null,"work_id":"28742373-121d-4ff8-88e7-28288b7d288a","year":2023},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:a32ce0aa7fb366bd9f6c994fb9ad117c1405fe4c73c931128bd086fc318dffe4","observation_id":"85acd3b9-9bc0-4d1f-9063-cf6bd6a51765","resolution":{"observed_at":"2026-05-26T21:13:04.835667Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Benchmarking Neural Network Ro- bustness to Common Corruptions and Perturbations","venue":null,"work_id":"987877ea-4619-4de5-a967-ad9cd63233b7","year":2019},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:81ac434cd371f8898b5cd06858eec10864e6491ee3464ebac0b5d5436141b410","observation_id":"942549ed-cecf-430b-88d8-353066f79cf2","resolution":{"observed_at":"2026-05-26T21:13:04.811986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Learning Robust Global Representations by Penalizing Local Predictive Power","venue":null,"work_id":"4efad05d-4b37-42ff-9205-e8ed91017846","year":2019},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:807c396592c34f53d6c997b716c6b2edeba5d9f4a520e52d54835d076217984b","observation_id":"a0d96d4e-d2b4-4f67-8d4a-6c3bd1e4b100","resolution":{"observed_at":"2026-05-26T21:13:04.805356Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"One-shot viewpoint invariance in matching novel objects","venue":null,"work_id":"540ee2d1-396f-4922-b7c1-e2c613211d2d","year":1999},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:23956832ccaa2fc67319a7ee014335fbc65de20423eaa86e336019e6be66b387","observation_id":"9da69384-7d5b-4821-a172-bd32ec26390b","resolution":{"observed_at":"2026-05-26T21:13:04.798440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On the Semantics of a Glance at a Scene","venue":null,"work_id":"1c5c1f19-1d79-472a-a780-2ed59d99f2e1","year":1981},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:81ddf1f25a07fde5f66b7938c7f76724189ff1e8ab5d83016c1e2bc266b0b37c","observation_id":"f34876b0-cb9b-4d0b-9c49-b74342f89f59","resolution":{"observed_at":"2026-05-26T21:13:04.792037Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03012","last_updated":"2015-12-09T19:42:48Z","snapshot_observed_at":"2026-07-06T04:39:20.735523Z","submitted_at":"2015-12-09T19:42:48Z","title":"ShapeNet: An Information-Rich 3D Model Repository","version":1},"cited_work":{"arxiv_id":"1512.03012","doi":"10.1111/2041-210x.12301","metadata_source":"pith","pith_arxiv_id":"1512.03012","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"ShapeNet: An Information-Rich 3D Model Repository","venue":"cs.GR","work_id":"b2ac5b60-daa9-435b-9369-12271e126edd","year":2015},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"cited_paper":"/paper/1512.03012","citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:0ea22302a65795da3874deafe327fe87cedd009e9dc7886281a43916325203c0","observation_id":"e0f00682-54b7-4b5a-886d-02fcc6ce8312","resolution":{"observed_at":"2026-05-11T21:51:11.370068Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Untangling invariant object recognition","venue":null,"work_id":"38acbe6c-c7bf-4f84-a4c1-231a457070fc","year":2007},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:c827187ba05a78564d7af6c37ed9ff7eb9d734e74c4d56ee1d25ff24b3da1f43","observation_id":"5680da5d-d30c-4d68-8972-21c735337e84","resolution":{"observed_at":"2026-05-26T21:13:04.795079Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1512.03385","last_updated":"2015-12-10T19:51:55Z","snapshot_observed_at":"2026-07-06T04:39:28.429064Z","submitted_at":"2015-12-10T19:51:55Z","title":"Deep Residual Learning for Image Recognition","version":1},"cited_work":{"arxiv_id":"1512.03385","doi":"10.48550/arxiv.1512.03385","metadata_source":"pith","pith_arxiv_id":"1512.03385","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Deep Residual Learning for Image Recognition","venue":"cs.CV","work_id":"ae9e5671-23e8-4853-82a4-699b5b8dd639","year":2015},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"cited_paper":"/paper/1512.03385","citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:121cedc40707f6eefd6eed2a77e29e8c4e5ee64627396373d4dbeea2b942c9cd","observation_id":"08f262f1-6af9-4440-8af5-56736ce10ae5","resolution":{"observed_at":"2026-05-11T21:51:11.374754Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-16T22:21:34.473166+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-16T22:21:34.473166+00:00","source":"openalex_status_cache"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"PyTorch