{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:HXB5QBHEGITVCJHOS27UFKZCRO","short_pith_number":"pith:HXB5QBHE","canonical_record":{"source":{"id":"2106.05058","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-09T13:26:02Z","cross_cats_sorted":[],"title_canon_sha256":"b5250df4171dd05565449312acac8d9949e79fe120c2b77097772a8f76e59235","abstract_canon_sha256":"f6eab95667c8f22b47f473f41ef9b07a27c872cc1258732c6cb23ea37dd49773"},"schema_version":"1.0"},"canonical_sha256":"3dc3d804e432275124ee96bf42ab228b9a706cf34af923e564e3f3c713d8713f","source":{"kind":"arxiv","id":"2106.05058","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05058","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05058v1","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05058","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"HXB5QBHEGITV","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"HXB5QBHEGITVCJHO","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"HXB5QBHE","created_at":"2026-07-05T02:47:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:HXB5QBHEGITVCJHOS27UFKZCRO","target":"record","payload":{"canonical_record":{"source":{"id":"2106.05058","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-09T13:26:02Z","cross_cats_sorted":[],"title_canon_sha256":"b5250df4171dd05565449312acac8d9949e79fe120c2b77097772a8f76e59235","abstract_canon_sha256":"f6eab95667c8f22b47f473f41ef9b07a27c872cc1258732c6cb23ea37dd49773"},"schema_version":"1.0"},"canonical_sha256":"3dc3d804e432275124ee96bf42ab228b9a706cf34af923e564e3f3c713d8713f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:47:52.288009Z","signature_b64":"brjBdl6VhK+8GucV2jzXjlpQCfBLZ9grgAIUHDUM9g6VEgbYb6hxIiOxD7CCy9TweqA2+wD7T29KzdBGzFV2Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3dc3d804e432275124ee96bf42ab228b9a706cf34af923e564e3f3c713d8713f","last_reissued_at":"2026-07-05T02:47:52.287662Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:47:52.287662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.05058","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":"2026-07-05T02:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z7s80tj6bJRDXV9KuENxP2e38mvYCnTUQEzjC+xwcFAI2W95qCLb+QeyaCxjrGYQ03+GQ50yDtSDiYIi61VQBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:10:31.827283Z"},"content_sha256":"9dcdc7021c188c6120b2e19437aebfbdb54a1034cc50f7b3e7bad8fc75206a43","schema_version":"1.0","event_id":"sha256:9dcdc7021c188c6120b2e19437aebfbdb54a1034cc50f7b3e7bad8fc75206a43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:HXB5QBHEGITVCJHOS27UFKZCRO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jianwen Jiang, Marcelo H. Ang Jr, Mingqian Tang, Nong Sang, Shiwei Zhang, Xiang Wang, Yutong Feng, Zhiwu Qing, Zhurong Xia, Ziyuan Huang","submitted_at":"2021-06-09T13:26:02Z","abstract_excerpt":"With the recent surge in the research of vision transformers, they have demonstrated remarkable potential for various challenging computer vision applications, such as image recognition, point cloud classification as well as video understanding. In this paper, we present empirical results for training a stronger video vision transformer on the EPIC-KITCHENS-100 Action Recognition dataset. Specifically, we explore training techniques for video vision transformers, such as augmentations, resolutions as well as initialization, etc. With our training recipe, a single ViViT model achieves the perfo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05058","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/2106.05058/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":"2026-07-05T02:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Vk6Vrz27JUQCrK35DpwiHcaeez8B3urHOAZRYAAAuDsudbpFj7QZpCJdl5BHGJ6inODq/GOEyneIzH7EaNO3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-05T13:10:31.827727Z"},"content_sha256":"7cfa6a8cef49aa18ae963a649ae2e7c33d3200a1f0e0015c484088c0142351b9","schema_version":"1.0","event_id":"sha256:7cfa6a8cef49aa18ae963a649ae2e7c33d3200a1f0e0015c484088c0142351b9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HXB5QBHEGITVCJHOS27UFKZCRO/bundle.json","state_url":"https://pith.science/pith/HXB5QBHEGITVCJHOS27UFKZCRO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