{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TEMAG5MX25CYVXIWXHSYIVJ3LX","short_pith_number":"pith:TEMAG5MX","schema_version":"1.0","canonical_sha256":"9918037597d7458add16b9e584553b5df492c82325c013820e63073f689a5367","source":{"kind":"arxiv","id":"2501.11653","version":3},"attestation_state":"computed","paper":{"title":"Dynamic Scene Understanding from Vision-Language Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hadar Averbuch-Elor, Morris Alper, Shahaf Pruss","submitted_at":"2025-01-20T18:33:46Z","abstract_excerpt":"Images depicting complex, dynamic scenes are challenging to parse automatically, requiring both high-level comprehension of the overall situation and fine-grained identification of participating entities and their interactions. Current approaches use distinct methods tailored to sub-tasks such as Situation Recognition and detection of Human-Human and Human-Object Interactions. However, recent advances in image understanding have often leveraged web-scale vision-language (V&L) representations to obviate task-specific engineering. In this work, we propose a framework for dynamic scene understand"},"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":"2501.11653","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T18:33:46Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3428c7e22956ab78915088f3d35656c0426330613645a60d0ce1787d91cc4ceb","abstract_canon_sha256":"1aed932a94a09b03725d4b310755b30d85ef9f532c996ade8c08c1722fc175a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:58:22.597460Z","signature_b64":"aMIZruMy9H0ggtK0LHCUsj1DR10JU7/Dtx5mu938uTMDjPkEHUuFTyzBsfckmAHldeuh6OS6SaotDpPwxL2MDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9918037597d7458add16b9e584553b5df492c82325c013820e63073f689a5367","last_reissued_at":"2026-07-05T10:58:22.596908Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:58:22.596908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dynamic Scene Understanding from Vision-Language Representations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Hadar Averbuch-Elor, Morris Alper, Shahaf Pruss","submitted_at":"2025-01-20T18:33:46Z","abstract_excerpt":"Images depicting complex, dynamic scenes are challenging to parse automatically, requiring both high-level comprehension of the overall situation and fine-grained identification of participating entities and their interactions. Current approaches use distinct methods tailored to sub-tasks such as Situation Recognition and detection of Human-Human and Human-Object Interactions. However, recent advances in image understanding have often leveraged web-scale vision-language (V&L) representations to obviate task-specific engineering. In this work, we propose a framework for dynamic scene understand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11653","kind":"arxiv","version":3},"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/2501.11653/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":"2501.11653","created_at":"2026-07-05T10:58:22.596968+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11653v3","created_at":"2026-07-05T10:58:22.596968+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11653","created_at":"2026-07-05T10:58:22.596968+00:00"},{"alias_kind":"pith_short_12","alias_value":"TEMAG5MX25CY","created_at":"2026-07-05T10:58:22.596968+00:00"},{"alias_kind":"pith_short_16","alias_value":"TEMAG5MX25CYVXIW","created_at":"2026-07-05T10:58:22.596968+00:00"},{"alias_kind":"pith_short_8","alias_value":"TEMAG5MX","created_at":"2026-07-05T10:58:22.596968+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/TEMAG5MX25CYVXIWXHSYIVJ3LX","json":"https://pith.science/pith/TEMAG5MX25CYVXIWXHSYIVJ3LX.json","graph_json":"https://pith.science/api/pith-number/TEMAG5MX25CYVXIWXHSYIVJ3LX/graph.json","events_json":"https://pith.science/api/pith-number/TEMAG5MX25CYVXIWXHSYIVJ3LX/events.json","paper":"https://pith.science/paper/TEMAG5MX"},"agent_actions":{"view_html":"https://pith.science/pith/TEMAG5MX25CYVXIWXHSYIVJ3LX","download_json":"https://pith.science/pith/TEMAG5MX25CYVXIWXHSYIVJ3LX.json","view_paper":"https://pith.science/paper/TEMAG5MX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11653&json=true","fetch_graph":"https://pith.science/api/pith-number/TEMAG5MX25CYVXIWXHSYIVJ3LX/graph.json","fetch_events":"https://pith.science/api/pith-number/TEMAG5MX25CYVXIWXHSYIVJ3LX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TEMAG5MX25CYVXIWXHSYIVJ3LX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TEMAG5MX25CYVXIWXHSYIVJ3LX/action/storage_attestation","attest_author":"https://pith.science/pith/TEMAG5MX25CYVXIWXHSYIVJ3LX/action/author_attestation","sign_citation":"https://pith.science/pith/TEMAG5MX25CYVXIWXHSYIVJ3LX/action/citation_signature","submit_replication":"https://pith.science/pith/TEMAG5MX25CYVXIWXHSYIVJ3LX/action/replication_record"}},"created_at":"2026-07-05T10:58:22.596968+00:00","updated_at":"2026-07-05T10:58:22.596968+00:00"}