Image Models","venue":null,"work_id":"38131d23-1cf4-4111-b7de-6e4c07c32d72","year":2019},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:d2b64be2773c1e62cb1ac61856027b7ec58b688da904d44cef413155dd5452a3","observation_id":"c753a963-cfaa-4259-95da-69f5649be994","resolution":{"observed_at":"2026-05-26T21:13:04.855496Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2002.05709","last_updated":"2020-07-01T00:09:08Z","snapshot_observed_at":"2026-07-06T08:57:07.862196Z","submitted_at":"2020-02-13T18:50:45Z","title":"A Simple Framework for Contrastive Learning of Visual Representations","version":3},"cited_work":{"arxiv_id":"2002.05709","doi":"10.48550/arxiv.2002.05709","metadata_source":"pith","pith_arxiv_id":"2002.05709","snapshot_observed_at":"2026-07-11T01:07:42.108030Z","title":"A Simple Framework for Contrastive Learning of Visual Representations","venue":"cs.LG","work_id":"77d995ce-c44e-4692-9c54-cf8ce771464a","year":2020},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"cited_paper":"/paper/2002.05709","citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:f0767a06e48b8c293a242d97745df3d3d5fbad09562514cbec4c4738957863c1","observation_id":"05170aed-4220-421a-9b6f-830507f4ed0f","resolution":{"observed_at":"2026-05-13T18:31:53.429341Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-11T01:49:38.745766+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-11T01:49:38.745766+00:00","source":"openalex_status_cache"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"DINOv2: Learning Robust Visual Fea- tures without Supervision","venue":null,"work_id":"99388f34-d133-481e-a915-a0d93199c928","year":2024},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:c9bcbad01bcec13483864028beb5da3cfadf715d9fae825aff03349bc960e085","observation_id":"f43db2ea-3707-4125-8cf4-a08837b04536","resolution":{"observed_at":"2026-05-26T21:13:04.808611Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Decoupled Contrastive Learning","venue":null,"work_id":"af3c577d-b1ba-4bf4-9c57-b2bcac90c9d1","year":2022},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:3f304ec52b3bf56c0b03e07d15b839f55cee2925a95c24ce6a310e1de7e99025","observation_id":"a484b0a0-2b3b-4fe9-acbb-9d622ee98f3b","resolution":{"observed_at":"2026-05-26T21:13:04.782382Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Unsupervised Learning of Visual Features by Contrasting Cluster Assignments","venue":null,"work_id":"6155da61-3803-47c3-94d0-fa4361fbba74","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:90e36c6b226900e807d43f72d8ce636a8aab330575098dd6b27044d81dd21e09","observation_id":"3df9575d-6919-4f95-ac79-bfc293896e0a","resolution":{"observed_at":"2026-05-26T21:13:04.789190Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"VICReg: Variance-Invariance- Covariance Regularization for Self-Supervised Learning","venue":null,"work_id":"613d95ce-63ef-45ce-aaa2-7e777680fc5c","year":2022},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:1c4b00fc5410c6576dc213b6c0a82f78e08963e0e77372f9edc55463cea54814","observation_id":"1671f66b-53c0-48d5-8fd2-a6dcd958919c","resolution":{"observed_at":"2026-05-26T21:13:04.907246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Momentum Contrast for Unsupervised Visual Representation Learning","venue":null,"work_id":"2128b3db-53f9-4231-9852-90ff103d5f94","year":2020},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:a42a93a89e53ff6859609477f700ddad96f9d40d86e44789c8eea46d4af1de7d","observation_id":"3406cd38-a4f0-457b-a986-ac5a1a8cd455","resolution":{"observed_at":"2026-05-26T21:13:04.775492Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Bootstrap your own latent: A new approach to self-supervised Learning","venue":null,"work_id":"8181544d-2a18-4f8b-97ec-93092b22b5ba","year":2020},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:bd8b7aee15515344edc1011c2262f9d8ebfc975c6095af3cfa117ec27685706e","observation_id":"de3e68fe-7353-4b79-8050-d7fefa886970","resolution":{"observed_at":"2026-05-26T21:13:04.772181Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Barlow