{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B5GK7HEGNYOBUOMCYAD7QZ3H2U","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":"4c9b819b41c164495d07d2df0d587c90fc2107bec5ccddafb31ed6b7ff3e4133","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T18:31:20Z","title_canon_sha256":"dd6efaf357de486dac905ca54d574d6be6535ce63a631716ec64a84610a67a4f"},"schema_version":"1.0","source":{"id":"2111.12681","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.12681","created_at":"2026-07-05T04:15:11Z"},{"alias_kind":"arxiv_version","alias_value":"2111.12681v2","created_at":"2026-07-05T04:15:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.12681","created_at":"2026-07-05T04:15:11Z"},{"alias_kind":"pith_short_12","alias_value":"B5GK7HEGNYOB","created_at":"2026-07-05T04:15:11Z"},{"alias_kind":"pith_short_16","alias_value":"B5GK7HEGNYOBUOMC","created_at":"2026-07-05T04:15:11Z"},{"alias_kind":"pith_short_8","alias_value":"B5GK7HEG","created_at":"2026-07-05T04:15:11Z"}],"graph_snapshots":[{"event_id":"sha256:a3d6f51aeae5a5d648358acc12a6dc0bd4bf174fabad83855e0c1bff6812d1a7","target":"graph","created_at":"2026-07-05T04:15:11Z","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/2111.12681/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A great challenge in video-language (VidL) modeling lies in the disconnection between fixed video representations extracted from image/video understanding models and downstream VidL data. Recent studies try to mitigate this disconnection via end-to-end training. To make it computationally feasible, prior works tend to \"imagify\" video inputs, i.e., a handful of sparsely sampled frames are fed into a 2D CNN, followed by a simple mean-pooling or concatenation to obtain the overall video representations. Although achieving promising results, such simple approaches may lose temporal information tha","authors_text":"Kevin Lin, Lijuan Wang, Linjie Li, Tsu-Jui Fu, William Yang Wang, Zhe Gan, Zicheng Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T18:31:20Z","title":"VIOLET : End-to-End Video-Language Transformers with Masked Visual-token Modeling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.12681","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":"sha256:6577783fe229bb6dd1ac17b2c9f496347f9cb89848a20c28306f3604949c523c","target":"record","created_at":"2026-07-05T04:15:11Z","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":"4c9b819b41c164495d07d2df0d587c90fc2107bec5ccddafb31ed6b7ff3e4133","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-11-24T18:31:20Z","title_canon_sha256":"dd6efaf357de486dac905ca54d574d6be6535ce63a631716ec64a84610a67a4f"},"schema_version":"1.0","source":{"id":"2111.12681","kind":"arxiv","version":2}},"canonical_sha256":"0f4caf9c866e1c1a3982c007f86767d517198327dbe417a93a4476afcc5958d5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f4caf9c866e1c1a3982c007f86767d517198327dbe417a93a4476afcc5958d5","first_computed_at":"2026-07-05T04:15:11.988646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:15:11.988646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cQTL8sP8HF1brhZxUjok7wdlE0a1v2n2ki9n3iFoqSJRHrSEK+Ppoex5EoYwY9sWdHpOqNwuEQ6/gQ8U7KbPCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:15:11.989182Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.12681","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6577783fe229bb6dd1ac17b2c9f496347f9cb89848a20c28306f3604949c523c","sha256:a3d6f51aeae5a5d648358acc12a6dc0bd4bf174fabad83855e0c1bff6812d1a7"],"state_sha256":"20e166d5307186278a05d26c3c13379d822a3a3f293af11fd7de7ac75a5fa340"}