{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TEMAG5MX25CYVXIWXHSYIVJ3LX","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1aed932a94a09b03725d4b310755b30d85ef9f532c996ade8c08c1722fc175a7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T18:33:46Z","title_canon_sha256":"3428c7e22956ab78915088f3d35656c0426330613645a60d0ce1787d91cc4ceb"},"schema_version":"1.0","source":{"id":"2501.11653","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.11653","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"arxiv_version","alias_value":"2501.11653v3","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11653","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"pith_short_12","alias_value":"TEMAG5MX25CY","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"pith_short_16","alias_value":"TEMAG5MX25CYVXIW","created_at":"2026-07-05T10:58:22Z"},{"alias_kind":"pith_short_8","alias_value":"TEMAG5MX","created_at":"2026-07-05T10:58:22Z"}],"graph_snapshots":[{"event_id":"sha256:9b514a1d860c0487c17449bb8beb1b1575a6a888b1fda1e9686c7071c6a3cbcf","target":"graph","created_at":"2026-07-05T10:58:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2501.11653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hadar Averbuch-Elor, Morris Alper, Shahaf Pruss","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T18:33:46Z","title":"Dynamic Scene Understanding from Vision-Language Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11653","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e48663831cd2e9a9953c4227846bd6b64f71d4aef02675a4ffab699846492b21","target":"record","created_at":"2026-07-05T10:58:22Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1aed932a94a09b03725d4b310755b30d85ef9f532c996ade8c08c1722fc175a7","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-20T18:33:46Z","title_canon_sha256":"3428c7e22956ab78915088f3d35656c0426330613645a60d0ce1787d91cc4ceb"},"schema_version":"1.0","source":{"id":"2501.11653","kind":"arxiv","version":3}},"canonical_sha256":"9918037597d7458add16b9e584553b5df492c82325c013820e63073f689a5367","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9918037597d7458add16b9e584553b5df492c82325c013820e63073f689a5367","first_computed_at":"2026-07-05T10:58:22.596908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:58:22.596908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aMIZruMy9H0ggtK0LHCUsj1DR10JU7/Dtx5mu938uTMDjPkEHUuFTyzBsfckmAHldeuh6OS6SaotDpPwxL2MDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:58:22.597460Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.11653","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e48663831cd2e9a9953c4227846bd6b64f71d4aef02675a4ffab699846492b21","sha256:9b514a1d860c0487c17449bb8beb1b1575a6a888b1fda1e9686c7071c6a3cbcf"],"state_sha256":"d33a3edb90561a87ec30db563840ad41dab1b49787f1ecf65ebc57c565948010"}