{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:RUCRMX2RMHQJH5BH2JRUNDXSAY","short_pith_number":"pith:RUCRMX2R","canonical_record":{"source":{"id":"2201.04288","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T03:33:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b65b9f8f195ff7690742f1e5cedb1dfbe78b61d14ec56736d93f7bd28c9e8be","abstract_canon_sha256":"e10f7c2609f172f6c3011c9da395f36cb59f5f40b945014b55583137669bc3a4"},"schema_version":"1.0"},"canonical_sha256":"8d05165f5161e093f427d263468ef2063db2b364de28dfd03029e452cc8ab5f5","source":{"kind":"arxiv","id":"2201.04288","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04288","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04288v4","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04288","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"pith_short_12","alias_value":"RUCRMX2RMHQJ","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"RUCRMX2RMHQJH5BH","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"RUCRMX2R","created_at":"2026-07-05T04:27:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:RUCRMX2RMHQJH5BH2JRUNDXSAY","target":"record","payload":{"canonical_record":{"source":{"id":"2201.04288","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T03:33:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"4b65b9f8f195ff7690742f1e5cedb1dfbe78b61d14ec56736d93f7bd28c9e8be","abstract_canon_sha256":"e10f7c2609f172f6c3011c9da395f36cb59f5f40b945014b55583137669bc3a4"},"schema_version":"1.0"},"canonical_sha256":"8d05165f5161e093f427d263468ef2063db2b364de28dfd03029e452cc8ab5f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:27:30.084528Z","signature_b64":"fg8xGVNRwCTZgBZFJjAJp/HZJAD8uQt8RL2P5DcJNW6VIh8nIhevVLpvw6XqM3+CeOXxqD+3zO0Tm2Ycfx7tAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d05165f5161e093f427d263468ef2063db2b364de28dfd03029e452cc8ab5f5","last_reissued_at":"2026-07-05T04:27:30.084022Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:27:30.084022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.04288","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":"2026-07-05T04:27:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zVcgnYD2E3J/8SS0CLFvafI3+scH9hyylvmOx0BT1rHxpCN0UmWbRxtEwEhBllQg99tKzCNDLbFoa+SfWlF3AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:50:27.134101Z"},"content_sha256":"9b4c0fe0eea8ba4bca092facfb311cefcfc3593db1a2acd0ed30db0e1cd39621","schema_version":"1.0","event_id":"sha256:9b4c0fe0eea8ba4bca092facfb311cefcfc3593db1a2acd0ed30db0e1cd39621"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:RUCRMX2RMHQJH5BH2JRUNDXSAY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multiview Transformers for Video Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Anurag Arnab, Chen Sun, Cordelia Schmid, Mi Zhang, Shen Yan, Xuehan Xiong, Zhichao Lu","submitted_at":"2022-01-12T03:33:57Z","abstract_excerpt":"Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art, they have not explicitly modelled different spatiotemporal resolutions. To this end, we present Multiview Transformers for Video Recognition (MTV). Our model consists of separate encoders to represent different views of the input video with lateral connections to fuse information across views. We present thorough ablation studies of our model and show that MT"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04288","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/2201.04288/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":"2026-07-05T04:27:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Xig6YgbhpWlVHz9AAk8k1kiPEViS0AybyAtcdV13XZaSAHicXH/1YlTao+Ce6sZh/a0aT45io8BpxBrkzzUEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T01:50:27.134786Z"},"content_sha256":"c1ed9b88d7a372b944fa97349132cea126d51cf83e888a942c99fc1fb17e73bb","schema_version":"1.0","event_id":"sha256:c1ed9b88d7a372b944fa97349132cea126d51cf83e888a942c99fc1fb17e73bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RUCRMX2RMHQJH5BH2JRUNDXSAY/bundle.json","state_url":"https://pith.science/pith/RUCRMX2RMHQJH5BH2JRUNDXSAY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RUCRMX2RMHQJH5BH2JRUNDXSAY/