{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:XHV2KPGI3QX5PBCXTBJMY5TSFI","short_pith_number":"pith:XHV2KPGI","canonical_record":{"source":{"id":"2001.06769","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-19T04:21:51Z","cross_cats_sorted":[],"title_canon_sha256":"03a2589126fd549b7cd01befff062c8484feba59e1c3485172b69e459457ffb8","abstract_canon_sha256":"47ea0c5a2e37b81dfc769c9226658656e9a5ad6b2572b7dc7ca716458fdb7e59"},"schema_version":"1.0"},"canonical_sha256":"b9eba53cc8dc2fd784579852cc76722a1a5c9632b61b75e821b5c57064a000aa","source":{"kind":"arxiv","id":"2001.06769","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.06769","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"arxiv_version","alias_value":"2001.06769v3","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.06769","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"pith_short_12","alias_value":"XHV2KPGI3QX5","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"pith_short_16","alias_value":"XHV2KPGI3QX5PBCX","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"pith_short_8","alias_value":"XHV2KPGI","created_at":"2026-07-05T00:35:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:XHV2KPGI3QX5PBCXTBJMY5TSFI","target":"record","payload":{"canonical_record":{"source":{"id":"2001.06769","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-19T04:21:51Z","cross_cats_sorted":[],"title_canon_sha256":"03a2589126fd549b7cd01befff062c8484feba59e1c3485172b69e459457ffb8","abstract_canon_sha256":"47ea0c5a2e37b81dfc769c9226658656e9a5ad6b2572b7dc7ca716458fdb7e59"},"schema_version":"1.0"},"canonical_sha256":"b9eba53cc8dc2fd784579852cc76722a1a5c9632b61b75e821b5c57064a000aa","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:56.562901Z","signature_b64":"6W7Rg1fXbfjT8rsQ9hQ6M/7XSCNW65OOl/+t1op/2B5M/reksgezn5fANEVpwqTWXPiOx4/OPpWISoLd9LA1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9eba53cc8dc2fd784579852cc76722a1a5c9632b61b75e821b5c57064a000aa","last_reissued_at":"2026-07-05T00:35:56.562343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:56.562343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2001.06769","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:35:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NA+swYHzaZAH5cC0wKOh670xSrJujtOFmytk8U+DFlQBlP+D1K2Tp8Y3vUJUMyDQJmLleEcExOgFlFGgjae6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:02:13.228538Z"},"content_sha256":"f37c7475770c2c3397018f9106d571532ea1fe8bd973442ef3a246b4feafaba9","schema_version":"1.0","event_id":"sha256:f37c7475770c2c3397018f9106d571532ea1fe8bd973442ef3a246b4feafaba9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:XHV2KPGI3QX5PBCXTBJMY5TSFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kaiyu Shan, Tingting Liang, Yangyan Li, Ying Chen, Yongtao Wang, Zhi Tang, Zhuoying Wang","submitted_at":"2020-01-19T04:21:51Z","abstract_excerpt":"To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone. However, they all exploit 1D temporal convolution of fixed kernel size (i.e., 3) in the network building block, thus have suboptimal temporal modeling capability to handle both long-term and short-term actions. To address this problem, we first investigate the impacts of different kernel sizes for the 1D temporal convolutional filters. Then, we propose a simple yet efficient operation called Mixed Temporal Convoluti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.06769","kind":"arxiv","version":3},"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/2001.06769/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":"2026-07-05T00:35:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kAbxjJxGFK4CUvCb7oPbglMHKxEDw47qzh2VTsl9tNb8flf3nyVuS6uxv2yNsKR51jCtxBP+iVWDL9MQadfZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:02:13.229380Z"},"content_sha256":"297c54394a0955e96fa5f9210304bc0379ccd8e1111bc3743958b83cdb869892","schema_version":"1.0","event_id":"sha256:297c54394a0955e96fa5f9210304bc0379ccd8e1111bc3743958b83cdb869892"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XHV2KPGI3QX5PBCXTBJMY5TSFI/bundle.json","state_url":"https://pith.science/pith/XHV2KPGI3QX5PBCXTBJMY5TSFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XHV2KPGI3QX5PBCXTBJMY5TSFI/