{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6IBFJNAXNW4OUVLS5K5RP5AVE4","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":"88556f0cff69468657a60a311b66803df95ececb4c371c9448277c8c07b60db6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-20T19:13:27Z","title_canon_sha256":"b4d60d09d3bb26e68d145b29c94ce906697d4ce8dad927c207fa15ea93081df8"},"schema_version":"1.0","source":{"id":"2105.09996","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.09996","created_at":"2026-07-05T03:19:12Z"},{"alias_kind":"arxiv_version","alias_value":"2105.09996v3","created_at":"2026-07-05T03:19:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.09996","created_at":"2026-07-05T03:19:12Z"},{"alias_kind":"pith_short_12","alias_value":"6IBFJNAXNW4O","created_at":"2026-07-05T03:19:12Z"},{"alias_kind":"pith_short_16","alias_value":"6IBFJNAXNW4OUVLS","created_at":"2026-07-05T03:19:12Z"},{"alias_kind":"pith_short_8","alias_value":"6IBFJNAX","created_at":"2026-07-05T03:19:12Z"}],"graph_snapshots":[{"event_id":"sha256:5a7a5f33901f5473e7ad206dd8db975d2c90100fea61e02baba994ae356e0dc5","target":"graph","created_at":"2026-07-05T03:19:12Z","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/2105.09996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present a simplified, task-agnostic multi-modal pre-training approach that can accept either video or text input, or both for a variety of end tasks. Existing pre-training are task-specific by adopting either a single cross-modal encoder that requires both modalities, limiting their use for retrieval-style end tasks or more complex multitask learning with two unimodal encoders, limiting early cross-modal fusion. We instead introduce new pretraining masking schemes that better mix across modalities (e.g. by forcing masks for text to predict the closest video embeddings) while also maintainin","authors_text":"Christoph Feichtenhofer, Florian Metze, Gargi Ghosh, Hu Xu, Luke Zettlemoyer, Masoumeh Aminzadeh, Po-Yao Huang, Prahal Arora","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-20T19:13:27Z","title":"VLM: Task-agnostic Video-Language Model Pre-training for Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.09996","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:dbdd299b226c0872b22ff450092b551c0f425548cb584f7ddcc29a5783db4593","target":"record","created_at":"2026-07-05T03:19:12Z","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":"88556f0cff69468657a60a311b66803df95ececb4c371c9448277c8c07b60db6","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2021-05-20T19:13:27Z","title_canon_sha256":"b4d60d09d3bb26e68d145b29c94ce906697d4ce8dad927c207fa15ea93081df8"},"schema_version":"1.0","source":{"id":"2105.09996","kind":"arxiv","version":3}},"canonical_sha256":"f20254b4176db8ea5572eabb17f4152710f369b9eed13edd27067d5e0d52e04a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f20254b4176db8ea5572eabb17f4152710f369b9eed13edd27067d5e0d52e04a","first_computed_at":"2026-07-05T03:19:12.161444Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:19:12.161444Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OPk1rvj3RecoW+Ty3BjySxNPW9x/vfl/Spo/gGIo8x74RpkJ9Xm2mf5Rj0TLnXujf1iVYKpqz2lAu5nnH7k9BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:19:12.161878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.09996","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dbdd299b226c0872b22ff450092b551c0f425548cb584f7ddcc29a5783db4593","sha256:5a7a5f33901f5473e7ad206dd8db975d2c90100fea61e02baba994ae356e0dc5"],"state_sha256":"9f51eadeff7a1dff192cac5285c858b84442d9b06e04c40821546378dd4ebf38"}