{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:PXGUKE732KBZJ346GQZFSIM46T","short_pith_number":"pith:PXGUKE73","canonical_record":{"source":{"id":"2506.00993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T12:49:39Z","cross_cats_sorted":[],"title_canon_sha256":"4646cb638e85ed08c987905925385b5ce93dd4c874d428958f8e7b863856602c","abstract_canon_sha256":"e22ebf91c80b11910319f691169285051a101d97c82ea5239afa115e950d45a2"},"schema_version":"1.0"},"canonical_sha256":"7dcd4513fbd28394ef9e343259219cf4cf11e2bf4e0c010103a2d36707005ccf","source":{"kind":"arxiv","id":"2506.00993","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00993","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00993v1","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00993","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"PXGUKE732KBZ","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"PXGUKE732KBZJ346","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"PXGUKE73","created_at":"2026-07-05T11:13:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:PXGUKE732KBZJ346GQZFSIM46T","target":"record","payload":{"canonical_record":{"source":{"id":"2506.00993","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T12:49:39Z","cross_cats_sorted":[],"title_canon_sha256":"4646cb638e85ed08c987905925385b5ce93dd4c874d428958f8e7b863856602c","abstract_canon_sha256":"e22ebf91c80b11910319f691169285051a101d97c82ea5239afa115e950d45a2"},"schema_version":"1.0"},"canonical_sha256":"7dcd4513fbd28394ef9e343259219cf4cf11e2bf4e0c010103a2d36707005ccf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:44.168178Z","signature_b64":"b7o/4veXX4hLx2/lFgV6Je8efsWa2CoWfxCVj3hhFeIQYOImGMWgg8N5PCRWy5qa7ip1+yA7ukMiTa83LVvWAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dcd4513fbd28394ef9e343259219cf4cf11e2bf4e0c010103a2d36707005ccf","last_reissued_at":"2026-07-05T11:13:44.167752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:44.167752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.00993","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":"2026-07-05T11:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2Xt5RpQaZbBfue2S0ws/G5h06b50u/x43zRk1Bhg9xy4rehbHixhSh6dzj1tS8Ofkc1d2eJGgr4C+f5O970/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:15:27.712660Z"},"content_sha256":"b87e2e0060590f833be09cfec76d9cd1cc4d1289d304ca0ae7944df5eb7dc3bb","schema_version":"1.0","event_id":"sha256:b87e2e0060590f833be09cfec76d9cd1cc4d1289d304ca0ae7944df5eb7dc3bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:PXGUKE732KBZJ346GQZFSIM46T","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FlexSelect: Flexible Token Selection for Efficient Long Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fengyun Rao, Linchao Zhu, Tianyi Wang, Yi Yang, Yu Lu, Yunzhu Zhang","submitted_at":"2025-06-01T12:49:39Z","abstract_excerpt":"Long-form video understanding poses a significant challenge for video large language models (VideoLLMs) due to prohibitively high computational and memory demands. In this paper, we propose FlexSelect, a flexible and efficient token selection strategy for processing long videos. FlexSelect identifies and retains the most semantically relevant content by leveraging cross-modal attention patterns from a reference transformer layer. It comprises two key components: (1) a training-free token ranking pipeline that leverages faithful cross-modal attention weights to estimate each video token's impor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00993","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/2506.00993/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":"2026-07-05T11:13:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OfQWYQpr6fL9xDsrJ/I8At2k9+hqXulYO26FfGIzTV903c1xSoPy72U2wd7414qtThwVr6dpTM9/GCki3cOgAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:15:27.713490Z"},"content_sha256":"535624185b451deeaf76d52c9082ec88eee0f8447ed2f052da3d5f3574498e62","schema_version":"1.0","event_id":"sha256:535624185b451deeaf76d52c9082ec88eee0f8447ed2f052da3d5f3574498e62"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PXGUKE732KBZJ346GQZFSIM46T/bundle.json","state_url":"https://pith.science/pith/PXGUKE732KBZJ346GQZFSIM46T/