{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:47ZVCZD6LSLXOOFL6PFBTZZXR7","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":"3f5fdb131f4df903c7ef92a720fc7d8a0f60824d91fd00480aa5dc0c3f9c5630","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-01T12:59:20Z","title_canon_sha256":"a1ac0bd70d9fa7e129e9d4c769c3c54bf90708faf909d35f08e6ec0804a19306"},"schema_version":"1.0","source":{"id":"2012.00451","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.00451","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"arxiv_version","alias_value":"2012.00451v3","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.00451","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"pith_short_12","alias_value":"47ZVCZD6LSLX","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"pith_short_16","alias_value":"47ZVCZD6LSLXOOFL","created_at":"2026-07-05T03:05:11Z"},{"alias_kind":"pith_short_8","alias_value":"47ZVCZD6","created_at":"2026-07-05T03:05:11Z"}],"graph_snapshots":[{"event_id":"sha256:5cc66b7af3a818f29b7c45ef44eaf0447ba22a0f6fa27d9c0e4d9882ea5ebb13","target":"graph","created_at":"2026-07-05T03:05:11Z","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/2012.00451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent methods for visual question answering rely on large-scale annotated datasets. Manual annotation of questions and answers for videos, however, is tedious, expensive and prevents scalability. In this work, we propose to avoid manual annotation and generate a large-scale training dataset for video question answering making use of automatic cross-modal supervision. We leverage a question generation transformer trained on text data and use it to generate question-answer pairs from transcribed video narrations. Given narrated videos, we then automatically generate the HowToVQA69M dataset with","authors_text":"Antoine Miech, Antoine Yang, Cordelia Schmid, Ivan Laptev, Josef Sivic","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-01T12:59:20Z","title":"Just Ask: Learning to Answer Questions from Millions of Narrated Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.00451","kind":"arxiv","version":3},"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:a00a961fcab590bf89f1099ee2f2628a62b19196f8fc24d94292041307ff4447","target":"record","created_at":"2026-07-05T03:05:11Z","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":"3f5fdb131f4df903c7ef92a720fc7d8a0f60824d91fd00480aa5dc0c3f9c5630","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-01T12:59:20Z","title_canon_sha256":"a1ac0bd70d9fa7e129e9d4c769c3c54bf90708faf909d35f08e6ec0804a19306"},"schema_version":"1.0","source":{"id":"2012.00451","kind":"arxiv","version":3}},"canonical_sha256":"e7f351647e5c977738abf3ca19e7378fd06476a3b9af75fad31c5e0cdc672532","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7f351647e5c977738abf3ca19e7378fd06476a3b9af75fad31c5e0cdc672532","first_computed_at":"2026-07-05T03:05:11.312583Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:05:11.312583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h9maxK1TSH2N1Jkw/Y8SDU8o0vOXR1Oko7Y1B5iaf/jAZiTXFgAI8kjXt4cWZTD4/LANHYAkzpr1flfmFwldAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:05:11.313048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.00451","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a00a961fcab590bf89f1099ee2f2628a62b19196f8fc24d94292041307ff4447","sha256:5cc66b7af3a818f29b7c45ef44eaf0447ba22a0f6fa27d9c0e4d9882ea5ebb13"],"state_sha256":"a498ccae52bb09a22607094c5a2fea2205345b0aec4893ae6b78222ae5febf2e"}