{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:4RQQOP4WXUG4AZATBOBFUB5QYD","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":"99497e87677ffe510d396f76fcd59b9ec6e64741da2b04d9c2a5397e32b09461","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-04T17:57:39Z","title_canon_sha256":"a5442c58529ef299edfee7bcec9b3b9cf33ab442c936b10e370eb45fc186ddce"},"schema_version":"1.0","source":{"id":"2106.02636","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.02636","created_at":"2026-07-05T03:24:43Z"},{"alias_kind":"arxiv_version","alias_value":"2106.02636v3","created_at":"2026-07-05T03:24:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.02636","created_at":"2026-07-05T03:24:43Z"},{"alias_kind":"pith_short_12","alias_value":"4RQQOP4WXUG4","created_at":"2026-07-05T03:24:43Z"},{"alias_kind":"pith_short_16","alias_value":"4RQQOP4WXUG4AZAT","created_at":"2026-07-05T03:24:43Z"},{"alias_kind":"pith_short_8","alias_value":"4RQQOP4W","created_at":"2026-07-05T03:24:43Z"}],"graph_snapshots":[{"event_id":"sha256:be8bdeb0126782addf6c713dccc688c6b2d87ab7cfc684a4ce735d4bdbecf2b6","target":"graph","created_at":"2026-07-05T03:24:43Z","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/2106.02636/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As humans, we understand events in the visual world contextually, performing multimodal reasoning across time to make inferences about the past, present, and future. We introduce MERLOT, a model that learns multimodal script knowledge by watching millions of YouTube videos with transcribed speech -- in an entirely label-free, self-supervised manner. By pretraining with a mix of both frame-level (spatial) and video-level (temporal) objectives, our model not only learns to match images to temporally corresponding words, but also to contextualize what is happening globally over time. As a result,","authors_text":"Ali Farhadi, Jack Hessel, Jae Sung Park, Jize Cao, Rowan Zellers, Ximing Lu, Yejin Choi, Youngjae Yu","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-04T17:57:39Z","title":"MERLOT: Multimodal Neural Script Knowledge Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.02636","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:c5bd2516fc8589160960aaa71532490c2ae36a077519092817048d81b1fa9edd","target":"record","created_at":"2026-07-05T03:24:43Z","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":"99497e87677ffe510d396f76fcd59b9ec6e64741da2b04d9c2a5397e32b09461","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-04T17:57:39Z","title_canon_sha256":"a5442c58529ef299edfee7bcec9b3b9cf33ab442c936b10e370eb45fc186ddce"},"schema_version":"1.0","source":{"id":"2106.02636","kind":"arxiv","version":3}},"canonical_sha256":"e461073f96bd0dc064130b825a07b0c0cf5ea044f8d2d06af2b1ce70fcae692c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e461073f96bd0dc064130b825a07b0c0cf5ea044f8d2d06af2b1ce70fcae692c","first_computed_at":"2026-07-05T03:24:43.194080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:43.194080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KPwaeY3Iy/a9Crfr1togSal0rzRlqkbHcv56HT1aFf2pYmY4kRya98MQ0x6EE+I0rCAwMB5X9Dhq5x0dCq5KCg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:43.194589Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.02636","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5bd2516fc8589160960aaa71532490c2ae36a077519092817048d81b1fa9edd","sha256:be8bdeb0126782addf6c713dccc688c6b2d87ab7cfc684a4ce735d4bdbecf2b6"],"state_sha256":"db08fee19389a123049bffc34121dda3f524260d90f209ceb925b5942921b4f1"}