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":"2026-08-11T01:50:27Z","links":{"resolver":"https://pith.science/pith/RUCRMX2RMHQJH5BH2JRUNDXSAY","bundle":"https://pith.science/pith/RUCRMX2RMHQJH5BH2JRUNDXSAY/bundle.json","state":"https://pith.science/pith/RUCRMX2RMHQJH5BH2JRUNDXSAY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RUCRMX2RMHQJH5BH2JRUNDXSAY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:RUCRMX2RMHQJH5BH2JRUNDXSAY","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":"e10f7c2609f172f6c3011c9da395f36cb59f5f40b945014b55583137669bc3a4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T03:33:57Z","title_canon_sha256":"4b65b9f8f195ff7690742f1e5cedb1dfbe78b61d14ec56736d93f7bd28c9e8be"},"schema_version":"1.0","source":{"id":"2201.04288","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.04288","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"arxiv_version","alias_value":"2201.04288v4","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.04288","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"pith_short_12","alias_value":"RUCRMX2RMHQJ","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"pith_short_16","alias_value":"RUCRMX2RMHQJH5BH","created_at":"2026-07-05T04:27:30Z"},{"alias_kind":"pith_short_8","alias_value":"RUCRMX2R","created_at":"2026-07-05T04:27:30Z"}],"graph_snapshots":[{"event_id":"sha256:c1ed9b88d7a372b944fa97349132cea126d51cf83e888a942c99fc1fb17e73bb","target":"graph","created_at":"2026-07-05T04:27:30Z","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/2201.04288/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video understanding requires reasoning at multiple spatiotemporal resolutions -- from short fine-grained motions to events taking place over longer durations. Although transformer architectures have recently advanced the state-of-the-art, they have not explicitly modelled different spatiotemporal resolutions. To this end, we present Multiview Transformers for Video Recognition (MTV). Our model consists of separate encoders to represent different views of the input video with lateral connections to fuse information across views. We present thorough ablation studies of our model and show that MT","authors_text":"Anurag Arnab, Chen Sun, Cordelia Schmid, Mi Zhang, Shen Yan, Xuehan Xiong, Zhichao Lu","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T03:33:57Z","title":"Multiview Transformers for Video Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.04288","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":"sha256:9b4c0fe0eea8ba4bca092facfb311cefcfc3593db1a2acd0ed30db0e1cd39621","target":"record","created_at":"2026-07-05T04:27:30Z","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":"e10f7c2609f172f6c3011c9da395f36cb59f5f40b945014b55583137669bc3a4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-12T03:33:57Z","title_canon_sha256":"4b65b9f8f195ff7690742f1e5cedb1dfbe78b61d14ec56736d93f7bd28c9e8be"},"schema_version":"1.0","source":{"id":"2201.04288","kind":"arxiv","version":4}},"canonical_sha256":"8d05165f5161e093f427d263468ef2063db2b364de28dfd03029e452cc8ab5f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d05165f5161e093f427d263468ef2063db2b364de28dfd03029e452cc8ab5f5","first_computed_at":"2026-07-05T04:27:30.084022Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:27:30.084022Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fg8xGVNRwCTZgBZFJjAJp/HZJAD8uQt8RL2P5DcJNW6VIh8nIhevVLpvw6XqM3+CeOXxqD+3zO0Tm2Ycfx7tAg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:27:30.084528Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.04288","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b4c0fe0eea8ba4bca092facfb311cefcfc3593db1a2acd0ed30db0e1cd39621","sha256:c1ed9b88d7a372b944fa97349132cea126d51cf83e888a942c99fc1fb17e73bb"],"state_sha256":"e70ea44bed4f12bd573046c6a61e662dffe90d16769833521b4b969767d6fe54"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8TPv1rJWq4zu1zMtNGeiNTqtcK/EjMWE+oWYg+52muiTEdc/ryVl51b4gFThp+XVoqxAUx+no2IGOWJbkgXOBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T01:50:27.138682Z","bundle_sha256":"57c6bcb12c4a81e7afb61c565a29c6f6cff9e3d82b06b8c586165e4edc99d5d2"}}