{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:BTF466H4EDI5KSLVLNPKVQZCC6","short_pith_number":"pith:BTF466H4","canonical_record":{"source":{"id":"2201.02639","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-07T19:00:21Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8b300b7a2ed75e09f6299cf38a60ca568acb5569bf3d3472b0e837d898c7b068","abstract_canon_sha256":"1ae8120e8fdaf74ee9b65f9b99027355bf4b6ee40d864ec7cf36866e15e7106d"},"schema_version":"1.0"},"canonical_sha256":"0ccbcf78fc20d1d549755b5eaac32217bc373d7ea3fb4408cc3c9adce6b577f0","source":{"kind":"arxiv","id":"2201.02639","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02639","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02639v4","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02639","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"BTF466H4EDI5","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"pith_short_16","alias_value":"BTF466H4EDI5KSLV","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"pith_short_8","alias_value":"BTF466H4","created_at":"2026-07-05T04:22:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:BTF466H4EDI5KSLVLNPKVQZCC6","target":"record","payload":{"canonical_record":{"source":{"id":"2201.02639","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-07T19:00:21Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8b300b7a2ed75e09f6299cf38a60ca568acb5569bf3d3472b0e837d898c7b068","abstract_canon_sha256":"1ae8120e8fdaf74ee9b65f9b99027355bf4b6ee40d864ec7cf36866e15e7106d"},"schema_version":"1.0"},"canonical_sha256":"0ccbcf78fc20d1d549755b5eaac32217bc373d7ea3fb4408cc3c9adce6b577f0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:22:53.585206Z","signature_b64":"Hp8XuZtOoWCmcaW/ozeWA/WvwfYzLo7L9UoWfXSNPvatzhyq/hQImewm9GN8aYLby4jvQtA1kHYDtKP899W3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ccbcf78fc20d1d549755b5eaac32217bc373d7ea3fb4408cc3c9adce6b577f0","last_reissued_at":"2026-07-05T04:22:53.584646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:22:53.584646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.02639","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HlHHno868ZiGbKaj4bWKrsTey9u2/Gx+soP8RaUBVL+PDF5RtTJklfDgk0WsYhLHbnVtOBMvOBLAmiS1+ocgCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T22:46:33.897066Z"},"content_sha256":"4a0fa87f970dcdab453af1aad2a2086388acc1ed22b611e28945d01296406fd0","schema_version":"1.0","event_id":"sha256:4a0fa87f970dcdab453af1aad2a2086388acc1ed22b611e28945d01296406fd0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:BTF466H4EDI5KSLVLNPKVQZCC6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Aditya Kusupati, Ali Farhadi, Jack Hessel, Jiasen Lu, Mohammadreza Salehi, Rowan Zellers, Ximing Lu, Yanpeng Zhao, Yejin Choi, Youngjae Yu","submitted_at":"2022-01-07T19:00:21Z","abstract_excerpt":"As humans, we navigate a multimodal world, building a holistic understanding from all our senses. We introduce MERLOT Reserve, a model that represents videos jointly over time -- through a new training objective that learns from audio, subtitles, and video frames. Given a video, we replace snippets of text and audio with a MASK token; the model learns by choosing the correct masked-out snippet. Our objective learns faster than alternatives, and performs well at scale: we pretrain on 20 million YouTube videos.\n  Empirical results show that MERLOT Reserve learns strong multimodal representations"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02639","kind":"arxiv","version":4},"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/2201.02639/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":"2026-07-05T04:22:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mpe0qjq7Tlkbhv1qO5nMFQf5RQtLpZ0IDl3MmBvS5JMui1YoQH11RsCHeFwW462LWcaYtNkDYH0v7a1RhXSBDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T22:46:33.897463Z"},"content_sha256":"216134c8a526028f024e5ba2385f6095fcd2da5bcf63407c56f924c9c001156f","schema_version":"1.0","event_id":"sha256:216134c8a526028f024e5ba2385f6095fcd2da5bcf63407c56f924c9c001156f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BTF466H4EDI5KSLVLNPKVQZCC6/bundle.json","state_url":"https://pith.science/pith/BTF466H4EDI5KSLVLNPKVQZCC6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BTF466H4EDI5KSLVLNPKVQZCC6/