{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WZGOP47YBTQD3ADH6JR6APIBOE","short_pith_number":"pith:WZGOP47Y","canonical_record":{"source":{"id":"2410.23782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T09:55:32Z","cross_cats_sorted":[],"title_canon_sha256":"30d29143c8343f11e952e852d61ff433e1f7381d7f78ff2d0b130b469384eaca","abstract_canon_sha256":"f0391b5888aaeaee6e6c02c6ca16c752af5e4323e750c3f96f0f488d7ef93fbc"},"schema_version":"1.0"},"canonical_sha256":"b64ce7f3f80ce03d8067f263e03d01711e1374422d9e8e53926b8a1abab9a6fc","source":{"kind":"arxiv","id":"2410.23782","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23782","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23782v1","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23782","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"WZGOP47YBTQD","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"WZGOP47YBTQD3ADH","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"WZGOP47Y","created_at":"2026-07-05T09:29:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WZGOP47YBTQD3ADH6JR6APIBOE","target":"record","payload":{"canonical_record":{"source":{"id":"2410.23782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T09:55:32Z","cross_cats_sorted":[],"title_canon_sha256":"30d29143c8343f11e952e852d61ff433e1f7381d7f78ff2d0b130b469384eaca","abstract_canon_sha256":"f0391b5888aaeaee6e6c02c6ca16c752af5e4323e750c3f96f0f488d7ef93fbc"},"schema_version":"1.0"},"canonical_sha256":"b64ce7f3f80ce03d8067f263e03d01711e1374422d9e8e53926b8a1abab9a6fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:05.121078Z","signature_b64":"wxPjev8QzCfNimEw2kAjLTVSpLyNMV4I4cMlfjjXT/5kpcbP7D6yN3IwJx544J8Oljqx0r/isWgvjCZbJ/jYCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b64ce7f3f80ce03d8067f263e03d01711e1374422d9e8e53926b8a1abab9a6fc","last_reissued_at":"2026-07-05T09:29:05.120671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:05.120671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.23782","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":"2026-07-05T09:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CVLxqaTNvXZ6eC/ulsVJofqIXUo1885YoUNhWr5Agpo7/rHme4ylpog6WVPFHgt68I39/rZh16MhHsgqlpVtBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:07:19.561166Z"},"content_sha256":"b5cdcab8c3f563990e40fb8a92fef8ebd191132bbd7933ee6b324c447c605e17","schema_version":"1.0","event_id":"sha256:b5cdcab8c3f563990e40fb8a92fef8ebd191132bbd7933ee6b324c447c605e17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WZGOP47YBTQD3ADH6JR6APIBOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video Token Merging for Long-form Video Understanding","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Fan, Jue Wang, Seon-Ho Lee, Xinyu Li, Zhikang Zhang","submitted_at":"2024-10-31T09:55:32Z","abstract_excerpt":"As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result in information loss, token merging shows promising results when used in collaboration with transformers. However, the application of token merging for long-form video processing is not trivial. We begin with the premise that token merging should not rely solely on the similarity of video tokens; the saliency of tokens should also be considered. To address thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23782","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/2410.23782/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":"2026-07-05T09:29:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ks3VJchJb+TZ4DZ+r2k9cbnjSoKdlTuf9L1lxNpDtwZhtYRWimPHbmsFoVxola1k7952UvX7zgZq4YJXbJrrDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T20:07:19.561654Z"},"content_sha256":"dda877daa56ea2aff7b55e6ab512dc93210c86087671ca4f25655284c365b2e3","schema_version":"1.0","event_id":"sha256:dda877daa56ea2aff7b55e6ab512dc93210c86087671ca4f25655284c365b2e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZGOP47YBTQD3ADH6JR6APIBOE/bundle.json","state_url":"https://pith.science/pith/WZGOP47YBTQD3ADH6JR6APIBOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZGOP47YBTQD3ADH6JR6APIBOE/