{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KM3GPU4MZ2IYUFIVJUNYJLBO27","short_pith_number":"pith:KM3GPU4M","schema_version":"1.0","canonical_sha256":"533667d38cce918a15154d1b84ac2ed7d76ef71c577916d96f425a83c4607726","source":{"kind":"arxiv","id":"2508.18226","version":1},"attestation_state":"computed","paper":{"title":"Disentangling the Factors of Convergence between Brains and Computer Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.NC"],"primary_cat":"cs.AI","authors_text":"Camille Couprie, Huy V. Vo, Jean-R\\'emi King, Jos\\'ephine Raugel, Marc Szafraniec, Patrick Labatut, Piotr Bojanowski, Valentin Wyart","submitted_at":"2025-08-25T17:23:27Z","abstract_excerpt":"Many AI models trained on natural images develop representations that resemble those of the human brain. However, the factors that drive this brain-model similarity remain poorly understood. To disentangle how the model, training and data independently lead a neural network to develop brain-like representations, we trained a family of self-supervised vision transformers (DINOv3) that systematically varied these different factors. We compare their representations of images to those of the human brain recorded with both fMRI and MEG, providing high resolution in spatial and temporal analyses. We"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.18226","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-25T17:23:27Z","cross_cats_sorted":["q-bio.NC"],"title_canon_sha256":"742095abb3ea0914ddad9555b78dbb11a4acda008645c8777391400696df5a0a","abstract_canon_sha256":"83f3e1e4a17466fbd95921d2aef87248e0197b99ea639400ab635286fe6417be"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:55.818533Z","signature_b64":"jazkerYSohKbmOsTGab//XT3szB32g861zPYP5trC7wZHAWyuaQSoCWj87lu6Q/fd+ufS2TaSgRQTAmid2XrDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"533667d38cce918a15154d1b84ac2ed7d76ef71c577916d96f425a83c4607726","last_reissued_at":"2026-07-05T11:58:55.818019Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:55.818019Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Disentangling the Factors of Convergence between Brains and Computer Vision Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.NC"],"primary_cat":"cs.AI","authors_text":"Camille Couprie, Huy V. Vo, Jean-R\\'emi King, Jos\\'ephine Raugel, Marc Szafraniec, Patrick Labatut, Piotr Bojanowski, Valentin Wyart","submitted_at":"2025-08-25T17:23:27Z","abstract_excerpt":"Many AI models trained on natural images develop representations that resemble those of the human brain. However, the factors that drive this brain-model similarity remain poorly understood. To disentangle how the model, training and data independently lead a neural network to develop brain-like representations, we trained a family of self-supervised vision transformers (DINOv3) that systematically varied these different factors. We compare their representations of images to those of the human brain recorded with both fMRI and MEG, providing high resolution in spatial and temporal analyses. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.18226","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.18226/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.18226","created_at":"2026-07-05T11:58:55.818077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.18226v1","created_at":"2026-07-05T11:58:55.818077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.18226","created_at":"2026-07-05T11:58:55.818077+00:00"},{"alias_kind":"pith_short_12","alias_value":"KM3GPU4MZ2IY","created_at":"2026-07-05T11:58:55.818077+00:00"},{"alias_kind":"pith_short_16","alias_value":"KM3GPU4MZ2IYUFIV","created_at":"2026-07-05T11:58:55.818077+00:00"},{"alias_kind":"pith_short_8","alias_value":"KM3GPU4M","created_at":"2026-07-05T11:58:55.818077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28693","citing_title":"Misalignment Between Backpropagation and the Hierarchy of Brain Responses to Images","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.22570","citing_title":"CanViT: Toward Active-Vision Foundation Models","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06017","citing_title":"Toward Aristotelian Medical Representations: Backpropagation-Free Layer-wise Analysis for Interpretable Generalized Metric Learning on MedMNIST","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KM3GPU4MZ2IYUFIVJUNYJLBO27","json":"https://pith.science/pith/KM3GPU4MZ2IYUFIVJUNYJLBO27.json","graph_json":"https://pith.science/api/pith-number/KM3GPU4MZ2IYUFIVJUNYJLBO27/graph.json","events_json":"https://pith.science/api/pith-number/KM3GPU4MZ2IYUFIVJUNYJLBO27/events.json","paper":"https://pith.science/paper/KM3GPU4M"},"agent_actions":{"view_html":"https://pith.science/pith/KM3GPU4MZ2IYUFIVJUNYJLBO27","download_json":"https://pith.science/pith/KM3GPU4MZ2IYUFIVJUNYJLBO27.json","view_paper":"https://pith.science/paper/KM3GPU4M","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.18226&json=true","fetch_graph":"https://pith.science/api/pith-number/KM3GPU4MZ2IYUFIVJUNYJLBO27/graph.json","fetch_events":"https://pith.science/api/pith-number/KM3GPU4MZ2IYUFIVJUNYJLBO27/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KM3GPU4MZ2IYUFIVJUNYJLBO27/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KM3GPU4MZ2IYUFIVJUNYJLBO27/action/storage_attestation","attest_author":"https://pith.science/pith/KM3GPU4MZ2IYUFIVJUNYJLBO27/action/author_attestation","sign_citation":"https://pith.science/pith/KM3GPU4MZ2IYUFIVJUNYJLBO27/action/citation_signature","submit_replication":"https://pith.science/pith/KM3GPU4MZ2IYUFIVJUNYJLBO27/action/replication_record"}},"created_at":"2026-07-05T11:58:55.818077+00:00","updated_at":"2026-07-05T11:58:55.818077+00:00"}