{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MJQ6HW4D5YAFKEXKODHY3VRNGV","short_pith_number":"pith:MJQ6HW4D","canonical_record":{"source":{"id":"2110.06178","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T17:25:07Z","cross_cats_sorted":[],"title_canon_sha256":"2ea62ad37f6232ae8b5903353c506cadd1c2d6b89628e3e5759ea96e7b5bffe6","abstract_canon_sha256":"70535e81141d4309083386c4f41659eb9cdd57c85323769ca795cc93a343c7ba"},"schema_version":"1.0"},"canonical_sha256":"6261e3db83ee005512ea70cf8dd62d357daf60779e2431d20a7ef6630e7cde31","source":{"kind":"arxiv","id":"2110.06178","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06178","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06178v4","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06178","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"MJQ6HW4D5YAF","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"MJQ6HW4D5YAFKEXK","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"MJQ6HW4D","created_at":"2026-07-05T04:06:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MJQ6HW4D5YAFKEXKODHY3VRNGV","target":"record","payload":{"canonical_record":{"source":{"id":"2110.06178","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T17:25:07Z","cross_cats_sorted":[],"title_canon_sha256":"2ea62ad37f6232ae8b5903353c506cadd1c2d6b89628e3e5759ea96e7b5bffe6","abstract_canon_sha256":"70535e81141d4309083386c4f41659eb9cdd57c85323769ca795cc93a343c7ba"},"schema_version":"1.0"},"canonical_sha256":"6261e3db83ee005512ea70cf8dd62d357daf60779e2431d20a7ef6630e7cde31","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:00.033607Z","signature_b64":"WkMzNntFZ0FoqTVIon7oA+BcNK/gQO2JgMaRS4xHhvgwbC/pDc2+bdDU1cZqcdk7OH51pj+pOUwlKxPdsOnTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6261e3db83ee005512ea70cf8dd62d357daf60779e2431d20a7ef6630e7cde31","last_reissued_at":"2026-07-05T04:06:00.033225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:00.033225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.06178","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WKqZerz9vyC1Lv8RmxlmYy2hbRbt755OnSCj2QhTMn0ZFMv94nLMPpwpXefHJlZwJ161sc2iD1xFT6FqNHRoDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:19:24.790443Z"},"content_sha256":"649f838bbfb6d99d61c38cc58343b158ea6fabf6d63119f0b1893e63c6af4302","schema_version":"1.0","event_id":"sha256:649f838bbfb6d99d61c38cc58343b158ea6fabf6d63119f0b1893e63c6af4302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MJQ6HW4D5YAFKEXKODHY3VRNGV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TAda! Temporally-Adaptive Convolutions for Video Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Liang Pan, Marcelo H. Ang Jr, Mingqian Tang, Shiwei Zhang, Zhiwu Qing, Ziwei Liu, Ziyuan Huang","submitted_at":"2021-10-12T17:25:07Z","abstract_excerpt":"Spatial convolutions are widely used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive Convolutions (TAdaConv) for video understanding, which shows that adaptive weight calibration along the temporal dimension is an efficient way to facilitate modelling complex temporal dynamics in videos. Specifically, TAdaConv empowers the spatial convolutions with temporal modelling abilities by calibrating the convolution weights for each frame according to its local a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06178","kind":"arxiv","version":4},"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/2110.06178/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":"2026-07-05T04:06:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ytz1eCYlJWIcbl9zBAjOoD0HDdY640GN+ddhiUl8iB5ClWK32AYpZ7VbskjnQ6YZYCvIoIyiCCMxK1OU9IGqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:19:24.790835Z"},"content_sha256":"fe8b06692d869ad1be87b55b01865b5d977fee33cd23e1647f4b75265b3ceb14","schema_version":"1.0","event_id":"sha256:fe8b06692d869ad1be87b55b01865b5d977fee33cd23e1647f4b75265b3ceb14"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MJQ6HW4D5YAFKEXKODHY3VRNGV/bundle.json","state_url":"https://pith.science/pith/MJQ6HW4D5YAFKEXKODHY3VRNGV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MJQ6HW4D5YAFKEXKODHY3VRNGV/