{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TWW2CTPYS3I7NGGZKOG7VIG5AU","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":"6c051686e081f190f5d2814ef80740831ac932cadcd3bc6923a2b61967d45b11","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-26T04:34:33Z","title_canon_sha256":"76d6fa09b6b569e4fddaca64eb53a971d5aadc2f66614e30995fce9062b47415"},"schema_version":"1.0","source":{"id":"2108.11575","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.11575","created_at":"2026-07-05T03:27:04Z"},{"alias_kind":"arxiv_version","alias_value":"2108.11575v5","created_at":"2026-07-05T03:27:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11575","created_at":"2026-07-05T03:27:04Z"},{"alias_kind":"pith_short_12","alias_value":"TWW2CTPYS3I7","created_at":"2026-07-05T03:27:04Z"},{"alias_kind":"pith_short_16","alias_value":"TWW2CTPYS3I7NGGZ","created_at":"2026-07-05T03:27:04Z"},{"alias_kind":"pith_short_8","alias_value":"TWW2CTPY","created_at":"2026-07-05T03:27:04Z"}],"graph_snapshots":[{"event_id":"sha256:c34d430cdefffbf59f7fc3e5325263d3f2ba2c59f08e497ae1a16df75c23c22e","target":"graph","created_at":"2026-07-05T03:27:04Z","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/2108.11575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spatio-temporal representational learning has been widely adopted in various fields such as action recognition, video object segmentation, and action anticipation. Previous spatio-temporal representational learning approaches primarily employ ConvNets or sequential models,e.g., LSTM, to learn the intra-frame and inter-frame features. Recently, Transformer models have successfully dominated the study of natural language processing (NLP), image classification, etc. However, the pure-Transformer based spatio-temporal learning can be prohibitively costly on memory and computation to extract fine-g","authors_text":"Ji Liu, Sen Yang, Tingxun Lv, Wentao Zhu, Xuefan Zha","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-26T04:34:33Z","title":"Shifted Chunk Transformer for Spatio-Temporal Representational Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11575","kind":"arxiv","version":5},"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":"sha256:16e8955ce06c2e37e6d282b57974c1c5a5ed4ca195660c2f0bf5a3e48875ca75","target":"record","created_at":"2026-07-05T03:27:04Z","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":"6c051686e081f190f5d2814ef80740831ac932cadcd3bc6923a2b61967d45b11","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2021-08-26T04:34:33Z","title_canon_sha256":"76d6fa09b6b569e4fddaca64eb53a971d5aadc2f66614e30995fce9062b47415"},"schema_version":"1.0","source":{"id":"2108.11575","kind":"arxiv","version":5}},"canonical_sha256":"9dada14df896d1f698d9538dfaa0dd05049045f564f3904057d1a5814370a984","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9dada14df896d1f698d9538dfaa0dd05049045f564f3904057d1a5814370a984","first_computed_at":"2026-07-05T03:27:04.530650Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:27:04.530650Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DQfKLkXy6Vnj28h0er5Rcz7/axiPGDPK31qmTjY1yqFWFu0WNVoh5MN+fMtNEWYowJEGn4m/z8TfVUU0MihVAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:27:04.531014Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.11575","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16e8955ce06c2e37e6d282b57974c1c5a5ed4ca195660c2f0bf5a3e48875ca75","sha256:c34d430cdefffbf59f7fc3e5325263d3f2ba2c59f08e497ae1a16df75c23c22e"],"state_sha256":"72e639978f7b9a14d06594f80fd1bcbd01ca131b1d3c05d9683b64ab7e32cc03"}