{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4GQSSQOA6C6OOUDOZKHLYNM7AJ","short_pith_number":"pith:4GQSSQOA","schema_version":"1.0","canonical_sha256":"e1a12941c0f0bce7506eca8ebc359f027527b28fba2d886443a833d34550dfc2","source":{"kind":"arxiv","id":"2312.00937","version":1},"attestation_state":"computed","paper":{"title":"Zero-Shot Video Question Answering with Procedural Programs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Koichiro Niinuma, Kris M. Kitani, L\\'aszl\\'o A. Jeni, Rohan Choudhury","submitted_at":"2023-12-01T21:34:10Z","abstract_excerpt":"We propose to answer zero-shot questions about videos by generating short procedural programs that derive a final answer from solving a sequence of visual subtasks. We present Procedural Video Querying (ProViQ), which uses a large language model to generate such programs from an input question and an API of visual modules in the prompt, then executes them to obtain the output. Recent similar procedural approaches have proven successful for image question answering, but videos remain challenging: we provide ProViQ with modules intended for video understanding, allowing it to generalize to a wid"},"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":"2312.00937","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-01T21:34:10Z","cross_cats_sorted":[],"title_canon_sha256":"1ff70302f9303a4fc5437dd1289d68921312a5e0c6b4791eb0524541467898ca","abstract_canon_sha256":"05697c7a59239091567d816db64e6c28f349d74458f2d929413b25aa877ad11f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:19:26.714714Z","signature_b64":"1xkidgZw62CmVZLOMcmI7kkfF0/+yWXji4laVYtAvrJ5Mf5Rem3a2+srLzKSK62bwp3GHE22hb+5wpBLb1IkDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1a12941c0f0bce7506eca8ebc359f027527b28fba2d886443a833d34550dfc2","last_reissued_at":"2026-07-05T07:19:26.714216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:19:26.714216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Zero-Shot Video Question Answering with Procedural Programs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Koichiro Niinuma, Kris M. Kitani, L\\'aszl\\'o A. Jeni, Rohan Choudhury","submitted_at":"2023-12-01T21:34:10Z","abstract_excerpt":"We propose to answer zero-shot questions about videos by generating short procedural programs that derive a final answer from solving a sequence of visual subtasks. We present Procedural Video Querying (ProViQ), which uses a large language model to generate such programs from an input question and an API of visual modules in the prompt, then executes them to obtain the output. Recent similar procedural approaches have proven successful for image question answering, but videos remain challenging: we provide ProViQ with modules intended for video understanding, allowing it to generalize to a wid"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.00937","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/2312.00937/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":"2312.00937","created_at":"2026-07-05T07:19:26.714283+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.00937v1","created_at":"2026-07-05T07:19:26.714283+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.00937","created_at":"2026-07-05T07:19:26.714283+00:00"},{"alias_kind":"pith_short_12","alias_value":"4GQSSQOA6C6O","created_at":"2026-07-05T07:19:26.714283+00:00"},{"alias_kind":"pith_short_16","alias_value":"4GQSSQOA6C6OOUDO","created_at":"2026-07-05T07:19:26.714283+00:00"},{"alias_kind":"pith_short_8","alias_value":"4GQSSQOA","created_at":"2026-07-05T07:19:26.714283+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2404.16994","citing_title":"PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4GQSSQOA6C6OOUDOZKHLYNM7AJ","json":"https://pith.science/pith/4GQSSQOA6C6OOUDOZKHLYNM7AJ.json","graph_json":"https://pith.science/api/pith-number/4GQSSQOA6C6OOUDOZKHLYNM7AJ/graph.json","events_json":"https://pith.science/api/pith-number/4GQSSQOA6C6OOUDOZKHLYNM7AJ/events.json","paper":"https://pith.science/paper/4GQSSQOA"},"agent_actions":{"view_html":"https://pith.science/pith/4GQSSQOA6C6OOUDOZKHLYNM7AJ","download_json":"https://pith.science/pith/4GQSSQOA6C6OOUDOZKHLYNM7AJ.json","view_paper":"https://pith.science/paper/4GQSSQOA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.00937&json=true","fetch_graph":"https://pith.science/api/pith-number/4GQSSQOA6C6OOUDOZKHLYNM7AJ/graph.json","fetch_events":"https://pith.science/api/pith-number/4GQSSQOA6C6OOUDOZKHLYNM7AJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4GQSSQOA6C6OOUDOZKHLYNM7AJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4GQSSQOA6C6OOUDOZKHLYNM7AJ/action/storage_attestation","attest_author":"https://pith.science/pith/4GQSSQOA6C6OOUDOZKHLYNM7AJ/action/author_attestation","sign_citation":"https://pith.science/pith/4GQSSQOA6C6OOUDOZKHLYNM7AJ/action/citation_signature","submit_replication":"https://pith.science/pith/4GQSSQOA6C6OOUDOZKHLYNM7AJ/action/replication_record"}},"created_at":"2026-07-05T07:19:26.714283+00:00","updated_at":"2026-07-05T07:19:26.714283+00:00"}