{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RRH72DYQZCZYRZNJLSIQCH3PZ6","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":"29ca40c7cc2f8f6142da4b206db7573e1b123ed07f17352e6411e067080fa967","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-05T10:30:38Z","title_canon_sha256":"b111ebe3179dba5e63cafa545af506483b2d8340545aa9d3ecb100276988665b"},"schema_version":"1.0","source":{"id":"2404.04007","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.04007","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"arxiv_version","alias_value":"2404.04007v1","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04007","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"pith_short_12","alias_value":"RRH72DYQZCZY","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"pith_short_16","alias_value":"RRH72DYQZCZYRZNJ","created_at":"2026-07-05T08:04:44Z"},{"alias_kind":"pith_short_8","alias_value":"RRH72DYQ","created_at":"2026-07-05T08:04:44Z"}],"graph_snapshots":[{"event_id":"sha256:2d27b10d4e9064fa96b8cdb692bab6ed1b28bbf59670235e22ddac2a487b053b","target":"graph","created_at":"2026-07-05T08:04:44Z","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/2404.04007/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Compositional spatio-temporal reasoning poses a significant challenge in the field of video question answering (VideoQA). Existing approaches struggle to establish effective symbolic reasoning structures, which are crucial for answering compositional spatio-temporal questions. To address this challenge, we propose a neural-symbolic framework called Neural-Symbolic VideoQA (NS-VideoQA), specifically designed for real-world VideoQA tasks. The uniqueness and superiority of NS-VideoQA are two-fold: 1) It proposes a Scene Parser Network (SPN) to transform static-dynamic video scenes into Symbolic R","authors_text":"Guanglu Sun, Jin Qiu, Lili Liang, Lizhong Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-05T10:30:38Z","title":"Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04007","kind":"arxiv","version":1},"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":"sha256:071e5acb0b0e25113ad829314fd8ee971d483812cc4022a22eeab00b7bd93f6c","target":"record","created_at":"2026-07-05T08:04:44Z","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":"29ca40c7cc2f8f6142da4b206db7573e1b123ed07f17352e6411e067080fa967","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-05T10:30:38Z","title_canon_sha256":"b111ebe3179dba5e63cafa545af506483b2d8340545aa9d3ecb100276988665b"},"schema_version":"1.0","source":{"id":"2404.04007","kind":"arxiv","version":1}},"canonical_sha256":"8c4ffd0f10c8b388e5a95c91011f6fcfa520d9606333c59b2ba7e5ce4332bfa0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c4ffd0f10c8b388e5a95c91011f6fcfa520d9606333c59b2ba7e5ce4332bfa0","first_computed_at":"2026-07-05T08:04:44.292430Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:44.292430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rYNvLIkBo1kFxtiouEsyQOv8SL9q6zF8R4sTDkwo5EsyU4gdKs/pE32m0Q61CTgPIPvOXR01jhPm0uxRhiCMDw==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:44.292918Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.04007","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:071e5acb0b0e25113ad829314fd8ee971d483812cc4022a22eeab00b7bd93f6c","sha256:2d27b10d4e9064fa96b8cdb692bab6ed1b28bbf59670235e22ddac2a487b053b"],"state_sha256":"2866fad3f6d44e2061c4f9cafd4b6200493f3ca485d87f23ef1980918226e4d8"}