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PXGUKE732KBZJ346GQZFSIM46T/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":"2026-08-06T06:15:27Z","links":{"resolver":"https://pith.science/pith/PXGUKE732KBZJ346GQZFSIM46T","bundle":"https://pith.science/pith/PXGUKE732KBZJ346GQZFSIM46T/bundle.json","state":"https://pith.science/pith/PXGUKE732KBZJ346GQZFSIM46T/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PXGUKE732KBZJ346GQZFSIM46T/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PXGUKE732KBZJ346GQZFSIM46T","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":"e22ebf91c80b11910319f691169285051a101d97c82ea5239afa115e950d45a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T12:49:39Z","title_canon_sha256":"4646cb638e85ed08c987905925385b5ce93dd4c874d428958f8e7b863856602c"},"schema_version":"1.0","source":{"id":"2506.00993","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.00993","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"arxiv_version","alias_value":"2506.00993v1","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00993","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_12","alias_value":"PXGUKE732KBZ","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_16","alias_value":"PXGUKE732KBZJ346","created_at":"2026-07-05T11:13:44Z"},{"alias_kind":"pith_short_8","alias_value":"PXGUKE73","created_at":"2026-07-05T11:13:44Z"}],"graph_snapshots":[{"event_id":"sha256:535624185b451deeaf76d52c9082ec88eee0f8447ed2f052da3d5f3574498e62","target":"graph","created_at":"2026-07-05T11:13:44Z","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/2506.00993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Long-form video understanding poses a significant challenge for video large language models (VideoLLMs) due to prohibitively high computational and memory demands. In this paper, we propose FlexSelect, a flexible and efficient token selection strategy for processing long videos. FlexSelect identifies and retains the most semantically relevant content by leveraging cross-modal attention patterns from a reference transformer layer. It comprises two key components: (1) a training-free token ranking pipeline that leverages faithful cross-modal attention weights to estimate each video token's impor","authors_text":"Fengyun Rao, Linchao Zhu, Tianyi Wang, Yi Yang, Yu Lu, Yunzhu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T12:49:39Z","title":"FlexSelect: Flexible Token Selection for Efficient Long Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00993","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:b87e2e0060590f833be09cfec76d9cd1cc4d1289d304ca0ae7944df5eb7dc3bb","target":"record","created_at":"2026-07-05T11:13:44Z","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":"e22ebf91c80b11910319f691169285051a101d97c82ea5239afa115e950d45a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-01T12:49:39Z","title_canon_sha256":"4646cb638e85ed08c987905925385b5ce93dd4c874d428958f8e7b863856602c"},"schema_version":"1.0","source":{"id":"2506.00993","kind":"arxiv","version":1}},"canonical_sha256":"7dcd4513fbd28394ef9e343259219cf4cf11e2bf4e0c010103a2d36707005ccf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dcd4513fbd28394ef9e343259219cf4cf11e2bf4e0c010103a2d36707005ccf","first_computed_at":"2026-07-05T11:13:44.167752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:44.167752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"b7o/4veXX4hLx2/lFgV6Je8efsWa2CoWfxCVj3hhFeIQYOImGMWgg8N5PCRWy5qa7ip1+yA7ukMiTa83LVvWAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:44.168178Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.00993","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b87e2e0060590f833be09cfec76d9cd1cc4d1289d304ca0ae7944df5eb7dc3bb","sha256:535624185b451deeaf76d52c9082ec88eee0f8447ed2f052da3d5f3574498e62"],"state_sha256":"d2ffe7466d6e7953e88a19bf963c0206c1618010d8d725e5cd1248c08be58219"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1U3gUzJ+Lyr67BZwc/31/u1vOTA9HWGHPvYLVtCGaQz9SlH3VAArgY3KxBRhISswhP17e86GUx0IshOM64ygCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:15:27.719159Z","bundle_sha256":"5c6b4ae4176b0d0fe271084af9ce3c2b4cb3e2b1bf5e9f802167d696ca9f1cb1"}}