HXB5QBHEGITVCJHOS27UFKZCRO/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":"2026-07-05T13:10:31Z","links":{"resolver":"https://pith.science/pith/HXB5QBHEGITVCJHOS27UFKZCRO","bundle":"https://pith.science/pith/HXB5QBHEGITVCJHOS27UFKZCRO/bundle.json","state":"https://pith.science/pith/HXB5QBHEGITVCJHOS27UFKZCRO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HXB5QBHEGITVCJHOS27UFKZCRO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:HXB5QBHEGITVCJHOS27UFKZCRO","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":"f6eab95667c8f22b47f473f41ef9b07a27c872cc1258732c6cb23ea37dd49773","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-09T13:26:02Z","title_canon_sha256":"b5250df4171dd05565449312acac8d9949e79fe120c2b77097772a8f76e59235"},"schema_version":"1.0","source":{"id":"2106.05058","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.05058","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2106.05058v1","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.05058","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"HXB5QBHEGITV","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"HXB5QBHEGITVCJHO","created_at":"2026-07-05T02:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"HXB5QBHE","created_at":"2026-07-05T02:47:52Z"}],"graph_snapshots":[{"event_id":"sha256:7cfa6a8cef49aa18ae963a649ae2e7c33d3200a1f0e0015c484088c0142351b9","target":"graph","created_at":"2026-07-05T02:47:52Z","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/2106.05058/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the recent surge in the research of vision transformers, they have demonstrated remarkable potential for various challenging computer vision applications, such as image recognition, point cloud classification as well as video understanding. In this paper, we present empirical results for training a stronger video vision transformer on the EPIC-KITCHENS-100 Action Recognition dataset. Specifically, we explore training techniques for video vision transformers, such as augmentations, resolutions as well as initialization, etc. With our training recipe, a single ViViT model achieves the perfo","authors_text":"Jianwen Jiang, Marcelo H. Ang Jr, Mingqian Tang, Nong Sang, Shiwei Zhang, Xiang Wang, Yutong Feng, Zhiwu Qing, Zhurong Xia, Ziyuan Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-09T13:26:02Z","title":"Towards Training Stronger Video Vision Transformers for EPIC-KITCHENS-100 Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.05058","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":"sha256:9dcdc7021c188c6120b2e19437aebfbdb54a1034cc50f7b3e7bad8fc75206a43","target":"record","created_at":"2026-07-05T02:47:52Z","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":"f6eab95667c8f22b47f473f41ef9b07a27c872cc1258732c6cb23ea37dd49773","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-06-09T13:26:02Z","title_canon_sha256":"b5250df4171dd05565449312acac8d9949e79fe120c2b77097772a8f76e59235"},"schema_version":"1.0","source":{"id":"2106.05058","kind":"arxiv","version":1}},"canonical_sha256":"3dc3d804e432275124ee96bf42ab228b9a706cf34af923e564e3f3c713d8713f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3dc3d804e432275124ee96bf42ab228b9a706cf34af923e564e3f3c713d8713f","first_computed_at":"2026-07-05T02:47:52.287662Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:47:52.287662Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"brjBdl6VhK+8GucV2jzXjlpQCfBLZ9grgAIUHDUM9g6VEgbYb6hxIiOxD7CCy9TweqA2+wD7T29KzdBGzFV2Cw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:47:52.288009Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.05058","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9dcdc7021c188c6120b2e19437aebfbdb54a1034cc50f7b3e7bad8fc75206a43","sha256:7cfa6a8cef49aa18ae963a649ae2e7c33d3200a1f0e0015c484088c0142351b9"],"state_sha256":"84bc631664c0d09e5f09a2d9f0b2fe734588431b612bcbea86f74fa34fb1227f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A2hfSCeQx1UtfFgv2UoRGM+PlRdSv5Dc55Z5MG7qsBj6yce+UBEoaaaND4t43QsaWRmiDKrQjyoaKKIZgfjsDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-05T13:10:31.830207Z","bundle_sha256":"ba89c9026297b54a999628c0120591c5c674f7fcd5a92faa8616df22bbb0bc00"}}