{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:RUKBH75CVZILTKC6G35D4KWKZF","short_pith_number":"pith:RUKBH75C","canonical_record":{"source":{"id":"2112.07175","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T05:41:39Z","cross_cats_sorted":[],"title_canon_sha256":"f2bd82afdc2151810c57f325278b03172a04d49532c522379104af99b0a5df6f","abstract_canon_sha256":"bd03c2cbc900a116b6f5c5bc26e9d4ff61f17388c1b4005cec4c229f591e92e7"},"schema_version":"1.0"},"canonical_sha256":"8d1413ffa2ae50b9a85e36fa3e2acac95eec5352bf363f84a7234ca1d8f4188e","source":{"kind":"arxiv","id":"2112.07175","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07175","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07175v1","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07175","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"RUKBH75CVZIL","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"pith_short_16","alias_value":"RUKBH75CVZILTKC6","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"pith_short_8","alias_value":"RUKBH75C","created_at":"2026-07-05T03:40:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:RUKBH75CVZILTKC6G35D4KWKZF","target":"record","payload":{"canonical_record":{"source":{"id":"2112.07175","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T05:41:39Z","cross_cats_sorted":[],"title_canon_sha256":"f2bd82afdc2151810c57f325278b03172a04d49532c522379104af99b0a5df6f","abstract_canon_sha256":"bd03c2cbc900a116b6f5c5bc26e9d4ff61f17388c1b4005cec4c229f591e92e7"},"schema_version":"1.0"},"canonical_sha256":"8d1413ffa2ae50b9a85e36fa3e2acac95eec5352bf363f84a7234ca1d8f4188e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:40:55.478061Z","signature_b64":"7tnTPsN39qmjT82insWQrZx/ei/61GEv2BTBrPWMjJixSNZ6EBO3OZiWxKn0YwzoHmviexZPP2BGZHCYelvtDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d1413ffa2ae50b9a85e36fa3e2acac95eec5352bf363f84a7234ca1d8f4188e","last_reissued_at":"2026-07-05T03:40:55.477596Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:40:55.477596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.07175","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":"2026-07-05T03:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FX9CDlvMgc7KMLacK2cp+gtVx+KmIRbehE8jq++bPTwRVtxJWVJI9DDEQp+QlnAvOXzYz5m4kYc+zUcEar3zDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:30:26.203930Z"},"content_sha256":"8acc563f5323cefbc15b5ac639eb30d4c69094970b31dcfa315734b889ade414","schema_version":"1.0","event_id":"sha256:8acc563f5323cefbc15b5ac639eb30d4c69094970b31dcfa315734b889ade414"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:RUKBH75CVZILTKC6G35D4KWKZF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Co-training Transformer with Videos and Images Improves Action Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Andrew M. Dai, Bowen Zhang, Christopher Fifty, Fei Sha, Jiahui Yu, Ruoming Pang, Wei Han","submitted_at":"2021-12-14T05:41:39Z","abstract_excerpt":"In learning action recognition, models are typically pre-trained on object recognition with images, such as ImageNet, and later fine-tuned on target action recognition with videos. This approach has achieved good empirical performance especially with recent transformer-based video architectures. While recently many works aim to design more advanced transformer architectures for action recognition, less effort has been made on how to train video transformers. In this work, we explore several training paradigms and present two findings. First, video transformers benefit from joint training on di"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07175","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/2112.07175/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":"2026-07-05T03:40:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q6rhtpsm7gtDPT9pa7Wcl//mhJ34YAYyPJCLAAFub6dHtP/baAoibRRTWWcJ3aAnCwGzqC5QToN4EG/Xt20BBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:30:26.204430Z"},"content_sha256":"69610343e4735a6d23680d6f1935a4ae0437bde41f9fe5df7dee7999957bb376","schema_version":"1.0","event_id":"sha256:69610343e4735a6d23680d6f1935a4ae0437bde41f9fe5df7dee7999957bb376"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RUKBH75CVZILTKC6G35D4KWKZF/bundle.json","state_url":"https://pith.science/pith/RUKBH75CVZILTKC6G35D4KWKZF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RUKBH75CVZILTKC6G35D4KWKZF/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":"2026-08-09T22:30:26Z","links":{"resolver":"https://pith.science/pith/RUKBH75CVZILTKC6G35D4KWKZF","bundle":"https://pith.science/pith/RUKBH75CVZILTKC6G35D4KWKZF/bundle.json","state":"https://pith.science/pith/RUKBH75CVZILTKC6G35D4KWKZF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RUKBH75CVZILTKC6G35D4KWKZF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:RUKBH75CVZILTKC6G35D4KWKZF","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":"bd03c2cbc900a116b6f5c5bc26e9d4ff61f17388c1b4005cec4c229f591e92e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T05:41:39Z","title_canon_sha256":"f2bd82afdc2151810c57f325278b03172a04d49532c522379104af99b0a5df6f"},"schema_version":"1.0","source":{"id":"2112.07175","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.07175","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"arxiv_version","alias_value":"2112.07175v1","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.07175","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"pith_short_12","alias_value":"RUKBH75CVZIL","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"pith_short_16","alias_value":"RUKBH75CVZILTKC6","created_at":"2026-07-05T03:40:55Z"},{"alias_kind":"pith_short_8","alias_value":"RUKBH75C","created_at":"2026-07-05T03:40:55Z"}],"graph_snapshots":[{"event_id":"sha256:69610343e4735a6d23680d6f1935a4ae0437bde41f9fe5df7dee7999957bb376","target":"graph","created_at":"2026-07-05T03:40:55Z","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/2112.07175/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In learning action recognition, models are typically pre-trained on object recognition with images, such as ImageNet, and later fine-tuned on target action recognition with videos. This approach has achieved good empirical performance especially with recent transformer-based video architectures. While recently many works aim to design more advanced transformer architectures for action recognition, less effort has been made on how to train video transformers. In this work, we explore several training paradigms and present two findings. First, video transformers benefit from joint training on di","authors_text":"Andrew M. Dai, Bowen Zhang, Christopher Fifty, Fei Sha, Jiahui Yu, Ruoming Pang, Wei Han","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T05:41:39Z","title":"Co-training Transformer with Videos and Images Improves Action Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.07175","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":"sha256:8acc563f5323cefbc15b5ac639eb30d4c69094970b31dcfa315734b889ade414","target":"record","created_at":"2026-07-05T03:40:55Z","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":"bd03c2cbc900a116b6f5c5bc26e9d4ff61f17388c1b4005cec4c229f591e92e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-12-14T05:41:39Z","title_canon_sha256":"f2bd82afdc2151810c57f325278b03172a04d49532c522379104af99b0a5df6f"},"schema_version":"1.0","source":{"id":"2112.07175","kind":"arxiv","version":1}},"canonical_sha256":"8d1413ffa2ae50b9a85e36fa3e2acac95eec5352bf363f84a7234ca1d8f4188e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d1413ffa2ae50b9a85e36fa3e2acac95eec5352bf363f84a7234ca1d8f4188e","first_computed_at":"2026-07-05T03:40:55.477596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:40:55.477596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7tnTPsN39qmjT82insWQrZx/ei/61GEv2BTBrPWMjJixSNZ6EBO3OZiWxKn0YwzoHmviexZPP2BGZHCYelvtDA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:40:55.478061Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.07175","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8acc563f5323cefbc15b5ac639eb30d4c69094970b31dcfa315734b889ade414","sha256:69610343e4735a6d23680d6f1935a4ae0437bde41f9fe5df7dee7999957bb376"],"state_sha256":"5493ff0006fb25a80e9e54572b73e5904857e345147da602d0d9f9391a82e516"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EuLNnM8abF9/WwCi64imjJFRGhhdjfUtPmfNQFKIacZ9kE9jycYwxKiUg8pP1dA+7PTghg4GGWuacYEx9BdqCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:30:26.207765Z","bundle_sha256":"cc32b6a77c7aacec24857cb859e6081e09eeba1e5ae82564b522eb696d90f14d"}}