Twins: Self-Supervised Learning via Redundancy Reduction","venue":null,"work_id":"4dc646a8-7b85-421f-935b-73b6c8dfe496","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:afc16b1612cd534a9926a7a60508956b3eb2f4288908f2521f496366a6a1a1b3","observation_id":"a921b1fd-bd52-4709-977b-ea9101c41cc5","resolution":{"observed_at":"2026-05-26T21:13:04.778797Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Emerging Properties in Self-Supervised Vision Transform- ers","venue":null,"work_id":"6fb177b7-9729-4073-8fa6-b42560d76baa","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:7a79d6a66d4c3178827e13a9debf86c4b77557df7ab36afdad193a45bd839682","observation_id":"7e7739e6-a8b7-4b8c-afa2-67d0724bca59","resolution":{"observed_at":"2026-05-26T21:13:04.785796Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.09348","last_updated":"2022-04-23T16:44:20Z","snapshot_observed_at":"2026-07-06T11:59:08.372025Z","submitted_at":"2021-10-18T14:22:19Z","title":"Understanding Dimensional Collapse in Contrastive Self-supervised Learning","version":3},"cited_work":{"arxiv_id":"2110.09348","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2110.09348","snapshot_observed_at":"2026-07-04T08:29:41.975441Z","title":"Understanding dimen- sional collapse in contrastive self-supervised learning","venue":null,"work_id":"d3155a4a-150d-4aa2-a978-3ee0e39151b2","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"cited_paper":"/paper/2110.09348","citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:698b7b1bd76c41fff7cca59b0d803c26f8b32d2736fbcda1f487039445a8248c","observation_id":"6a7d62ae-ba4e-4e99-808d-f19acc8b957e","resolution":{"observed_at":"2026-05-11T21:51:11.319046Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.08377","last_updated":"2020-10-16T13:28:13Z","snapshot_observed_at":"2026-07-06T10:05:07.321675Z","submitted_at":"2020-10-16T13:28:13Z","title":"On the surprising similarities between supervised and self-supervised models","version":1},"cited_work":{"arxiv_id":"2010.08377","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.08377","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"On the surprising similarities between supervised and self-supervised models","venue":null,"work_id":"a483720c-0c04-4d78-b74b-13e9849a9627","year":2010},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"cited_paper":"/paper/2010.08377","citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:d0d8ef7755572b8d76288ff63f46979437d029228db627ab6ca28ce1c3311833","observation_id":"999c7a79-4081-4f02-84b5-68b3b4ad7c36","resolution":{"observed_at":"2026-05-11T21:51:11.420036Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"ResNet strikes back: An improved training procedure in timm","venue":null,"work_id":"f1e3796a-4160-4255-b975-394894a132a7","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:0c0e0325aa32e183d2e713cf52ee18e44d5293bf1b0882195d994c2f5cec2db6","observation_id":"9421a137-7678-4557-bbb1-c28b49094cb1","resolution":{"observed_at":"2026-05-26T21:13:04.762637Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2010.11929","last_updated":"2021-06-03T13:08:56Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-10-22T17:55:59Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","version":2},"cited_work":{"arxiv_id":"2010.11929","doi":"10.1175/jcli-d-22-0357.1","metadata_source":"pith","pith_arxiv_id":"2010.11929","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale","venue":"cs.CV","work_id":"e96730e3-129b-4db6-b981-15ab7932e297","year":2020},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"cited_paper":"/paper/2010.11929","citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:e633dbe4bfc0c1846f2fad6733fabac236dd11a2048c6ec7b9c247f409778fed","observation_id":"d04692b6-8f12-4cfd-9990-bf88952516d0","resolution":{"observed_at":"2026-05-11T21:51:11.438865Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"A ConvNet for the 2020s","venue":null,"work_id":"c3ee8b0e-97e2-4e8c-a883-a2a29d01f452","year":2022},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:11df7daf36be5f6d62feb950067931a17aaff95b18803d9dbdd1bebc5cb0f297","observation_id":"ee5a151a-f694-4a93-9a52-dddcef02fa6a","resolution":{"observed_at":"2026-05-26T21:13:04.765745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"ConvFormer: Combining CNN and Transformer for Medical Image Segmentation","venue":null,"work_id":"f4317aff-afe3-4d7d-ae0e-3a75700d2be7","year":2022},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:4e13df2099f72cd313812dd77d08af0da9784a9f3639cf66fde3bba1c128404a","observation_id":"66bcda02-ed59-4d03-a470-34c2a99cf5b3","resolution":{"observed_at":"2026-05-26T21:13:04.759351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09681","last_updated":"2021-06-18T15:33:31Z","snapshot_observed_at":"2026-07-06T11:20:25.833561Z","submitted_at":"2021-06-17T17:33:35Z","title":"XCiT: Cross-Covariance Image Transformers","version":2},"cited_work":{"arxiv_id":"2106.09681","doi":"10.48550/arxiv.2106.09681","metadata_source":"arxiv_reference","pith_arxiv_id":"2106.09681","snapshot_observed_at":"2026-07-10T06:15:00.866473Z","title":"Xcit: Cross-covariance image transformers","venue":null,"work_id":"905f2cd4-52d0-43a8-98b5-bc26f144e4e4","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"cited_paper":"/paper/2106.09681","citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:8ec908eaffc2b344bc6a2bce96f38a6a174e44d6c3b5d68ceefbddd2715ef757","observation_id":"ee89778c-1346-499d-96ee-f4131f3bb937","resolution":{"observed_at":"2026-05-11T21:51:11.428456Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-05-22T13:22:34.184109+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-22T13:22:34.184109+00:00","source":"openalex_status_cache"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Going deeper with Image Transformers","venue":null,"work_id":"b3ca00e1-e2f9-45af-873f-c172addd8a06","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:217a7ff17abb2c375be2b7f7e99fe0e4b5b8aa7962216b83b281cfae2fb3a5e1","observation_id":"74ad036a-b62f-4c9d-a752-cb4e5551e4fc","resolution":{"observed_at":"2026-05-26T21:13:04.768886Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Masked Autoencoders Are Scalable Vision Learners","venue":null,"work_id":"79d93d5a-79f8-4d2b-af40-3f4e7cfd8b64","year":2021},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:89f63ddbb1741ce66c43dc86520d6a846e4f737544ca6443d797d7c7a7a2b3cc","observation_id":"9a4a6bb9-678a-4e10-ab88-8652ec3f022b","resolution":{"observed_at":"2026-05-26T21:13:04.893107Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Shortcut learning in deep neural networks","venue":null,"work_id":"bce6c93e-1c43-4d56-8f6b-ae4c1b3895e0","year":2020},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:477b6e48720d78cf49253745f51d904ed54b77ce6548df242a3622cd077d7bfe","observation_id":"de225720-f18c-4f3a-b323-2476520fd08e","resolution":{"observed_at":"2026-05-26T21:13:04.801916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"ImageNet-OOD: Deciphering Modern Out-of-Distribution Detection Algorithms","venue":null,"work_id":"b7c80914-c869-4301-851d-4438c303d4f8","year":2024},"citing_paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-08T04:13:28.233483Z"},"links":{"citing_paper":"/paper/2604.25065"},"observation_digest":"sha256:b5f226383212610a926ea7171952677ef304eb2c497a0df26688f087c383b652","observation_id":"ba6877da-da00-48b9-9e0a-c6cda9978329","resolution":{"observed_at":"2026-05-26T21:13:04.842277Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-07-21T06:31:05.380196+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2604.25065","last_updated":"2026-04-27T23:42:52Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-07-06T23:10:57.164248Z","submitted_at":"2026-04-27T23:42:52Z","title":"ShapeY: A Principled Framework for Measuring Shape Recognition Capacity via Nearest-Neighbor Matching"},"reference_resolution":{"displayed":55,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":0,"verified_exact":8,"verified_fuzzy":46},"total_outbound_references":55},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-07-21T06:31:05.380196+00:00","source":"crossref"},{"observed_at":"2026-07-21T06:31:00.184556+00:00","source":"retraction_watch"}],"thesis":"As of 22 July 2026, this Paper Citation Record lists 55 of 55 outbound references and 0 inbound Pith citation observations for arXiv:2604.25065."}