{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HT4T6FIMXZPAA4JXEPJZ656XII","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":"3a925f650450bec7b1c887b30e27f4252b13d6cdeeb42fe8aa058715d4403f26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T18:02:12Z","title_canon_sha256":"cc89fe419599ebe5827524fd5a04bb0df4cc1fa19d9682d4413de3163f101e84"},"schema_version":"1.0","source":{"id":"2111.13196","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2111.13196","created_at":"2026-07-05T04:32:53Z"},{"alias_kind":"arxiv_version","alias_value":"2111.13196v4","created_at":"2026-07-05T04:32:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.13196","created_at":"2026-07-05T04:32:53Z"},{"alias_kind":"pith_short_12","alias_value":"HT4T6FIMXZPA","created_at":"2026-07-05T04:32:53Z"},{"alias_kind":"pith_short_16","alias_value":"HT4T6FIMXZPAA4JX","created_at":"2026-07-05T04:32:53Z"},{"alias_kind":"pith_short_8","alias_value":"HT4T6FIM","created_at":"2026-07-05T04:32:53Z"}],"graph_snapshots":[{"event_id":"sha256:fe70715009f11aad56fdf9ad9bf12f0b0adeda8d5b4e30ccd858d1297bad578b","target":"graph","created_at":"2026-07-05T04:32:53Z","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/2111.13196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The canonical approach to video captioning dictates a caption generation model to learn from offline-extracted dense video features. These feature extractors usually operate on video frames sampled at a fixed frame rate and are often trained on image/video understanding tasks, without adaption to video captioning data. In this work, we present SwinBERT, an end-to-end transformer-based model for video captioning, which takes video frame patches directly as inputs, and outputs a natural language description. Instead of leveraging multiple 2D/3D feature extractors, our method adopts a video trans","authors_text":"Chung-Ching Lin, Faisal Ahmed, Kevin Lin, Lijuan Wang, Linjie Li, Yumao Lu, Zhe Gan, Zicheng Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T18:02:12Z","title":"SwinBERT: End-to-End Transformers with Sparse Attention for Video Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.13196","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":"sha256:84b8b990bfe84d808be5542eeabe6a00788e5268b109109557e1755adc6c62b4","target":"record","created_at":"2026-07-05T04:32:53Z","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":"3a925f650450bec7b1c887b30e27f4252b13d6cdeeb42fe8aa058715d4403f26","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-11-25T18:02:12Z","title_canon_sha256":"cc89fe419599ebe5827524fd5a04bb0df4cc1fa19d9682d4413de3163f101e84"},"schema_version":"1.0","source":{"id":"2111.13196","kind":"arxiv","version":4}},"canonical_sha256":"3cf93f150cbe5e00713723d39f77d7422d6198d87f1926e2c771552e53824143","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3cf93f150cbe5e00713723d39f77d7422d6198d87f1926e2c771552e53824143","first_computed_at":"2026-07-05T04:32:53.090527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:32:53.090527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZXjrBWq3A38If1y0hPXWS+tMJ5yOwGuAoxoqLiVizK7c+7JGpinpt6gcRUxjXmRRtCat+Lm7v2aoEM4v+RvuAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:32:53.091008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2111.13196","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84b8b990bfe84d808be5542eeabe6a00788e5268b109109557e1755adc6c62b4","sha256:fe70715009f11aad56fdf9ad9bf12f0b0adeda8d5b4e30ccd858d1297bad578b"],"state_sha256":"4b447484f42a6a674a336f0fb7b151d58a08b38d7b9f72ca6ea1ab0b5dd3965e"}