{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UGRH6HAFZQVI6IAI6U7ODTIZN2","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":"2fda980eb4f122a283796287a96aff0474c4eac8ebd4e229d0b6f81c41d3194d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T21:40:27Z","title_canon_sha256":"d9a3d803b29153f5fda8461276bb7a73cef90802eaf662c39d2e03e0db78d17d"},"schema_version":"1.0","source":{"id":"2403.11021","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11021","created_at":"2026-07-05T09:43:28Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11021v3","created_at":"2026-07-05T09:43:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11021","created_at":"2026-07-05T09:43:28Z"},{"alias_kind":"pith_short_12","alias_value":"UGRH6HAFZQVI","created_at":"2026-07-05T09:43:28Z"},{"alias_kind":"pith_short_16","alias_value":"UGRH6HAFZQVI6IAI","created_at":"2026-07-05T09:43:28Z"},{"alias_kind":"pith_short_8","alias_value":"UGRH6HAF","created_at":"2026-07-05T09:43:28Z"}],"graph_snapshots":[{"event_id":"sha256:83846a9cfbe845cd82c551d3e4c73efc841f9aa39af2be46678a8ebd4e253de7","target":"graph","created_at":"2026-07-05T09:43:28Z","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/2403.11021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The unprecedented surge in video data production in recent years necessitates efficient tools to extract meaningful frames from videos for downstream tasks. Long-term temporal reasoning is a key desideratum for frame retrieval systems. While state-of-the-art foundation models, like VideoLLaMA and ViCLIP, are proficient in short-term semantic understanding, they surprisingly fail at long-term reasoning across frames. A key reason for this failure is that they intertwine per-frame perception and temporal reasoning into a single deep network. Hence, decoupling but co-designing semantic understand","authors_text":"Harsh Goel, Minkyu Choi, Mohammad Omama, Sahil Shah, Sandeep Chinchali, Yunhao Yang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T21:40:27Z","title":"Towards Neuro-Symbolic Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11021","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:be04f1c2d38aa3bae1800768ce566505cdda45336b8f868f314b6dc35fc86ae5","target":"record","created_at":"2026-07-05T09:43:28Z","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":"2fda980eb4f122a283796287a96aff0474c4eac8ebd4e229d0b6f81c41d3194d","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T21:40:27Z","title_canon_sha256":"d9a3d803b29153f5fda8461276bb7a73cef90802eaf662c39d2e03e0db78d17d"},"schema_version":"1.0","source":{"id":"2403.11021","kind":"arxiv","version":3}},"canonical_sha256":"a1a27f1c05cc2a8f2008f53ee1cd196ea3b605a8ad5e84b976d8f7dcdbcb9c3a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1a27f1c05cc2a8f2008f53ee1cd196ea3b605a8ad5e84b976d8f7dcdbcb9c3a","first_computed_at":"2026-07-05T09:43:28.085346Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:43:28.085346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CzzDSpFXFHPajSuuysASTmbERlnCYCcoHme48xmOURlnJI3FPiA6efJb+txVxrmAXs3hYBprTJm1cZNC/CGICA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:43:28.085845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11021","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be04f1c2d38aa3bae1800768ce566505cdda45336b8f868f314b6dc35fc86ae5","sha256:83846a9cfbe845cd82c551d3e4c73efc841f9aa39af2be46678a8ebd4e253de7"],"state_sha256":"a0973a8cf55a08a87ee09acfb71d930be7be20794216acb3d546f12db6b48df9"}