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":"2026-08-10T20:07:19Z","links":{"resolver":"https://pith.science/pith/WZGOP47YBTQD3ADH6JR6APIBOE","bundle":"https://pith.science/pith/WZGOP47YBTQD3ADH6JR6APIBOE/bundle.json","state":"https://pith.science/pith/WZGOP47YBTQD3ADH6JR6APIBOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZGOP47YBTQD3ADH6JR6APIBOE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WZGOP47YBTQD3ADH6JR6APIBOE","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":"f0391b5888aaeaee6e6c02c6ca16c752af5e4323e750c3f96f0f488d7ef93fbc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T09:55:32Z","title_canon_sha256":"30d29143c8343f11e952e852d61ff433e1f7381d7f78ff2d0b130b469384eaca"},"schema_version":"1.0","source":{"id":"2410.23782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.23782","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"arxiv_version","alias_value":"2410.23782v1","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.23782","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"pith_short_12","alias_value":"WZGOP47YBTQD","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"pith_short_16","alias_value":"WZGOP47YBTQD3ADH","created_at":"2026-07-05T09:29:05Z"},{"alias_kind":"pith_short_8","alias_value":"WZGOP47Y","created_at":"2026-07-05T09:29:05Z"}],"graph_snapshots":[{"event_id":"sha256:dda877daa56ea2aff7b55e6ab512dc93210c86087671ca4f25655284c365b2e3","target":"graph","created_at":"2026-07-05T09:29:05Z","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/2410.23782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As the scale of data and models for video understanding rapidly expand, handling long-form video input in transformer-based models presents a practical challenge. Rather than resorting to input sampling or token dropping, which may result in information loss, token merging shows promising results when used in collaboration with transformers. However, the application of token merging for long-form video processing is not trivial. We begin with the premise that token merging should not rely solely on the similarity of video tokens; the saliency of tokens should also be considered. To address thi","authors_text":"David Fan, Jue Wang, Seon-Ho Lee, Xinyu Li, Zhikang Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T09:55:32Z","title":"Video Token Merging for Long-form Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.23782","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:b5cdcab8c3f563990e40fb8a92fef8ebd191132bbd7933ee6b324c447c605e17","target":"record","created_at":"2026-07-05T09:29:05Z","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":"f0391b5888aaeaee6e6c02c6ca16c752af5e4323e750c3f96f0f488d7ef93fbc","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-31T09:55:32Z","title_canon_sha256":"30d29143c8343f11e952e852d61ff433e1f7381d7f78ff2d0b130b469384eaca"},"schema_version":"1.0","source":{"id":"2410.23782","kind":"arxiv","version":1}},"canonical_sha256":"b64ce7f3f80ce03d8067f263e03d01711e1374422d9e8e53926b8a1abab9a6fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b64ce7f3f80ce03d8067f263e03d01711e1374422d9e8e53926b8a1abab9a6fc","first_computed_at":"2026-07-05T09:29:05.120671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:05.120671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wxPjev8QzCfNimEw2kAjLTVSpLyNMV4I4cMlfjjXT/5kpcbP7D6yN3IwJx544J8Oljqx0r/isWgvjCZbJ/jYCw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:05.121078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.23782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5cdcab8c3f563990e40fb8a92fef8ebd191132bbd7933ee6b324c447c605e17","sha256:dda877daa56ea2aff7b55e6ab512dc93210c86087671ca4f25655284c365b2e3"],"state_sha256":"90d2f32af061bffafbc5958a774c9b9c8a5d445cb6d79fb8bef8c8b9b6a2829f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yi4k2BJ+0/VaVQMaW9ZclGNgY6/a5mAkuFyrAwsk3JdKYfwLu5+icZbRqZDrCmrqk7KPhg7wRzv53XfAwWpBCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T20:07:19.566221Z","bundle_sha256":"ce84eab667b4ee527fcf272d9b215a103567353da21fc4098a4b2b463a8fbfbc"}}