{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UGRH6HAFZQVI6IAI6U7ODTIZN2","short_pith_number":"pith:UGRH6HAF","schema_version":"1.0","canonical_sha256":"a1a27f1c05cc2a8f2008f53ee1cd196ea3b605a8ad5e84b976d8f7dcdbcb9c3a","source":{"kind":"arxiv","id":"2403.11021","version":3},"attestation_state":"computed","paper":{"title":"Towards Neuro-Symbolic Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Harsh Goel, Minkyu Choi, Mohammad Omama, Sahil Shah, Sandeep Chinchali, Yunhao Yang","submitted_at":"2024-03-16T21:40:27Z","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"},"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":"2403.11021","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-16T21:40:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d9a3d803b29153f5fda8461276bb7a73cef90802eaf662c39d2e03e0db78d17d","abstract_canon_sha256":"2fda980eb4f122a283796287a96aff0474c4eac8ebd4e229d0b6f81c41d3194d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:28.085845Z","signature_b64":"CzzDSpFXFHPajSuuysASTmbERlnCYCcoHme48xmOURlnJI3FPiA6efJb+txVxrmAXs3hYBprTJm1cZNC/CGICA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1a27f1c05cc2a8f2008f53ee1cd196ea3b605a8ad5e84b976d8f7dcdbcb9c3a","last_reissued_at":"2026-07-05T09:43:28.085346Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:28.085346Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Neuro-Symbolic Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Harsh Goel, Minkyu Choi, Mohammad Omama, Sahil Shah, Sandeep Chinchali, Yunhao Yang","submitted_at":"2024-03-16T21:40:27Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11021","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/2403.11021/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":"2403.11021","created_at":"2026-07-05T09:43:28.085404+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.11021v3","created_at":"2026-07-05T09:43:28.085404+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11021","created_at":"2026-07-05T09:43:28.085404+00:00"},{"alias_kind":"pith_short_12","alias_value":"UGRH6HAFZQVI","created_at":"2026-07-05T09:43:28.085404+00:00"},{"alias_kind":"pith_short_16","alias_value":"UGRH6HAFZQVI6IAI","created_at":"2026-07-05T09:43:28.085404+00:00"},{"alias_kind":"pith_short_8","alias_value":"UGRH6HAF","created_at":"2026-07-05T09:43:28.085404+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.05519","citing_title":"Real-Time Privacy Preservation for Robot Visual Perception","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UGRH6HAFZQVI6IAI6U7ODTIZN2","json":"https://pith.science/pith/UGRH6HAFZQVI6IAI6U7ODTIZN2.json","graph_json":"https://pith.science/api/pith-number/UGRH6HAFZQVI6IAI6U7ODTIZN2/graph.json","events_json":"https://pith.science/api/pith-number/UGRH6HAFZQVI6IAI6U7ODTIZN2/events.json","paper":"https://pith.science/paper/UGRH6HAF"},"agent_actions":{"view_html":"https://pith.science/pith/UGRH6HAFZQVI6IAI6U7ODTIZN2","download_json":"https://pith.science/pith/UGRH6HAFZQVI6IAI6U7ODTIZN2.json","view_paper":"https://pith.science/paper/UGRH6HAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.11021&json=true","fetch_graph":"https://pith.science/api/pith-number/UGRH6HAFZQVI6IAI6U7ODTIZN2/graph.json","fetch_events":"https://pith.science/api/pith-number/UGRH6HAFZQVI6IAI6U7ODTIZN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UGRH6HAFZQVI6IAI6U7ODTIZN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UGRH6HAFZQVI6IAI6U7ODTIZN2/action/storage_attestation","attest_author":"https://pith.science/pith/UGRH6HAFZQVI6IAI6U7ODTIZN2/action/author_attestation","sign_citation":"https://pith.science/pith/UGRH6HAFZQVI6IAI6U7ODTIZN2/action/citation_signature","submit_replication":"https://pith.science/pith/UGRH6HAFZQVI6IAI6U7ODTIZN2/action/replication_record"}},"created_at":"2026-07-05T09:43:28.085404+00:00","updated_at":"2026-07-05T09:43:28.085404+00:00"}