{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:WBMFJVWSPMRTTVDZ2PB67OZGTF","short_pith_number":"pith:WBMFJVWS","canonical_record":{"source":{"id":"1906.03327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-07T20:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"c8a6f6014bcc5fc1aa871a165e494c6a125d577e69ca506d1b50f1c43a7354a3","abstract_canon_sha256":"7a926ee95a403fbc84d4d71a94d72539d1c22c6c7898c500f133dbbaac416ac6"},"schema_version":"1.0"},"canonical_sha256":"b05854d6d27b2339d479d3c3efbb269943f02eac7c200178178d1bcb2f0dd823","source":{"kind":"arxiv","id":"1906.03327","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03327","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03327v2","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03327","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"pith_short_12","alias_value":"WBMFJVWSPMRT","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"pith_short_16","alias_value":"WBMFJVWSPMRTTVDZ","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"pith_short_8","alias_value":"WBMFJVWS","created_at":"2026-07-04T23:50:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:WBMFJVWSPMRTTVDZ2PB67OZGTF","target":"record","payload":{"canonical_record":{"source":{"id":"1906.03327","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-07T20:48:19Z","cross_cats_sorted":[],"title_canon_sha256":"c8a6f6014bcc5fc1aa871a165e494c6a125d577e69ca506d1b50f1c43a7354a3","abstract_canon_sha256":"7a926ee95a403fbc84d4d71a94d72539d1c22c6c7898c500f133dbbaac416ac6"},"schema_version":"1.0"},"canonical_sha256":"b05854d6d27b2339d479d3c3efbb269943f02eac7c200178178d1bcb2f0dd823","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-04T23:50:45.750604Z","signature_b64":"qWl/ef8OgZTsRYo0rtMb3+PQj4IrNOjM/3xD1xYECYuSgo8LTNcdnHa2KVsP8ty/3jnRf6Au8jZqPHXGxIRKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b05854d6d27b2339d479d3c3efbb269943f02eac7c200178178d1bcb2f0dd823","last_reissued_at":"2026-07-04T23:50:45.750167Z","signature_status":"signed_v1","first_computed_at":"2026-07-04T23:50:45.750167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.03327","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":"2026-07-04T23:50:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tjIT9cp7tof4709ElyQJipi1pZ1Cjxma8b/tzoEx+zfjak5fwrriXublCOnsDUV+tvHwHR5Q5c6jF2qi3ghbDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:11:28.494994Z"},"content_sha256":"525e6095fa5e01d04b831cddc0bcfc00ddd5c1c2a1f0464f07709b6b398bb9f1","schema_version":"1.0","event_id":"sha256:525e6095fa5e01d04b831cddc0bcfc00ddd5c1c2a1f0464f07709b6b398bb9f1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:WBMFJVWSPMRTTVDZ2PB67OZGTF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Antoine Miech, Dimitri Zhukov, Ivan Laptev, Jean-Baptiste Alayrac, Josef Sivic, Makarand Tapaswi","submitted_at":"2019-06-07T20:48:19Z","abstract_excerpt":"Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose instead to learn such embeddings from video data with readily available natural language annotations in the form of automatically transcribed narrations. The contributions of this work are three-fold. First, we introduce HowTo100M: a large-scale dataset of 136 million video clips sourced from 1.22M narrated instructional web videos depicting humans "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03327","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/1906.03327/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":"2026-07-04T23:50:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"45DKkbtc1rzjTMEtqkEO6a/HDOQ56wMZYLMd31vvgfDNc+rUa33ypU2NXlAkEUsrl0VV48yO0yE9kpa8F4rUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:11:28.495992Z"},"content_sha256":"ffe08c19bfb5291effe75e8803678a66af82252b65f7ec039ee0b23b9a563e4f","schema_version":"1.0","event_id":"sha256:ffe08c19bfb5291effe75e8803678a66af82252b65f7ec039ee0b23b9a563e4f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WBMFJVWSPMRTTVDZ2PB67OZGTF/bundle.json","state_url":"https://pith.science/pith/WBMFJVWSPMRTTVDZ2PB67OZGTF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WBMFJVWSPMRTTVDZ2PB67OZGTF/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":"2026-08-06