{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2COMO4YJSTW4VLKP6RINLCCQQR","short_pith_number":"pith:2COMO4YJ","canonical_record":{"source":{"id":"2211.09552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T14:17:40Z","cross_cats_sorted":[],"title_canon_sha256":"0f17f8051f1d028cbafdd51e48bc2c1cb6f97b880c418fc28802fca95e3ce9e5","abstract_canon_sha256":"c463fa6beb6aae7c532105b372d8b9e030f24beb13b3be67d029a98cb04cf379"},"schema_version":"1.0"},"canonical_sha256":"d09cc7730994edcaad4ff450d588508463d36a700a7c90c6542629671c98be6c","source":{"kind":"arxiv","id":"2211.09552","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09552","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09552v1","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09552","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"2COMO4YJSTW4","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"2COMO4YJSTW4VLKP","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"2COMO4YJ","created_at":"2026-07-05T05:17:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2COMO4YJSTW4VLKP6RINLCCQQR","target":"record","payload":{"canonical_record":{"source":{"id":"2211.09552","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T14:17:40Z","cross_cats_sorted":[],"title_canon_sha256":"0f17f8051f1d028cbafdd51e48bc2c1cb6f97b880c418fc28802fca95e3ce9e5","abstract_canon_sha256":"c463fa6beb6aae7c532105b372d8b9e030f24beb13b3be67d029a98cb04cf379"},"schema_version":"1.0"},"canonical_sha256":"d09cc7730994edcaad4ff450d588508463d36a700a7c90c6542629671c98be6c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:17:03.566250Z","signature_b64":"mTYM6M622sf8/Fdj2vt8mWJEq6TOEQShg8CQGRGOT5VYCoYruCjZ4ZBNZxm7qcsdjTSuDRaAVJ17g4ZzIsWgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d09cc7730994edcaad4ff450d588508463d36a700a7c90c6542629671c98be6c","last_reissued_at":"2026-07-05T05:17:03.565914Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:17:03.565914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.09552","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":"2026-07-05T05:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MvoAuFImIsqlC2jFSgHpAIb1SwOSzF8T44S4rsQPg3x13UJ0xVp3DJ2boRnO1p5WjOK1VGS3EosorcE4hiMgAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:38:32.569691Z"},"content_sha256":"47eae53129e292331abcad2588e7adbe8834ec332de85b0a05ec4fd78f52ae45","schema_version":"1.0","event_id":"sha256:47eae53129e292331abcad2588e7adbe8834ec332de85b0a05ec4fd78f52ae45"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2COMO4YJSTW4VLKP6RINLCCQQR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kunchang Li, Limin Wang, Yali Wang, Yinan He, Yi Wang, Yizhuo Li, Yu Qiao","submitted_at":"2022-11-17T14:17:40Z","abstract_excerpt":"Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they exhibit limitations in tackling local video redundancy, due to the blind global comparison among tokens. UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format. However, this model has to require a tiresome and complicated image-pretraining phrase, before being finetuned on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09552","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/2211.09552/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":"2026-07-05T05:17:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4egL5yl4xjUeae6EzIX3Z6ISwu0UUOV5NwRD8V8/vovQ6Zi4EWKQDU+0ZMamNYtpypwyHLiYbvmovw1Ve3qnAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:38:32.570503Z"},"content_sha256":"f88a11acdbfad84ead1305bb638d94b16122d1e31b73a5be29b7a5833f844115","schema_version":"1.0","event_id":"sha256:f88a11acdbfad84ead1305bb638d94b16122d1e31b73a5be29b7a5833f844115"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR/bundle.json","state_url":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2COMO4YJSTW4VLKP6RINLCCQQR/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":"2026-08-07T05:38:32Z","links":{"resolver":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR","bundle":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR/bundle.json","state":"https://pith.science/pith/2COMO4YJSTW4VLKP6RINLCCQQR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2COMO4YJSTW4VLKP6RINLCCQQR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2COMO4YJSTW4VLKP6RINLCCQQR","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":"c463fa6beb6aae7c532105b372d8b9e030f24beb13b3be67d029a98cb04cf379","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T14:17:40Z","title_canon_sha256":"0f17f8051f1d028cbafdd51e48bc2c1cb6f97b880c418fc28802fca95e3ce9e5"},"schema_version":"1.0","source":{"id":"2211.09552","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.09552","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2211.09552v1","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.09552","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"2COMO4YJSTW4","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"2COMO4YJSTW4VLKP","created_at":"2026-07-05T05:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"2COMO4YJ","created_at":"2026-07-05T05:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:f88a11acdbfad84ead1305bb638d94b16122d1e31b73a5be29b7a5833f844115","target":"graph","created_at":"2026-07-05T05:17:03Z","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/2211.09552/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning discriminative spatiotemporal representation is the key problem of video understanding. Recently, Vision Transformers (ViTs) have shown their power in learning long-term video dependency with self-attention. Unfortunately, they exhibit limitations in tackling local video redundancy, due to the blind global comparison among tokens. UniFormer has successfully alleviated this issue, by unifying convolution and self-attention as a relation aggregator in the transformer format. However, this model has to require a tiresome and complicated image-pretraining phrase, before being finetuned on","authors_text":"Kunchang Li, Limin Wang, Yali Wang, Yinan He, Yi Wang, Yizhuo Li, Yu Qiao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T14:17:40Z","title":"UniFormerV2: Spatiotemporal Learning by Arming Image ViTs with Video UniFormer"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.09552","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":"sha256:47eae53129e292331abcad2588e7adbe8834ec332de85b0a05ec4fd78f52ae45","target":"record","created_at":"2026-07-05T05:17:03Z","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":"c463fa6beb6aae7c532105b372d8b9e030f24beb13b3be67d029a98cb04cf379","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-11-17T14:17:40Z","title_canon_sha256":"0f17f8051f1d028cbafdd51e48bc2c1cb6f97b880c418fc28802fca95e3ce9e5"},"schema_version":"1.0","source":{"id":"2211.09552","kind":"arxiv","version":1}},"canonical_sha256":"d09cc7730994edcaad4ff450d588508463d36a700a7c90c6542629671c98be6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d09cc7730994edcaad4ff450d588508463d36a700a7c90c6542629671c98be6c","first_computed_at":"2026-07-05T05:17:03.565914Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:17:03.565914Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mTYM6M622sf8/Fdj2vt8mWJEq6TOEQShg8CQGRGOT5VYCoYruCjZ4ZBNZxm7qcsdjTSuDRaAVJ17g4ZzIsWgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:17:03.566250Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.09552","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:47eae53129e292331abcad2588e7adbe8834ec332de85b0a05ec4fd78f52ae45","sha256:f88a11acdbfad84ead1305bb638d94b16122d1e31b73a5be29b7a5833f844115"],"state_sha256":"ebe848d747063a3f3bdea92310b8f18b8302228ff364a35bcc8f7df8a609d7b6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VU/QU0rjAayv95wIHQjcj+Whyh4ry9fJz9zi8xeO2uaSyXaAa5MzLNCE3bChB2Jgw+h1eF6CybgxdBn9VFcfAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:38:32.577713Z","bundle_sha256":"22bc1bb6ea573649b3ee0bad22f7c03494fda21edcb4cc9466ed40393c896644"}}