{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VYHSGZL67OLNOYT4LIMAPJRDLB","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":"63638b1286ce3b2486717becbd25df343a443cdc59d1bdd56e874bba2bfd10f0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-10T16:34:26Z","title_canon_sha256":"015f93d0cd5906e092e4282e320a606ef7f5d2e38eadaeeefcc26df75fcf25f9"},"schema_version":"1.0","source":{"id":"2205.05019","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.05019","created_at":"2026-07-05T04:22:22Z"},{"alias_kind":"arxiv_version","alias_value":"2205.05019v2","created_at":"2026-07-05T04:22:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.05019","created_at":"2026-07-05T04:22:22Z"},{"alias_kind":"pith_short_12","alias_value":"VYHSGZL67OLN","created_at":"2026-07-05T04:22:22Z"},{"alias_kind":"pith_short_16","alias_value":"VYHSGZL67OLNOYT4","created_at":"2026-07-05T04:22:22Z"},{"alias_kind":"pith_short_8","alias_value":"VYHSGZL6","created_at":"2026-07-05T04:22:22Z"}],"graph_snapshots":[{"event_id":"sha256:c4ea63d0b9b49bacfeb8940c4b3c04f70287b883d6cd55768ae18cde9e5ea4ec","target":"graph","created_at":"2026-07-05T04:22:22Z","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/2205.05019/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":"2022-05-10T16:34:26Z","title":"Learning to Answer Visual Questions from Web Videos"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05019","kind":"arxiv","version":2},"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:fde5d7474e4a572a7820a739c33cbec3d6497537821ab4ec57582a63c45d68d3","target":"record","created_at":"2026-07-05T04:22:22Z","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":"63638b1286ce3b2486717becbd25df343a443cdc59d1bdd56e874bba2bfd10f0","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-10T16:34:26Z","title_canon_sha256":"015f93d0cd5906e092e4282e320a606ef7f5d2e38eadaeeefcc26df75fcf25f9"},"schema_version":"1.0","source":{"id":"2205.05019","kind":"arxiv","version":2}},"canonical_sha256":"ae0f23657efb96d7627c5a1807a6235868df036b0fea996a2b617b81d124f0f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ae0f23657efb96d7627c5a1807a6235868df036b0fea996a2b617b81d124f0f1","first_computed_at":"2026-07-05T04:22:22.234951Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:22.234951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jfC9NM1yId3HosB0LXNToo24ntMk3YbbM+eiavHjo8KMkU9xdA0xB4YsFX5n9/d5CWmPpoq7axQtwFSOARlTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:22.235455Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.05019","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fde5d7474e4a572a7820a739c33cbec3d6497537821ab4ec57582a63c45d68d3","sha256:c4ea63d0b9b49bacfeb8940c4b3c04f70287b883d6cd55768ae18cde9e5ea4ec"],"state_sha256":"d5bc05f28099a9419f4bd4fc69e8dc0d45a97844c271406b7a43ee5aa8308d80"}