{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RRH72DYQZCZYRZNJLSIQCH3PZ6","short_pith_number":"pith:RRH72DYQ","schema_version":"1.0","canonical_sha256":"8c4ffd0f10c8b388e5a95c91011f6fcfa520d9606333c59b2ba7e5ce4332bfa0","source":{"kind":"arxiv","id":"2404.04007","version":1},"attestation_state":"computed","paper":{"title":"Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Sun, Jin Qiu, Lili Liang, Lizhong Zhang","submitted_at":"2024-04-05T10:30:38Z","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"},"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":"2404.04007","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-05T10:30:38Z","cross_cats_sorted":[],"title_canon_sha256":"b111ebe3179dba5e63cafa545af506483b2d8340545aa9d3ecb100276988665b","abstract_canon_sha256":"29ca40c7cc2f8f6142da4b206db7573e1b123ed07f17352e6411e067080fa967"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:44.292918Z","signature_b64":"rYNvLIkBo1kFxtiouEsyQOv8SL9q6zF8R4sTDkwo5EsyU4gdKs/pE32m0Q61CTgPIPvOXR01jhPm0uxRhiCMDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c4ffd0f10c8b388e5a95c91011f6fcfa520d9606333c59b2ba7e5ce4332bfa0","last_reissued_at":"2026-07-05T08:04:44.292430Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:44.292430Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural-Symbolic VideoQA: Learning Compositional Spatio-Temporal Reasoning for Real-world Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Guanglu Sun, Jin Qiu, Lili Liang, Lizhong Zhang","submitted_at":"2024-04-05T10:30:38Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.04007","kind":"arxiv","version":1},"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/2404.04007/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":"2404.04007","created_at":"2026-07-05T08:04:44.292489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.04007v1","created_at":"2026-07-05T08:04:44.292489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.04007","created_at":"2026-07-05T08:04:44.292489+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRH72DYQZCZY","created_at":"2026-07-05T08:04:44.292489+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRH72DYQZCZYRZNJ","created_at":"2026-07-05T08:04:44.292489+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRH72DYQ","created_at":"2026-07-05T08:04:44.292489+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17279","citing_title":"Training LLMs with Reinforcement Learning over Digital Twin Representations for Reasoning-Intensive Surgical VideoQA","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRH72DYQZCZYRZNJLSIQCH3PZ6","json":"https://pith.science/pith/RRH72DYQZCZYRZNJLSIQCH3PZ6.json","graph_json":"https://pith.science/api/pith-number/RRH72DYQZCZYRZNJLSIQCH3PZ6/graph.json","events_json":"https://pith.science/api/pith-number/RRH72DYQZCZYRZNJLSIQCH3PZ6/events.json","paper":"https://pith.science/paper/RRH72DYQ"},"agent_actions":{"view_html":"https://pith.science/pith/RRH72DYQZCZYRZNJLSIQCH3PZ6","download_json":"https://pith.science/pith/RRH72DYQZCZYRZNJLSIQCH3PZ6.json","view_paper":"https://pith.science/paper/RRH72DYQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.04007&json=true","fetch_graph":"https://pith.science/api/pith-number/RRH72DYQZCZYRZNJLSIQCH3PZ6/graph.json","fetch_events":"https://pith.science/api/pith-number/RRH72DYQZCZYRZNJLSIQCH3PZ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRH72DYQZCZYRZNJLSIQCH3PZ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRH72DYQZCZYRZNJLSIQCH3PZ6/action/storage_attestation","attest_author":"https://pith.science/pith/RRH72DYQZCZYRZNJLSIQCH3PZ6/action/author_attestation","sign_citation":"https://pith.science/pith/RRH72DYQZCZYRZNJLSIQCH3PZ6/action/citation_signature","submit_replication":"https://pith.science/pith/RRH72DYQZCZYRZNJLSIQCH3PZ6/action/replication_record"}},"created_at":"2026-07-05T08:04:44.292489+00:00","updated_at":"2026-07-05T08:04:44.292489+00:00"}