T14:11:28Z","links":{"resolver":"https://pith.science/pith/WBMFJVWSPMRTTVDZ2PB67OZGTF","bundle":"https://pith.science/pith/WBMFJVWSPMRTTVDZ2PB67OZGTF/bundle.json","state":"https://pith.science/pith/WBMFJVWSPMRTTVDZ2PB67OZGTF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WBMFJVWSPMRTTVDZ2PB67OZGTF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:WBMFJVWSPMRTTVDZ2PB67OZGTF","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":"7a926ee95a403fbc84d4d71a94d72539d1c22c6c7898c500f133dbbaac416ac6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-07T20:48:19Z","title_canon_sha256":"c8a6f6014bcc5fc1aa871a165e494c6a125d577e69ca506d1b50f1c43a7354a3"},"schema_version":"1.0","source":{"id":"1906.03327","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.03327","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"arxiv_version","alias_value":"1906.03327v2","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.03327","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"pith_short_12","alias_value":"WBMFJVWSPMRT","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"pith_short_16","alias_value":"WBMFJVWSPMRTTVDZ","created_at":"2026-07-04T23:50:45Z"},{"alias_kind":"pith_short_8","alias_value":"WBMFJVWS","created_at":"2026-07-04T23:50:45Z"}],"graph_snapshots":[{"event_id":"sha256:ffe08c19bfb5291effe75e8803678a66af82252b65f7ec039ee0b23b9a563e4f","target":"graph","created_at":"2026-07-04T23:50:45Z","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/1906.03327/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning text-video embeddings usually requires a dataset of video clips with manually provided captions. However, such datasets are expensive and time consuming to create and therefore difficult to obtain on a large scale. In this work, we propose instead to learn such embeddings from video data with readily available natural language annotations in the form of automatically transcribed narrations. The contributions of this work are three-fold. First, we introduce HowTo100M: a large-scale dataset of 136 million video clips sourced from 1.22M narrated instructional web videos depicting humans ","authors_text":"Antoine Miech, Dimitri Zhukov, Ivan Laptev, Jean-Baptiste Alayrac, Josef Sivic, Makarand Tapaswi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-07T20:48:19Z","title":"HowTo100M: Learning a Text-Video Embedding by Watching Hundred Million Narrated Video Clips"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.03327","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":"sha256:525e6095fa5e01d04b831cddc0bcfc00ddd5c1c2a1f0464f07709b6b398bb9f1","target":"record","created_at":"2026-07-04T23:50:45Z","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":"7a926ee95a403fbc84d4d71a94d72539d1c22c6c7898c500f133dbbaac416ac6","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-06-07T20:48:19Z","title_canon_sha256":"c8a6f6014bcc5fc1aa871a165e494c6a125d577e69ca506d1b50f1c43a7354a3"},"schema_version":"1.0","source":{"id":"1906.03327","kind":"arxiv","version":2}},"canonical_sha256":"b05854d6d27b2339d479d3c3efbb269943f02eac7c200178178d1bcb2f0dd823","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b05854d6d27b2339d479d3c3efbb269943f02eac7c200178178d1bcb2f0dd823","first_computed_at":"2026-07-04T23:50:45.750167Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-04T23:50:45.750167Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qWl/ef8OgZTsRYo0rtMb3+PQj4IrNOjM/3xD1xYECYuSgo8LTNcdnHa2KVsP8ty/3jnRf6Au8jZqPHXGxIRKAA==","signature_status":"signed_v1","signed_at":"2026-07-04T23:50:45.750604Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.03327","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:525e6095fa5e01d04b831cddc0bcfc00ddd5c1c2a1f0464f07709b6b398bb9f1","sha256:ffe08c19bfb5291effe75e8803678a66af82252b65f7ec039ee0b23b9a563e4f"],"state_sha256":"1502d6161d997e5bc58c5972c185f7c3f7fa1a6f89b32e007f4ff26ed2d5af3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Kpl8bM+hgfS8h/4X7XgWqMGafGjtaAYnT//zhOAkg1llJcQ5XdSR5rn/FnPiKVaZmkFB1TXhTBbClcllyDdDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:11:28.504965Z","bundle_sha256":"fb4cc5515818dde23263a89d877da6e77f84df3dc8be8a2711be873bd71cf652"}}