{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:SJEPP2PFVS7TUWEKEMZLS32TOH","short_pith_number":"pith:SJEPP2PF","canonical_record":{"source":{"id":"2011.02543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-04T21:20:08Z","cross_cats_sorted":[],"title_canon_sha256":"7a5cbc6a9cd6e6711ecff51b6a6f77f309c22b2d74a7690a3d6a66713bd2f9d4","abstract_canon_sha256":"81af8456b49a04d68737a908d3940e571fc9c18258181f4e9f816709aa3d0372"},"schema_version":"1.0"},"canonical_sha256":"9248f7e9e5acbf3a588a2332b96f5371c094f5a3d5fefd857055a2c55b7c9037","source":{"kind":"arxiv","id":"2011.02543","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02543","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02543v1","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02543","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"pith_short_12","alias_value":"SJEPP2PFVS7T","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"pith_short_16","alias_value":"SJEPP2PFVS7TUWEK","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"pith_short_8","alias_value":"SJEPP2PF","created_at":"2026-07-05T01:49:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:SJEPP2PFVS7TUWEKEMZLS32TOH","target":"record","payload":{"canonical_record":{"source":{"id":"2011.02543","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-04T21:20:08Z","cross_cats_sorted":[],"title_canon_sha256":"7a5cbc6a9cd6e6711ecff51b6a6f77f309c22b2d74a7690a3d6a66713bd2f9d4","abstract_canon_sha256":"81af8456b49a04d68737a908d3940e571fc9c18258181f4e9f816709aa3d0372"},"schema_version":"1.0"},"canonical_sha256":"9248f7e9e5acbf3a588a2332b96f5371c094f5a3d5fefd857055a2c55b7c9037","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:22.215534Z","signature_b64":"JqUKf67zvt7N2UikuwOZCpjWr3cEKqBpS6VR+xva3yISw4nVSAffbw0KVTofhfFAvXSypIIIytaWSgAjhtGqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9248f7e9e5acbf3a588a2332b96f5371c094f5a3d5fefd857055a2c55b7c9037","last_reissued_at":"2026-07-05T01:49:22.215122Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:22.215122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.02543","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":"2026-07-05T01:49:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eQYWrMF9oR92WcDwjjOA6HZ0TNErwD4niXEI0cWljNVOA6n6wrTcgSPou1cMpbvcuHdTqvetZFSE0pUdXC+rBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:58.397132Z"},"content_sha256":"0be5ba2784139994ae1a54a5c9e078b144f184e9762bba204d99f99089d3e02e","schema_version":"1.0","event_id":"sha256:0be5ba2784139994ae1a54a5c9e078b144f184e9762bba204d99f99089d3e02e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:SJEPP2PFVS7TUWEKEMZLS32TOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Mutual Modality Learning for Video Action Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aleksandr Petiushko, Maksim Dzabraev, Stepan Komkov","submitted_at":"2020-11-04T21:20:08Z","abstract_excerpt":"The construction of models for video action classification progresses rapidly. However, the performance of those models can still be easily improved by ensembling with the same models trained on different modalities (e.g. Optical flow). Unfortunately, it is computationally expensive to use several modalities during inference. Recent works examine the ways to integrate advantages of multi-modality into a single RGB-model. Yet, there is still a room for improvement. In this paper, we explore the various methods to embed the ensemble power into a single model. We show that proper initialization, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02543","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/2011.02543/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":"2026-07-05T01:49:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/YKnOYaByv4/iLZavno/2Z0MKerNMjGTm6sv4GPAvvTDEdMdYJL1uB3I4FTx8QxmyfsQOvdJp3pMDDDJsM9QAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:58:58.397519Z"},"content_sha256":"f586287e17b7b6cb69199a544b58606e2c0c9403b21133f42eebf00ecce0ee59","schema_version":"1.0","event_id":"sha256:f586287e17b7b6cb69199a544b58606e2c0c9403b21133f42eebf00ecce0ee59"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SJEPP2PFVS7TUWEKEMZLS32TOH/bundle.json","state_url":"https://pith.science/pith/SJEPP2PFVS7TUWEKEMZLS32TOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SJEPP2PFVS7TUWEKEMZLS32TOH/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":"2026-07-06T20:58:58Z","links":{"resolver":"https://pith.science/pith/SJEPP2PFVS7TUWEKEMZLS32TOH","bundle":"https://pith.science/pith/SJEPP2PFVS7TUWEKEMZLS32TOH/bundle.json","state":"https://pith.science/pith/SJEPP2PFVS7TUWEKEMZLS32TOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SJEPP2PFVS7TUWEKEMZLS32TOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:SJEPP2PFVS7TUWEKEMZLS32TOH","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":"81af8456b49a04d68737a908d3940e571fc9c18258181f4e9f816709aa3d0372","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-04T21:20:08Z","title_canon_sha256":"7a5cbc6a9cd6e6711ecff51b6a6f77f309c22b2d74a7690a3d6a66713bd2f9d4"},"schema_version":"1.0","source":{"id":"2011.02543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.02543","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"arxiv_version","alias_value":"2011.02543v1","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.02543","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"pith_short_12","alias_value":"SJEPP2PFVS7T","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"pith_short_16","alias_value":"SJEPP2PFVS7TUWEK","created_at":"2026-07-05T01:49:22Z"},{"alias_kind":"pith_short_8","alias_value":"SJEPP2PF","created_at":"2026-07-05T01:49:22Z"}],"graph_snapshots":[{"event_id":"sha256:f586287e17b7b6cb69199a544b58606e2c0c9403b21133f42eebf00ecce0ee59","target":"graph","created_at":"2026-07-05T01:49:22Z","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/2011.02543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The construction of models for video action classification progresses rapidly. However, the performance of those models can still be easily improved by ensembling with the same models trained on different modalities (e.g. Optical flow). Unfortunately, it is computationally expensive to use several modalities during inference. Recent works examine the ways to integrate advantages of multi-modality into a single RGB-model. Yet, there is still a room for improvement. In this paper, we explore the various methods to embed the ensemble power into a single model. We show that proper initialization, ","authors_text":"Aleksandr Petiushko, Maksim Dzabraev, Stepan Komkov","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-04T21:20:08Z","title":"Mutual Modality Learning for Video Action Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.02543","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":"sha256:0be5ba2784139994ae1a54a5c9e078b144f184e9762bba204d99f99089d3e02e","target":"record","created_at":"2026-07-05T01:49:22Z","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":"81af8456b49a04d68737a908d3940e571fc9c18258181f4e9f816709aa3d0372","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-11-04T21:20:08Z","title_canon_sha256":"7a5cbc6a9cd6e6711ecff51b6a6f77f309c22b2d74a7690a3d6a66713bd2f9d4"},"schema_version":"1.0","source":{"id":"2011.02543","kind":"arxiv","version":1}},"canonical_sha256":"9248f7e9e5acbf3a588a2332b96f5371c094f5a3d5fefd857055a2c55b7c9037","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9248f7e9e5acbf3a588a2332b96f5371c094f5a3d5fefd857055a2c55b7c9037","first_computed_at":"2026-07-05T01:49:22.215122Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:22.215122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JqUKf67zvt7N2UikuwOZCpjWr3cEKqBpS6VR+xva3yISw4nVSAffbw0KVTofhfFAvXSypIIIytaWSgAjhtGqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:22.215534Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.02543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0be5ba2784139994ae1a54a5c9e078b144f184e9762bba204d99f99089d3e02e","sha256:f586287e17b7b6cb69199a544b58606e2c0c9403b21133f42eebf00ecce0ee59"],"state_sha256":"9cbb57d0fc084dfbfe64df8030ec3e1a26682fe1aef25134086524803fde088a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DNnkWwS3L6IYmp8tYof1kOWSoDo51jeusX40Bh9vmF0ZsucJnIBQzUx1i0ILBbsso4eTOBu2fxwqXI3bGzy9CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:58:58.399518Z","bundle_sha256":"f62ab41fa0fc90c1d54b5431727c222439e82ea982308219ee8bcf7eab84712f"}}