{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6UUTNNDMYYPNQOFDBZKJZCDW2N","short_pith_number":"pith:6UUTNNDM","canonical_record":{"source":{"id":"2311.10873","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T21:23:12Z","cross_cats_sorted":[],"title_canon_sha256":"66d06a82dfc551273a85263670c3c5eb417eab679c35bae0592d0a1b3b292ec2","abstract_canon_sha256":"c1a226a31d549559cd0013948d8508a9d540170832ebf4d21f226ab55b5a4afa"},"schema_version":"1.0"},"canonical_sha256":"f52936b46cc61ed838a30e549c8876d34120dd18cec32bb6cb014b1e23672096","source":{"kind":"arxiv","id":"2311.10873","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.10873","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"arxiv_version","alias_value":"2311.10873v2","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10873","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"pith_short_12","alias_value":"6UUTNNDMYYPN","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"pith_short_16","alias_value":"6UUTNNDMYYPNQOFD","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"pith_short_8","alias_value":"6UUTNNDM","created_at":"2026-07-05T11:24:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6UUTNNDMYYPNQOFDBZKJZCDW2N","target":"record","payload":{"canonical_record":{"source":{"id":"2311.10873","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T21:23:12Z","cross_cats_sorted":[],"title_canon_sha256":"66d06a82dfc551273a85263670c3c5eb417eab679c35bae0592d0a1b3b292ec2","abstract_canon_sha256":"c1a226a31d549559cd0013948d8508a9d540170832ebf4d21f226ab55b5a4afa"},"schema_version":"1.0"},"canonical_sha256":"f52936b46cc61ed838a30e549c8876d34120dd18cec32bb6cb014b1e23672096","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:59.947513Z","signature_b64":"/igZkOgjLmUbe9dTCERH2oVbYnrlUiYIjW5Bubk7Q8EoIvZ6XDfPnZyTSsFDbNuyLX+8AjSKtRrB/TwYoKWvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f52936b46cc61ed838a30e549c8876d34120dd18cec32bb6cb014b1e23672096","last_reissued_at":"2026-07-05T11:24:59.947159Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:59.947159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.10873","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:24:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GmQI+CrpUj+gF/++UKJm+aHyJxN5t3spClSttdLlAug4k3NPDOOnlY9HfZ72lv+8HwrsDlnpOnEv4To9vUQpBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:49:39.955549Z"},"content_sha256":"1a4ff6efc34cb06a7e74d23cd99f1dd916f0a71ab574871ce6e0694c08ce83c9","schema_version":"1.0","event_id":"sha256:1a4ff6efc34cb06a7e74d23cd99f1dd916f0a71ab574871ce6e0694c08ce83c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6UUTNNDMYYPNQOFDBZKJZCDW2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-entity Video Transformers for Fine-Grained Video Representation Learning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abhinav Shrivastava, Kai Sheng Tai, Keyur Muzumdar, Matthew Walmer, Rose Kanjirathinkal, Taipeng Tian","submitted_at":"2023-11-17T21:23:12Z","abstract_excerpt":"The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we advance the state-of-the-art for self-supervised models in this area by re-examining the design of transformer architectures for video representation learning. A key aspect of our approach is the improved sharing of scene information in the temporal pipeline by representing multiple salient entities per frame. Prior works use late-fusion architectures that reduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10873","kind":"arxiv","version":2},"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/2311.10873/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":"2026-07-05T11:24:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTgqIufT8r9jU3Jp7Fe+x+iXSwsi9RdBfAWXVNMbLy1ZwP3wj8vwcfEIhqXF69ZtOX3SPvkEjlhlY3hGVGKlBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:49:39.956549Z"},"content_sha256":"5399a69f5e383decf6cfa1d5280f7e37e5e7d9d6182bfa2604b2c9feb7c1a5f9","schema_version":"1.0","event_id":"sha256:5399a69f5e383decf6cfa1d5280f7e37e5e7d9d6182bfa2604b2c9feb7c1a5f9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/bundle.json","state_url":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/