{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YIXQYKPCYRFMY254O7GDMFSWWS","short_pith_number":"pith:YIXQYKPC","schema_version":"1.0","canonical_sha256":"c22f0c29e2c44acc6bbc77cc361656b489f8d74f111d33a2381c54f0cf0d4097","source":{"kind":"arxiv","id":"2606.09646","version":1},"attestation_state":"computed","paper":{"title":"Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Francesco Massafra, Ippokratis Pantelidis, Mohammadreza Salehi, Niccol\\`o Caselli, Salvatore Lo Sardo, Samuele Punzo","submitted_at":"2026-06-08T15:40:32Z","abstract_excerpt":"We study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how this information varies across model families, layers, and probe types. Using frozen-feature probing on IntPhys2 and Minimal Video Pairs (MVP), we compare predictive joint-embedding models (V-JEPA), masked reconstruction models (VideoMAE), and a diffusion-based video generator (LTX-Video). V-JEPA achieves the strongest overall results across benchmarks, especially with probes that model temporal dynamics, while VideoMAE remains competitive and LTX-Video recovers wea"},"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":"2606.09646","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-08T15:40:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"dc49f4c7514aafa7d25e67aa1a91cc3c4f62e7e6d991d1e15cb33edbec28e909","abstract_canon_sha256":"a2efcf0e6e90bb899c10fc9faf57d31e76c448ca1e87d1f7faed75a0ea263ebe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:09:01.153484Z","signature_b64":"ScrGLVm9b5xo0aJnAfVQkC8BHwIushZHjVj+B0SQzViBCKdnQw75c77ZcX3WcA40aN4zl9+ZFKRLpoMMEI1cCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c22f0c29e2c44acc6bbc77cc361656b489f8d74f111d33a2381c54f0cf0d4097","last_reissued_at":"2026-06-09T02:09:01.152633Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:09:01.152633Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Do Video Foundation Models Understand Intuitive Physics? A Layerwise Probing Analysis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Francesco Massafra, Ippokratis Pantelidis, Mohammadreza Salehi, Niccol\\`o Caselli, Salvatore Lo Sardo, Samuele Punzo","submitted_at":"2026-06-08T15:40:32Z","abstract_excerpt":"We study whether pretrained video foundation models encode intuitive-physics information in their frozen representations, and how this information varies across model families, layers, and probe types. Using frozen-feature probing on IntPhys2 and Minimal Video Pairs (MVP), we compare predictive joint-embedding models (V-JEPA), masked reconstruction models (VideoMAE), and a diffusion-based video generator (LTX-Video). V-JEPA achieves the strongest overall results across benchmarks, especially with probes that model temporal dynamics, while VideoMAE remains competitive and LTX-Video recovers wea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09646","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/2606.09646/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":"2606.09646","created_at":"2026-06-09T02:09:01.152769+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09646v1","created_at":"2026-06-09T02:09:01.152769+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09646","created_at":"2026-06-09T02:09:01.152769+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIXQYKPCYRFM","created_at":"2026-06-09T02:09:01.152769+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIXQYKPCYRFMY254","created_at":"2026-06-09T02:09:01.152769+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIXQYKPC","created_at":"2026-06-09T02:09:01.152769+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIXQYKPCYRFMY254O7GDMFSWWS","json":"https://pith.science/pith/YIXQYKPCYRFMY254O7GDMFSWWS.json","graph_json":"https://pith.science/api/pith-number/YIXQYKPCYRFMY254O7GDMFSWWS/graph.json","events_json":"https://pith.science/api/pith-number/YIXQYKPCYRFMY254O7GDMFSWWS/events.json","paper":"https://pith.science/paper/YIXQYKPC"},"agent_actions":{"view_html":"https://pith.science/pith/YIXQYKPCYRFMY254O7GDMFSWWS","download_json":"https://pith.science/pith/YIXQYKPCYRFMY254O7GDMFSWWS.json","view_paper":"https://pith.science/paper/YIXQYKPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09646&json=true","fetch_graph":"https://pith.science/api/pith-number/YIXQYKPCYRFMY254O7GDMFSWWS/graph.json","fetch_events":"https://pith.science/api/pith-number/YIXQYKPCYRFMY254O7GDMFSWWS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIXQYKPCYRFMY254O7GDMFSWWS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIXQYKPCYRFMY254O7GDMFSWWS/action/storage_attestation","attest_author":"https://pith.science/pith/YIXQYKPCYRFMY254O7GDMFSWWS/action/author_attestation","sign_citation":"https://pith.science/pith/YIXQYKPCYRFMY254O7GDMFSWWS/action/citation_signature","submit_replication":"https://pith.science/pith/YIXQYKPCYRFMY254O7GDMFSWWS/action/replication_record"}},"created_at":"2026-06-09T02:09:01.152769+00:00","updated_at":"2026-06-09T02:09:01.152769+00:00"}