{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FVZODSESEBKCVHUL5ZQKGPSWF2","short_pith_number":"pith:FVZODSES","canonical_record":{"source":{"id":"2103.10043","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-18T06:39:09Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"76de83e8c792a561ed36a756055ee7ee09a13a5b874e29659c6b1590b9697f19","abstract_canon_sha256":"0ee013d5a93493590f516a18a41b0ad113c1c5c426a32384b3b6346a26a816f3"},"schema_version":"1.0"},"canonical_sha256":"2d72e1c89220542a9e8bee60a33e562ea1878a531fc7edf0f6aa1a0f6455c6e9","source":{"kind":"arxiv","id":"2103.10043","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10043","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10043v1","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10043","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"FVZODSESEBKC","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"FVZODSESEBKCVHUL","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"FVZODSES","created_at":"2026-07-05T02:24:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FVZODSESEBKCVHUL5ZQKGPSWF2","target":"record","payload":{"canonical_record":{"source":{"id":"2103.10043","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-18T06:39:09Z","cross_cats_sorted":["cs.LG","cs.MM"],"title_canon_sha256":"76de83e8c792a561ed36a756055ee7ee09a13a5b874e29659c6b1590b9697f19","abstract_canon_sha256":"0ee013d5a93493590f516a18a41b0ad113c1c5c426a32384b3b6346a26a816f3"},"schema_version":"1.0"},"canonical_sha256":"2d72e1c89220542a9e8bee60a33e562ea1878a531fc7edf0f6aa1a0f6455c6e9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:24:15.953344Z","signature_b64":"Gv3UaTt5nKfz9/aUdWhUTWb64GIq/FOGo6G29rFqwfqGkfrFDBeZvp/pFy50RGg1TsUllA3mb2qzxe8fuBlJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d72e1c89220542a9e8bee60a33e562ea1878a531fc7edf0f6aa1a0f6455c6e9","last_reissued_at":"2026-07-05T02:24:15.952988Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:24:15.952988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2103.10043","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"id3LlrtzwmMFBz/IlmjhXFh3zk2+yL7qQ7YKRcuqBU5ljR9ocxafKagcr7ThhAvu70kuI9LbVxavzKZ9Zi/ACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:47:51.413152Z"},"content_sha256":"7c98b95b35d1e92017bb947600e33344d2a9b7d9098a654b3f8305eb9536e505","schema_version":"1.0","event_id":"sha256:7c98b95b35d1e92017bb947600e33344d2a9b7d9098a654b3f8305eb9536e505"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FVZODSESEBKCVHUL5ZQKGPSWF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.MM"],"primary_cat":"cs.CV","authors_text":"Palash Goyal, Saurabh Sahu","submitted_at":"2021-03-18T06:39:09Z","abstract_excerpt":"The introduction of Transformer model has led to tremendous advancements in sequence modeling, especially in text domain. However, the use of attention-based models for video understanding is still relatively unexplored. In this paper, we introduce Gated Adversarial Transformer (GAT) to enhance the applicability of attention-based models to videos. GAT uses a multi-level attention gate to model the relevance of a frame based on local and global contexts. This enables the model to understand the video at various granularities. Further, GAT uses adversarial training to improve model generalizati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10043","kind":"arxiv","version":1},"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/2103.10043/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":"2026-07-05T02:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6J9LOtUjdvDgeQ27rXwh+RFsK6BjwAgmiWGWAVjgGODL+pi1QCbDwrOViUemHSp9yPo1wsVGDKTyhF51F7g+BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T13:47:51.413539Z"},"content_sha256":"11c161124ab05aa4cf59397b62b02c2fb586326064b5f804d1a4f97081698d31","schema_version":"1.0","event_id":"sha256:11c161124ab05aa4cf59397b62b02c2fb586326064b5f804d1a4f97081698d31"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/bundle.json","state_url":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/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":"2026-07-06T13:47:51Z","links":{"resolver":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2","bundle":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/bundle.json","state":"https://pith.science/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FVZODSESEBKCVHUL5ZQKGPSWF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FVZODSESEBKCVHUL5ZQKGPSWF2","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":"0ee013d5a93493590f516a18a41b0ad113c1c5c426a32384b3b6346a26a816f3","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-18T06:39:09Z","title_canon_sha256":"76de83e8c792a561ed36a756055ee7ee09a13a5b874e29659c6b1590b9697f19"},"schema_version":"1.0","source":{"id":"2103.10043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2103.10043","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2103.10043v1","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.10043","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"FVZODSESEBKC","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"FVZODSESEBKCVHUL","created_at":"2026-07-05T02:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"FVZODSES","created_at":"2026-07-05T02:24:15Z"}],"graph_snapshots":[{"event_id":"sha256:11c161124ab05aa4cf59397b62b02c2fb586326064b5f804d1a4f97081698d31","target":"graph","created_at":"2026-07-05T02:24:15Z","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/2103.10043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The introduction of Transformer model has led to tremendous advancements in sequence modeling, especially in text domain. However, the use of attention-based models for video understanding is still relatively unexplored. In this paper, we introduce Gated Adversarial Transformer (GAT) to enhance the applicability of attention-based models to videos. GAT uses a multi-level attention gate to model the relevance of a frame based on local and global contexts. This enables the model to understand the video at various granularities. Further, GAT uses adversarial training to improve model generalizati","authors_text":"Palash Goyal, Saurabh Sahu","cross_cats":["cs.LG","cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-18T06:39:09Z","title":"Enhancing Transformer for Video Understanding Using Gated Multi-Level Attention and Temporal Adversarial Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.10043","kind":"arxiv","version":1},"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":"sha256:7c98b95b35d1e92017bb947600e33344d2a9b7d9098a654b3f8305eb9536e505","target":"record","created_at":"2026-07-05T02:24:15Z","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":"0ee013d5a93493590f516a18a41b0ad113c1c5c426a32384b3b6346a26a816f3","cross_cats_sorted":["cs.LG","cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-03-18T06:39:09Z","title_canon_sha256":"76de83e8c792a561ed36a756055ee7ee09a13a5b874e29659c6b1590b9697f19"},"schema_version":"1.0","source":{"id":"2103.10043","kind":"arxiv","version":1}},"canonical_sha256":"2d72e1c89220542a9e8bee60a33e562ea1878a531fc7edf0f6aa1a0f6455c6e9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d72e1c89220542a9e8bee60a33e562ea1878a531fc7edf0f6aa1a0f6455c6e9","first_computed_at":"2026-07-05T02:24:15.952988Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:24:15.952988Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gv3UaTt5nKfz9/aUdWhUTWb64GIq/FOGo6G29rFqwfqGkfrFDBeZvp/pFy50RGg1TsUllA3mb2qzxe8fuBlJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:24:15.953344Z","signed_message":"canonical_sha256_bytes"},"source_id":"2103.10043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7c98b95b35d1e92017bb947600e33344d2a9b7d9098a654b3f8305eb9536e505","sha256:11c161124ab05aa4cf59397b62b02c2fb586326064b5f804d1a4f97081698d31"],"state_sha256":"fb831e0f3cb8035222afa384141a9c0eb082c52ed57c9199608d2d028722b4de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SNQa1hSHDUiVs4VwruZk5PmHl0Xger72v91wv+gySQMDTyRyxXwLOJFtzi/UeaTacQGviGp14dIV7oJafpRFBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T13:47:51.415476Z","bundle_sha256":"ef15de58e91a1ea6ef8fc18547ead8c7b63df73ef3c74313676088620be0c9d4"}}