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":"2026-08-07T18:49:39Z","links":{"resolver":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N","bundle":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/bundle.json","state":"https://pith.science/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6UUTNNDMYYPNQOFDBZKJZCDW2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6UUTNNDMYYPNQOFDBZKJZCDW2N","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":"c1a226a31d549559cd0013948d8508a9d540170832ebf4d21f226ab55b5a4afa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T21:23:12Z","title_canon_sha256":"66d06a82dfc551273a85263670c3c5eb417eab679c35bae0592d0a1b3b292ec2"},"schema_version":"1.0","source":{"id":"2311.10873","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.10873","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"arxiv_version","alias_value":"2311.10873v2","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.10873","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"pith_short_12","alias_value":"6UUTNNDMYYPN","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"pith_short_16","alias_value":"6UUTNNDMYYPNQOFD","created_at":"2026-07-05T11:24:59Z"},{"alias_kind":"pith_short_8","alias_value":"6UUTNNDM","created_at":"2026-07-05T11:24:59Z"}],"graph_snapshots":[{"event_id":"sha256:5399a69f5e383decf6cfa1d5280f7e37e5e7d9d6182bfa2604b2c9feb7c1a5f9","target":"graph","created_at":"2026-07-05T11:24:59Z","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/2311.10873/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The area of temporally fine-grained video representation learning focuses on generating frame-by-frame representations for temporally dense tasks, such as fine-grained action phase classification and frame retrieval. In this work, we advance the state-of-the-art for self-supervised models in this area by re-examining the design of transformer architectures for video representation learning. A key aspect of our approach is the improved sharing of scene information in the temporal pipeline by representing multiple salient entities per frame. Prior works use late-fusion architectures that reduce ","authors_text":"Abhinav Shrivastava, Kai Sheng Tai, Keyur Muzumdar, Matthew Walmer, Rose Kanjirathinkal, Taipeng Tian","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T21:23:12Z","title":"Multi-entity Video Transformers for Fine-Grained Video Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.10873","kind":"arxiv","version":2},"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":"sha256:1a4ff6efc34cb06a7e74d23cd99f1dd916f0a71ab574871ce6e0694c08ce83c9","target":"record","created_at":"2026-07-05T11:24:59Z","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":"c1a226a31d549559cd0013948d8508a9d540170832ebf4d21f226ab55b5a4afa","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-17T21:23:12Z","title_canon_sha256":"66d06a82dfc551273a85263670c3c5eb417eab679c35bae0592d0a1b3b292ec2"},"schema_version":"1.0","source":{"id":"2311.10873","kind":"arxiv","version":2}},"canonical_sha256":"f52936b46cc61ed838a30e549c8876d34120dd18cec32bb6cb014b1e23672096","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f52936b46cc61ed838a30e549c8876d34120dd18cec32bb6cb014b1e23672096","first_computed_at":"2026-07-05T11:24:59.947159Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:59.947159Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/igZkOgjLmUbe9dTCERH2oVbYnrlUiYIjW5Bubk7Q8EoIvZ6XDfPnZyTSsFDbNuyLX+8AjSKtRrB/TwYoKWvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:59.947513Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.10873","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a4ff6efc34cb06a7e74d23cd99f1dd916f0a71ab574871ce6e0694c08ce83c9","sha256:5399a69f5e383decf6cfa1d5280f7e37e5e7d9d6182bfa2604b2c9feb7c1a5f9"],"state_sha256":"c65c83381fa83ac92a597e5f1e227f1c60ba25a8beaae94cf43de664b0c74572"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w3qltQ/Ax2mmWq7uxCOKpIPaOegcGlALyyQ/xuB+V1a0sM3XbcuFIzVYFjHQ1ghzHOCoTyG+UKHFKHnuzFPoDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:49:39.962802Z","bundle_sha256":"3281915d429be56b9516533ead224cbba118e5c5e167f1da8f10b8f177e75af6"}}