{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:47ZVCZD6LSLXOOFL6PFBTZZXR7","short_pith_number":"pith:47ZVCZD6","canonical_record":{"source":{"id":"2012.00451","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-01T12:59:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a1ac0bd70d9fa7e129e9d4c769c3c54bf90708faf909d35f08e6ec0804a19306","abstract_canon_sha256":"3f5fdb131f4df903c7ef92a720fc7d8a0f60824d91fd00480aa5dc0c3f9c5630"},"schema_version":"1.0"},"canonical_sha256":"e7f351647e5c977738abf3ca19e7378fd06476a3b9af75fad31c5e0cdc672532","source":{"kind":"arxiv","id":"2012.00451","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:47ZVCZD6LSLXOOFL6PFBTZZXR7","target":"record","payload":{"canonical_record":{"source":{"id":"2012.00451","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-12-01T12:59:20Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"a1ac0bd70d9fa7e129e9d4c769c3c54bf90708faf909d35f08e6ec0804a19306","abstract_canon_sha256":"3f5fdb131f4df903c7ef92a720fc7d8a0f60824d91fd00480aa5dc0c3f9c5630"},"schema_version":"1.0"},"canonical_sha256":"e7f351647e5c977738abf3ca19e7378fd06476a3b9af75fad31c5e0cdc672532","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:05:11.313048Z","signature_b64":"h9maxK1TSH2N1Jkw/Y8SDU8o0vOXR1Oko7Y1B5iaf/jAZiTXFgAI8kjXt4cWZTD4/LANHYAkzpr1flfmFwldAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7f351647e5c977738abf3ca19e7378fd06476a3b9af75fad31c5e0cdc672532","last_reissued_at":"2026-07-05T03:05:11.312583Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:05:11.312583Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.00451","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i8oPg8xC8Fu5DBSEyFEdrvfwUKz+b+BN42g87DuJcmDBEzOg34yanL2I5wMZinWxnc2RH0r42GlG6CkOjw3UAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:44:07.878308Z"},"content_sha256":"a00a961fcab590bf89f1099ee2f2628a62b19196f8fc24d94292041307ff4447","schema_version":"1.0","event_id":"sha256:a00a961fcab590bf89f1099ee2f2628a62b19196f8fc24d94292041307ff4447"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:47ZVCZD6LSLXOOFL6PFBTZZXR7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Just Ask: Learning to Answer Questions from Millions of Narrated 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":"2020-12-01T12:59:20Z","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":"2012.00451","kind":"arxiv","version":3},"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/2012.00451/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":"2026-07-05T03:05:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lD9Aur4FyrowVt7JoB6dtdv494x9ixwhWo3CUAD6JLmml8KsFoT1am00IxZtLvpDzw5diITXQ/FE47h8XbL/CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:44:07.878810Z"},"content_sha256":"5cc66b7af3a818f29b7c45ef44eaf0447ba22a0f6fa27d9c0e4d9882ea5ebb13","schema_version":"1.0","event_id":"sha256:5cc66b7af3a818f29b7c45ef44eaf0447ba22a0f6fa27d9c0e4d9882ea5ebb13"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/47ZVCZD6LSLXOOFL6PFBTZZXR7/bundle.json","state_url":"https://pith.science/pith/47ZVCZD6LSLXOOFL6PFBTZZXR7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/47ZVCZD6LSLXOOFL6PFBTZZXR7/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":"2026-08-08T11:44:07Z","links":{"resolver":"https://pith.science/pith/47ZVCZD6LSLXOOFL6PFBTZZXR7","bundle":"https://pith.science/pith/47ZVCZD6LSLXOOFL6PFBTZZXR7/bundle.json","state":"https://pith.science/pith/47ZVCZD6LSLXOOFL6PFBTZZXR7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/47ZVCZD6LSLXOOFL6PFBTZZXR7/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IASZph4iEtM83OikUwqqdOOR398QgjQFzMn4z7/bmYS7w+WmeulLmixkCiv+1fyAekHB54JSxNBpJoqINP1XAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:44:07.883043Z","bundle_sha256":"483fd5062279ae6d7dbdc682b9aea7771ae2f3127cf4faad64c514da10b43320"}}