{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6KGAXQFFXQBSAIBGOSIGEIO3VN","short_pith_number":"pith:6KGAXQFF","schema_version":"1.0","canonical_sha256":"f28c0bc0a5bc0320202674906221dbab48a5abd5022442d0f2faa5685028eb29","source":{"kind":"arxiv","id":"2503.06820","version":1},"attestation_state":"computed","paper":{"title":"Towards Fine-Grained Video Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alan Luo, Arnold Milstein, Debadutta Dash, Ehsan Adeli, Kevin Schulman, Li Fei-Fei, Wei Dai, Zane Durante","submitted_at":"2025-03-10T01:02:01Z","abstract_excerpt":"In the rapidly evolving domain of video understanding, Video Question Answering (VideoQA) remains a focal point. However, existing datasets exhibit gaps in temporal and spatial granularity, which consequently limits the capabilities of existing VideoQA methods. This paper introduces the Multi-Object Multi-Actor Question Answering (MOMA-QA) dataset, which is designed to address these shortcomings by emphasizing temporal localization, spatial relationship reasoning, and entity-centric queries. With ground truth scene graphs and temporal interval annotations, MOMA-QA is ideal for developing model"},"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":"2503.06820","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-10T01:02:01Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"172713ba26e4b02fe2d3e5a18943e72e30e99bafe539c342bd6a3f6462bbf3db","abstract_canon_sha256":"144346a76a0bbba6ccac0f6ee1ef71dcc8c6780caac1929ff5e8f5aa427aa238"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:43.417312Z","signature_b64":"M3tKnYJ/wZVu0sEvWapfsPxdpL/2NKhgnZcwkIAkyd86UDvGTaibu2OV/1mg74BFk40MljTKlnzOI05Qg0MWAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f28c0bc0a5bc0320202674906221dbab48a5abd5022442d0f2faa5685028eb29","last_reissued_at":"2026-07-05T10:27:43.416869Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:43.416869Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Fine-Grained Video Question Answering","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alan Luo, Arnold Milstein, Debadutta Dash, Ehsan Adeli, Kevin Schulman, Li Fei-Fei, Wei Dai, Zane Durante","submitted_at":"2025-03-10T01:02:01Z","abstract_excerpt":"In the rapidly evolving domain of video understanding, Video Question Answering (VideoQA) remains a focal point. However, existing datasets exhibit gaps in temporal and spatial granularity, which consequently limits the capabilities of existing VideoQA methods. This paper introduces the Multi-Object Multi-Actor Question Answering (MOMA-QA) dataset, which is designed to address these shortcomings by emphasizing temporal localization, spatial relationship reasoning, and entity-centric queries. With ground truth scene graphs and temporal interval annotations, MOMA-QA is ideal for developing model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06820","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/2503.06820/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":"2503.06820","created_at":"2026-07-05T10:27:43.416929+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.06820v1","created_at":"2026-07-05T10:27:43.416929+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06820","created_at":"2026-07-05T10:27:43.416929+00:00"},{"alias_kind":"pith_short_12","alias_value":"6KGAXQFFXQBS","created_at":"2026-07-05T10:27:43.416929+00:00"},{"alias_kind":"pith_short_16","alias_value":"6KGAXQFFXQBSAIBG","created_at":"2026-07-05T10:27:43.416929+00:00"},{"alias_kind":"pith_short_8","alias_value":"6KGAXQFF","created_at":"2026-07-05T10:27:43.416929+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.04939","citing_title":"Reading Between the Frames: Interpreting Implicit and Non-literal Meaning in Social Media Videos","ref_index":23,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6KGAXQFFXQBSAIBGOSIGEIO3VN","json":"https://pith.science/pith/6KGAXQFFXQBSAIBGOSIGEIO3VN.json","graph_json":"https://pith.science/api/pith-number/6KGAXQFFXQBSAIBGOSIGEIO3VN/graph.json","events_json":"https://pith.science/api/pith-number/6KGAXQFFXQBSAIBGOSIGEIO3VN/events.json","paper":"https://pith.science/paper/6KGAXQFF"},"agent_actions":{"view_html":"https://pith.science/pith/6KGAXQFFXQBSAIBGOSIGEIO3VN","download_json":"https://pith.science/pith/6KGAXQFFXQBSAIBGOSIGEIO3VN.json","view_paper":"https://pith.science/paper/6KGAXQFF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.06820&json=true","fetch_graph":"https://pith.science/api/pith-number/6KGAXQFFXQBSAIBGOSIGEIO3VN/graph.json","fetch_events":"https://pith.science/api/pith-number/6KGAXQFFXQBSAIBGOSIGEIO3VN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6KGAXQFFXQBSAIBGOSIGEIO3VN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6KGAXQFFXQBSAIBGOSIGEIO3VN/action/storage_attestation","attest_author":"https://pith.science/pith/6KGAXQFFXQBSAIBGOSIGEIO3VN/action/author_attestation","sign_citation":"https://pith.science/pith/6KGAXQFFXQBSAIBGOSIGEIO3VN/action/citation_signature","submit_replication":"https://pith.science/pith/6KGAXQFFXQBSAIBGOSIGEIO3VN/action/replication_record"}},"created_at":"2026-07-05T10:27:43.416929+00:00","updated_at":"2026-07-05T10:27:43.416929+00:00"}