{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VYHSGZL67OLNOYT4LIMAPJRDLB","short_pith_number":"pith:VYHSGZL6","canonical_record":{"source":{"id":"2205.05019","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-10T16:34:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"015f93d0cd5906e092e4282e320a606ef7f5d2e38eadaeeefcc26df75fcf25f9","abstract_canon_sha256":"63638b1286ce3b2486717becbd25df343a443cdc59d1bdd56e874bba2bfd10f0"},"schema_version":"1.0"},"canonical_sha256":"ae0f23657efb96d7627c5a1807a6235868df036b0fea996a2b617b81d124f0f1","source":{"kind":"arxiv","id":"2205.05019","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VYHSGZL67OLNOYT4LIMAPJRDLB","target":"record","payload":{"canonical_record":{"source":{"id":"2205.05019","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-05-10T16:34:26Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"015f93d0cd5906e092e4282e320a606ef7f5d2e38eadaeeefcc26df75fcf25f9","abstract_canon_sha256":"63638b1286ce3b2486717becbd25df343a443cdc59d1bdd56e874bba2bfd10f0"},"schema_version":"1.0"},"canonical_sha256":"ae0f23657efb96d7627c5a1807a6235868df036b0fea996a2b617b81d124f0f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:22.235455Z","signature_b64":"jfC9NM1yId3HosB0LXNToo24ntMk3YbbM+eiavHjo8KMkU9xdA0xB4YsFX5n9/d5CWmPpoq7axQtwFSOARlTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae0f23657efb96d7627c5a1807a6235868df036b0fea996a2b617b81d124f0f1","last_reissued_at":"2026-07-05T04:22:22.234951Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:22.234951Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.05019","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:22:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZpqEuBJ08cNRjLUtSfMJ47Vm214pDEfOzulqJrVJ+BXq3Gj9ynLLfJHchP5IvYqHppxOS2KgBnv3gEtXhr1JAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:12:20.625899Z"},"content_sha256":"fde5d7474e4a572a7820a739c33cbec3d6497537821ab4ec57582a63c45d68d3","schema_version":"1.0","event_id":"sha256:fde5d7474e4a572a7820a739c33cbec3d6497537821ab4ec57582a63c45d68d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VYHSGZL67OLNOYT4LIMAPJRDLB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning to Answer Visual Questions from Web Videos","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Antoine Miech, Antoine Yang, Cordelia Schmid, Ivan Laptev, Josef Sivic","submitted_at":"2022-05-10T16:34:26Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.05019","kind":"arxiv","version":2},"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/2205.05019/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:22:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oDulBNiCVmcZYr43gHs7jRs/9G3zhJbzfM9G3NRQT8EHDE8uAtEpDEQKgmjyxJrq+a5ETXJ36urvTbXg1/XvCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T10:12:20.627760Z"},"content_sha256":"c4ea63d0b9b49bacfeb8940c4b3c04f70287b883d6cd55768ae18cde9e5ea4ec","schema_version":"1.0","event_id":"sha256:c4ea63d0b9b49bacfeb8940c4b3c04f70287b883d6cd55768ae18cde9e5ea4ec"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VYHSGZL67OLNOYT4LIMAPJRDLB/bundle.json","state_url":"https://pith.science/pith/VYHSGZL67OLNOYT4LIMAPJRDLB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VYHSGZL67OLNOYT4LIMAPJRDLB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T10:12:20Z","links":{"resolver":"https://pith.science/pith/VYHSGZL67OLNOYT4LIMAPJRDLB","bundle":"https://pith.science/pith/VYHSGZL67OLNOYT4LIMAPJRDLB/bundle.json","state":"https://pith.science/pith/VYHSGZL67OLNOYT4LIMAPJRDLB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VYHSGZL67OLNOYT4LIMAPJRDLB/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9vIRZOZYAmR6guHqBZaXrWFzC/oVlbEphMIMJf/GB30co5efvGW2jF6zvduDHoZ1wayG0+s9PL845+C3CeH4Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T10:12:20.729349Z","bundle_sha256":"00322204ff7eafc424921cf5d0176d3b0c7c0a78264bb97102edbeaede0443ed"}}