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":"2026-08-07T06:19:24Z","links":{"resolver":"https://pith.science/pith/MJQ6HW4D5YAFKEXKODHY3VRNGV","bundle":"https://pith.science/pith/MJQ6HW4D5YAFKEXKODHY3VRNGV/bundle.json","state":"https://pith.science/pith/MJQ6HW4D5YAFKEXKODHY3VRNGV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MJQ6HW4D5YAFKEXKODHY3VRNGV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MJQ6HW4D5YAFKEXKODHY3VRNGV","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":"70535e81141d4309083386c4f41659eb9cdd57c85323769ca795cc93a343c7ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T17:25:07Z","title_canon_sha256":"2ea62ad37f6232ae8b5903353c506cadd1c2d6b89628e3e5759ea96e7b5bffe6"},"schema_version":"1.0","source":{"id":"2110.06178","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.06178","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"arxiv_version","alias_value":"2110.06178v4","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06178","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_12","alias_value":"MJQ6HW4D5YAF","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_16","alias_value":"MJQ6HW4D5YAFKEXK","created_at":"2026-07-05T04:06:00Z"},{"alias_kind":"pith_short_8","alias_value":"MJQ6HW4D","created_at":"2026-07-05T04:06:00Z"}],"graph_snapshots":[{"event_id":"sha256:fe8b06692d869ad1be87b55b01865b5d977fee33cd23e1647f4b75265b3ceb14","target":"graph","created_at":"2026-07-05T04:06:00Z","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/2110.06178/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatial convolutions are widely used in numerous deep video models. It fundamentally assumes spatio-temporal invariance, i.e., using shared weights for every location in different frames. This work presents Temporally-Adaptive Convolutions (TAdaConv) for video understanding, which shows that adaptive weight calibration along the temporal dimension is an efficient way to facilitate modelling complex temporal dynamics in videos. Specifically, TAdaConv empowers the spatial convolutions with temporal modelling abilities by calibrating the convolution weights for each frame according to its local a","authors_text":"Liang Pan, Marcelo H. Ang Jr, Mingqian Tang, Shiwei Zhang, Zhiwu Qing, Ziwei Liu, Ziyuan Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T17:25:07Z","title":"TAda! Temporally-Adaptive Convolutions for Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06178","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":"sha256:649f838bbfb6d99d61c38cc58343b158ea6fabf6d63119f0b1893e63c6af4302","target":"record","created_at":"2026-07-05T04:06:00Z","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":"70535e81141d4309083386c4f41659eb9cdd57c85323769ca795cc93a343c7ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-10-12T17:25:07Z","title_canon_sha256":"2ea62ad37f6232ae8b5903353c506cadd1c2d6b89628e3e5759ea96e7b5bffe6"},"schema_version":"1.0","source":{"id":"2110.06178","kind":"arxiv","version":4}},"canonical_sha256":"6261e3db83ee005512ea70cf8dd62d357daf60779e2431d20a7ef6630e7cde31","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6261e3db83ee005512ea70cf8dd62d357daf60779e2431d20a7ef6630e7cde31","first_computed_at":"2026-07-05T04:06:00.033225Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:06:00.033225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WkMzNntFZ0FoqTVIon7oA+BcNK/gQO2JgMaRS4xHhvgwbC/pDc2+bdDU1cZqcdk7OH51pj+pOUwlKxPdsOnTBg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:06:00.033607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.06178","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:649f838bbfb6d99d61c38cc58343b158ea6fabf6d63119f0b1893e63c6af4302","sha256:fe8b06692d869ad1be87b55b01865b5d977fee33cd23e1647f4b75265b3ceb14"],"state_sha256":"727ffbcf4b41b5e49ed37d7996b40fc73510a8031fbbfa86b95aa773fa66c1be"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q8Bvp47ItBwmIYjXxjMYBDSoFnKfge5QiSiooXEMVzcB22d0qub0E7vQm0kZR/GsysOTWwLS+26LVQzZk1JRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:19:24.793615Z","bundle_sha256":"b2de3f9bfdafb48cbe1897d47d136d9e97ada97f3bb3262df5740b7018712600"}}