{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OZ4YNC6Q3ISDAD42K43GRXHYUD","short_pith_number":"pith:OZ4YNC6Q","schema_version":"1.0","canonical_sha256":"7679868bd0da24300f9a573668dcf8a0dc46cbf95263be998d66ec2c64ee1500","source":{"kind":"arxiv","id":"2510.01502","version":2},"attestation_state":"computed","paper":{"title":"Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Kathy Garcia, Leyla Isik","submitted_at":"2025-10-01T22:29:55Z","abstract_excerpt":"Current video foundation models, including the strongest self-supervised models such as V-JEPA2, fail to capture how humans organize social information in dynamic scenes. For example, across a range of diverse vision models tested, none were able to predict human similarity judgments to social video clips as well as a sentence embedding model of the caption text (MPNet). We show this gap in vision model performance can be closed by a compact behavioral supervisory signal. We introduce behavioral geometric supervision (BGS): a hybrid objective that constrains local and global pairwise embedding"},"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":"2510.01502","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"q-bio.NC","submitted_at":"2025-10-01T22:29:55Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"ee4763c59c4f33073cbf328524ce7dfee0fc49a0ac81e9b3cc73f189a76bcab2","abstract_canon_sha256":"cd83764ad39491d25427af3f3a93079305fb063f81a85c00052408753ed76840"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:12.109279Z","signature_b64":"EL9CNFNuxzVDzaQVcSRGmBl5+rXKZqQnsOZqBSujDqMqp4rV1UNHdCsKPMDF2ycxDf+HZ9qjbImLFQoomi9ECw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7679868bd0da24300f9a573668dcf8a0dc46cbf95263be998d66ec2c64ee1500","last_reissued_at":"2026-05-18T03:10:12.108539Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:12.108539Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Behavioral Geometric Supervision Aligns Video Foundation Models with Human Social Perception","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"q-bio.NC","authors_text":"Kathy Garcia, Leyla Isik","submitted_at":"2025-10-01T22:29:55Z","abstract_excerpt":"Current video foundation models, including the strongest self-supervised models such as V-JEPA2, fail to capture how humans organize social information in dynamic scenes. For example, across a range of diverse vision models tested, none were able to predict human similarity judgments to social video clips as well as a sentence embedding model of the caption text (MPNet). We show this gap in vision model performance can be closed by a compact behavioral supervisory signal. We introduce behavioral geometric supervision (BGS): a hybrid objective that constrains local and global pairwise embedding"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.01502","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2510.01502","created_at":"2026-05-18T03:10:12.108661+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.01502v2","created_at":"2026-05-18T03:10:12.108661+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.01502","created_at":"2026-05-18T03:10:12.108661+00:00"},{"alias_kind":"pith_short_12","alias_value":"OZ4YNC6Q3ISD","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"OZ4YNC6Q3ISDAD42","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"OZ4YNC6Q","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.07541","citing_title":"Multimodal Large Language Models as Synthetic Participants in Video-Based Studies: An Evaluation","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OZ4YNC6Q3ISDAD42K43GRXHYUD","json":"https://pith.science/pith/OZ4YNC6Q3ISDAD42K43GRXHYUD.json","graph_json":"https://pith.science/api/pith-number/OZ4YNC6Q3ISDAD42K43GRXHYUD/graph.json","events_json":"https://pith.science/api/pith-number/OZ4YNC6Q3ISDAD42K43GRXHYUD/events.json","paper":"https://pith.science/paper/OZ4YNC6Q"},"agent_actions":{"view_html":"https://pith.science/pith/OZ4YNC6Q3ISDAD42K43GRXHYUD","download_json":"https://pith.science/pith/OZ4YNC6Q3ISDAD42K43GRXHYUD.json","view_paper":"https://pith.science/paper/OZ4YNC6Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.01502&json=true","fetch_graph":"https://pith.science/api/pith-number/OZ4YNC6Q3ISDAD42K43GRXHYUD/graph.json","fetch_events":"https://pith.science/api/pith-number/OZ4YNC6Q3ISDAD42K43GRXHYUD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OZ4YNC6Q3ISDAD42K43GRXHYUD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OZ4YNC6Q3ISDAD42K43GRXHYUD/action/storage_attestation","attest_author":"https://pith.science/pith/OZ4YNC6Q3ISDAD42K43GRXHYUD/action/author_attestation","sign_citation":"https://pith.science/pith/OZ4YNC6Q3ISDAD42K43GRXHYUD/action/citation_signature","submit_replication":"https://pith.science/pith/OZ4YNC6Q3ISDAD42K43GRXHYUD/action/replication_record"}},"created_at":"2026-05-18T03:10:12.108661+00:00","updated_at":"2026-05-18T03:10:12.108661+00:00"}