{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3WU5PTUTAHA5O3WHD2ZLVDWJTF","short_pith_number":"pith:3WU5PTUT","schema_version":"1.0","canonical_sha256":"dda9d7ce9301c1d76ec71eb2ba8ec9995e8462856e0d06b6194faed3e4a05825","source":{"kind":"arxiv","id":"2505.13429","version":1},"attestation_state":"computed","paper":{"title":"Understanding Complexity in VideoQA via Visual Program Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achal Dave, Cristobal Eyzaguirre, Igor Vasiljevic, Jiajun Wu, Juan Carlos Niebles, Pavel Tokmakov, Rares Andrei Ambrus, Thomas Kollar","submitted_at":"2025-05-19T17:55:14Z","abstract_excerpt":"We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design challenging questions, yet we experimentally show that humans struggle to predict which questions are difficult for machine learning models. Our automatic approach leverages recent advances in code generation for visual question answering, using the complexity of generated code as a proxy for question difficulty. We demonstrate that this measure correlates significantly better with model performance than human estim"},"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":"2505.13429","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T17:55:14Z","cross_cats_sorted":[],"title_canon_sha256":"996a274b705f661841112c7cbf7ea1b245c00b829aca2664fb1ef9c79fd65309","abstract_canon_sha256":"7b34a653831fe802142283e2f31eaff371982eb4d4083d71ea2d647ebb3debeb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:30.065149Z","signature_b64":"SKqLUnfIznBLY518W2mOgxw7sTTEvvDX2OuppQYnm7aDUORw8Id0l0x027i3xPF+24Y9FebXEFDMHOuLlCIwDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dda9d7ce9301c1d76ec71eb2ba8ec9995e8462856e0d06b6194faed3e4a05825","last_reissued_at":"2026-07-05T11:05:30.064661Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:30.064661Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Complexity in VideoQA via Visual Program Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Achal Dave, Cristobal Eyzaguirre, Igor Vasiljevic, Jiajun Wu, Juan Carlos Niebles, Pavel Tokmakov, Rares Andrei Ambrus, Thomas Kollar","submitted_at":"2025-05-19T17:55:14Z","abstract_excerpt":"We propose a data-driven approach to analyzing query complexity in Video Question Answering (VideoQA). Previous efforts in benchmark design have relied on human expertise to design challenging questions, yet we experimentally show that humans struggle to predict which questions are difficult for machine learning models. Our automatic approach leverages recent advances in code generation for visual question answering, using the complexity of generated code as a proxy for question difficulty. We demonstrate that this measure correlates significantly better with model performance than human estim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.13429","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/2505.13429/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":"2505.13429","created_at":"2026-07-05T11:05:30.064720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.13429v1","created_at":"2026-07-05T11:05:30.064720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.13429","created_at":"2026-07-05T11:05:30.064720+00:00"},{"alias_kind":"pith_short_12","alias_value":"3WU5PTUTAHA5","created_at":"2026-07-05T11:05:30.064720+00:00"},{"alias_kind":"pith_short_16","alias_value":"3WU5PTUTAHA5O3WH","created_at":"2026-07-05T11:05:30.064720+00:00"},{"alias_kind":"pith_short_8","alias_value":"3WU5PTUT","created_at":"2026-07-05T11:05:30.064720+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00640","citing_title":"An Attribute-Based Measure of Video Complexity","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3WU5PTUTAHA5O3WHD2ZLVDWJTF","json":"https://pith.science/pith/3WU5PTUTAHA5O3WHD2ZLVDWJTF.json","graph_json":"https://pith.science/api/pith-number/3WU5PTUTAHA5O3WHD2ZLVDWJTF/graph.json","events_json":"https://pith.science/api/pith-number/3WU5PTUTAHA5O3WHD2ZLVDWJTF/events.json","paper":"https://pith.science/paper/3WU5PTUT"},"agent_actions":{"view_html":"https://pith.science/pith/3WU5PTUTAHA5O3WHD2ZLVDWJTF","download_json":"https://pith.science/pith/3WU5PTUTAHA5O3WHD2ZLVDWJTF.json","view_paper":"https://pith.science/paper/3WU5PTUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.13429&json=true","fetch_graph":"https://pith.science/api/pith-number/3WU5PTUTAHA5O3WHD2ZLVDWJTF/graph.json","fetch_events":"https://pith.science/api/pith-number/3WU5PTUTAHA5O3WHD2ZLVDWJTF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3WU5PTUTAHA5O3WHD2ZLVDWJTF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3WU5PTUTAHA5O3WHD2ZLVDWJTF/action/storage_attestation","attest_author":"https://pith.science/pith/3WU5PTUTAHA5O3WHD2ZLVDWJTF/action/author_attestation","sign_citation":"https://pith.science/pith/3WU5PTUTAHA5O3WHD2ZLVDWJTF/action/citation_signature","submit_replication":"https://pith.science/pith/3WU5PTUTAHA5O3WHD2ZLVDWJTF/action/replication_record"}},"created_at":"2026-07-05T11:05:30.064720+00:00","updated_at":"2026-07-05T11:05:30.064720+00:00"}