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":"2026-07-14T22:46:33Z","links":{"resolver":"https://pith.science/pith/BTF466H4EDI5KSLVLNPKVQZCC6","bundle":"https://pith.science/pith/BTF466H4EDI5KSLVLNPKVQZCC6/bundle.json","state":"https://pith.science/pith/BTF466H4EDI5KSLVLNPKVQZCC6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BTF466H4EDI5KSLVLNPKVQZCC6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:BTF466H4EDI5KSLVLNPKVQZCC6","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":"1ae8120e8fdaf74ee9b65f9b99027355bf4b6ee40d864ec7cf36866e15e7106d","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-07T19:00:21Z","title_canon_sha256":"8b300b7a2ed75e09f6299cf38a60ca568acb5569bf3d3472b0e837d898c7b068"},"schema_version":"1.0","source":{"id":"2201.02639","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02639","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02639v4","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02639","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"pith_short_12","alias_value":"BTF466H4EDI5","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"pith_short_16","alias_value":"BTF466H4EDI5KSLV","created_at":"2026-07-05T04:22:53Z"},{"alias_kind":"pith_short_8","alias_value":"BTF466H4","created_at":"2026-07-05T04:22:53Z"}],"graph_snapshots":[{"event_id":"sha256:216134c8a526028f024e5ba2385f6095fcd2da5bcf63407c56f924c9c001156f","target":"graph","created_at":"2026-07-05T04:22:53Z","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/2201.02639/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As humans, we navigate a multimodal world, building a holistic understanding from all our senses. We introduce MERLOT Reserve, a model that represents videos jointly over time -- through a new training objective that learns from audio, subtitles, and video frames. Given a video, we replace snippets of text and audio with a MASK token; the model learns by choosing the correct masked-out snippet. Our objective learns faster than alternatives, and performs well at scale: we pretrain on 20 million YouTube videos.\n  Empirical results show that MERLOT Reserve learns strong multimodal representations","authors_text":"Aditya Kusupati, Ali Farhadi, Jack Hessel, Jiasen Lu, Mohammadreza Salehi, Rowan Zellers, Ximing Lu, Yanpeng Zhao, Yejin Choi, Youngjae Yu","cross_cats":["cs.CL","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-07T19:00:21Z","title":"MERLOT Reserve: Neural Script Knowledge through Vision and Language and Sound"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02639","kind":"arxiv","version":4},"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":"sha256:4a0fa87f970dcdab453af1aad2a2086388acc1ed22b611e28945d01296406fd0","target":"record","created_at":"2026-07-05T04:22:53Z","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":"1ae8120e8fdaf74ee9b65f9b99027355bf4b6ee40d864ec7cf36866e15e7106d","cross_cats_sorted":["cs.CL","cs.LG","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-07T19:00:21Z","title_canon_sha256":"8b300b7a2ed75e09f6299cf38a60ca568acb5569bf3d3472b0e837d898c7b068"},"schema_version":"1.0","source":{"id":"2201.02639","kind":"arxiv","version":4}},"canonical_sha256":"0ccbcf78fc20d1d549755b5eaac32217bc373d7ea3fb4408cc3c9adce6b577f0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ccbcf78fc20d1d549755b5eaac32217bc373d7ea3fb4408cc3c9adce6b577f0","first_computed_at":"2026-07-05T04:22:53.584646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:22:53.584646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hp8XuZtOoWCmcaW/ozeWA/WvwfYzLo7L9UoWfXSNPvatzhyq/hQImewm9GN8aYLby4jvQtA1kHYDtKP899W3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:22:53.585206Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.02639","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a0fa87f970dcdab453af1aad2a2086388acc1ed22b611e28945d01296406fd0","sha256:216134c8a526028f024e5ba2385f6095fcd2da5bcf63407c56f924c9c001156f"],"state_sha256":"9fbe2939f12ce3d1a4e991880c2dc47ddb14cdee6d167acf36ee788fc6a17cee"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/vD41Aq4Wsh6LKy2M0Es+WESdP1S71NtZFfVaD+oVefYaIeXUn53T3vi0SyLyZ9WFFhBdLZeHHRc1B/U4+zPDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T22:46:33.899915Z","bundle_sha256":"9a54c6ad7044e3218f13a7c8a89037b01a1da9e853b31ae30af00c5245e35039"}}