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":"2026-08-18T13:02:13Z","links":{"resolver":"https://pith.science/pith/XHV2KPGI3QX5PBCXTBJMY5TSFI","bundle":"https://pith.science/pith/XHV2KPGI3QX5PBCXTBJMY5TSFI/bundle.json","state":"https://pith.science/pith/XHV2KPGI3QX5PBCXTBJMY5TSFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XHV2KPGI3QX5PBCXTBJMY5TSFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:XHV2KPGI3QX5PBCXTBJMY5TSFI","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":"47ea0c5a2e37b81dfc769c9226658656e9a5ad6b2572b7dc7ca716458fdb7e59","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-19T04:21:51Z","title_canon_sha256":"03a2589126fd549b7cd01befff062c8484feba59e1c3485172b69e459457ffb8"},"schema_version":"1.0","source":{"id":"2001.06769","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2001.06769","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"arxiv_version","alias_value":"2001.06769v3","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.06769","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"pith_short_12","alias_value":"XHV2KPGI3QX5","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"pith_short_16","alias_value":"XHV2KPGI3QX5PBCX","created_at":"2026-07-05T00:35:56Z"},{"alias_kind":"pith_short_8","alias_value":"XHV2KPGI","created_at":"2026-07-05T00:35:56Z"}],"graph_snapshots":[{"event_id":"sha256:297c54394a0955e96fa5f9210304bc0379ccd8e1111bc3743958b83cdb869892","target":"graph","created_at":"2026-07-05T00:35:56Z","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/2001.06769/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"To efficiently extract spatiotemporal features of video for action recognition, most state-of-the-art methods integrate 1D temporal convolution into a conventional 2D CNN backbone. However, they all exploit 1D temporal convolution of fixed kernel size (i.e., 3) in the network building block, thus have suboptimal temporal modeling capability to handle both long-term and short-term actions. To address this problem, we first investigate the impacts of different kernel sizes for the 1D temporal convolutional filters. Then, we propose a simple yet efficient operation called Mixed Temporal Convoluti","authors_text":"Kaiyu Shan, Tingting Liang, Yangyan Li, Ying Chen, Yongtao Wang, Zhi Tang, Zhuoying Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-19T04:21:51Z","title":"MixTConv: Mixed Temporal Convolutional Kernels for Efficient Action Recogntion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.06769","kind":"arxiv","version":3},"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:f37c7475770c2c3397018f9106d571532ea1fe8bd973442ef3a246b4feafaba9","target":"record","created_at":"2026-07-05T00:35:56Z","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":"47ea0c5a2e37b81dfc769c9226658656e9a5ad6b2572b7dc7ca716458fdb7e59","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-01-19T04:21:51Z","title_canon_sha256":"03a2589126fd549b7cd01befff062c8484feba59e1c3485172b69e459457ffb8"},"schema_version":"1.0","source":{"id":"2001.06769","kind":"arxiv","version":3}},"canonical_sha256":"b9eba53cc8dc2fd784579852cc76722a1a5c9632b61b75e821b5c57064a000aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9eba53cc8dc2fd784579852cc76722a1a5c9632b61b75e821b5c57064a000aa","first_computed_at":"2026-07-05T00:35:56.562343Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:35:56.562343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6W7Rg1fXbfjT8rsQ9hQ6M/7XSCNW65OOl/+t1op/2B5M/reksgezn5fANEVpwqTWXPiOx4/OPpWISoLd9LA1BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:35:56.562901Z","signed_message":"canonical_sha256_bytes"},"source_id":"2001.06769","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f37c7475770c2c3397018f9106d571532ea1fe8bd973442ef3a246b4feafaba9","sha256:297c54394a0955e96fa5f9210304bc0379ccd8e1111bc3743958b83cdb869892"],"state_sha256":"baf9ebbadc910408d55a9dc6bf394ca19129e818cc2999e2eaee0515cde475b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vNYghSTWrWPpV5QkaFFeZqJM5j16J5G0uxl/zYnpHHYy0kkPHs8DL6NikkkTlTwL/BbCX9ULwLztl+XsgGLMCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T13:02:13.237731Z","bundle_sha256":"0a6a36e91bc1b25aa2f94f8d6716f964231a7f830ef7bdd2aed43e4404c3e8e6"}}