{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XYBZXXFKCACC7IL65AZZJBRXMH","short_pith_number":"pith:XYBZXXFK","canonical_record":{"source":{"id":"2504.17447","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T11:19:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3d54bd4292d8cf075b1693ab80968bb176353a67f8d3f455c4ba9ce63a79956","abstract_canon_sha256":"7138de4eb191ad4a4d2091d007dd210a363c3b49c30fd5c87a361f284d6f0e50"},"schema_version":"1.0"},"canonical_sha256":"be039bdcaa10042fa17ee83394863761d4df945f8512edeb5be045557b9c1737","source":{"kind":"arxiv","id":"2504.17447","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17447","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17447v1","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17447","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"XYBZXXFKCACC","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"XYBZXXFKCACC7IL6","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"XYBZXXFK","created_at":"2026-07-05T10:53:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XYBZXXFKCACC7IL65AZZJBRXMH","target":"record","payload":{"canonical_record":{"source":{"id":"2504.17447","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T11:19:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3d54bd4292d8cf075b1693ab80968bb176353a67f8d3f455c4ba9ce63a79956","abstract_canon_sha256":"7138de4eb191ad4a4d2091d007dd210a363c3b49c30fd5c87a361f284d6f0e50"},"schema_version":"1.0"},"canonical_sha256":"be039bdcaa10042fa17ee83394863761d4df945f8512edeb5be045557b9c1737","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:53:28.910697Z","signature_b64":"MTHisrFQMAjdbd4skWYE7xyny0iKtfAZQqr+KtpMmppBkTdFclFj3BHNdhZSgJlqYa+cd3Z9rkHzfRjWihptBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be039bdcaa10042fa17ee83394863761d4df945f8512edeb5be045557b9c1737","last_reissued_at":"2026-07-05T10:53:28.910123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:53:28.910123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.17447","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":"2026-07-05T10:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yxm4zhi/qgkL+OCqmGe8dnyexhIL/ajvT9y/aCxJU0jnJejnpireC5BJ0gtR2aY5WQ6tW5cOsrHi/aJ7rZwlBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:34:39.395848Z"},"content_sha256":"3de2aaa80b186bfd566279bb18bd3f0f4746f3dcf57e3090b5e4f89cbaaa4a07","schema_version":"1.0","event_id":"sha256:3de2aaa80b186bfd566279bb18bd3f0f4746f3dcf57e3090b5e4f89cbaaa4a07"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XYBZXXFKCACC7IL65AZZJBRXMH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"De-An Huang, Jan Kautz, Subhashree Radhakrishnan, Zhiding Yu","submitted_at":"2025-04-24T11:19:18Z","abstract_excerpt":"There has been impressive progress in Large Multimodal Models (LMMs). Recent works extend these models to long inputs, including multi-page documents and long videos. However, the model size and performance of these long context models are still limited due to the computational cost in both training and inference. In this work, we explore an orthogonal direction and process long inputs without long context LMMs. We propose Frame Selection Augmented Generation (FRAG), where the model first selects relevant frames within the input, and then only generates the final outputs based on the selected "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17447","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/2504.17447/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":"2026-07-05T10:53:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iwrYhT+x89FkvRmBBw8TdFQEMl7pXcDkvdOniTAglymEbyKdFcpGo202V5hFHqo5GxSO9mWF/ZW2sEJhUQNpCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T20:34:39.396890Z"},"content_sha256":"05287b60216e707c7b97118f6d12f45c2f2078d8e94a145d67e956696cfaa62f","schema_version":"1.0","event_id":"sha256:05287b60216e707c7b97118f6d12f45c2f2078d8e94a145d67e956696cfaa62f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XYBZXXFKCACC7IL65AZZJBRXMH/bundle.json","state_url":"https://pith.science/pith/XYBZXXFKCACC7IL65AZZJBRXMH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XYBZXXFKCACC7IL65AZZJBRXMH/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":"2026-08-17T20:34:39Z","links":{"resolver":"https://pith.science/pith/XYBZXXFKCACC7IL65AZZJBRXMH","bundle":"https://pith.science/pith/XYBZXXFKCACC7IL65AZZJBRXMH/bundle.json","state":"https://pith.science/pith/XYBZXXFKCACC7IL65AZZJBRXMH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XYBZXXFKCACC7IL65AZZJBRXMH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XYBZXXFKCACC7IL65AZZJBRXMH","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":"7138de4eb191ad4a4d2091d007dd210a363c3b49c30fd5c87a361f284d6f0e50","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T11:19:18Z","title_canon_sha256":"b3d54bd4292d8cf075b1693ab80968bb176353a67f8d3f455c4ba9ce63a79956"},"schema_version":"1.0","source":{"id":"2504.17447","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.17447","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"arxiv_version","alias_value":"2504.17447v1","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.17447","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"pith_short_12","alias_value":"XYBZXXFKCACC","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"pith_short_16","alias_value":"XYBZXXFKCACC7IL6","created_at":"2026-07-05T10:53:28Z"},{"alias_kind":"pith_short_8","alias_value":"XYBZXXFK","created_at":"2026-07-05T10:53:28Z"}],"graph_snapshots":[{"event_id":"sha256:05287b60216e707c7b97118f6d12f45c2f2078d8e94a145d67e956696cfaa62f","target":"graph","created_at":"2026-07-05T10:53:28Z","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/2504.17447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"There has been impressive progress in Large Multimodal Models (LMMs). Recent works extend these models to long inputs, including multi-page documents and long videos. However, the model size and performance of these long context models are still limited due to the computational cost in both training and inference. In this work, we explore an orthogonal direction and process long inputs without long context LMMs. We propose Frame Selection Augmented Generation (FRAG), where the model first selects relevant frames within the input, and then only generates the final outputs based on the selected ","authors_text":"De-An Huang, Jan Kautz, Subhashree Radhakrishnan, Zhiding Yu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T11:19:18Z","title":"FRAG: Frame Selection Augmented Generation for Long Video and Long Document Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.17447","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":"sha256:3de2aaa80b186bfd566279bb18bd3f0f4746f3dcf57e3090b5e4f89cbaaa4a07","target":"record","created_at":"2026-07-05T10:53:28Z","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":"7138de4eb191ad4a4d2091d007dd210a363c3b49c30fd5c87a361f284d6f0e50","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-24T11:19:18Z","title_canon_sha256":"b3d54bd4292d8cf075b1693ab80968bb176353a67f8d3f455c4ba9ce63a79956"},"schema_version":"1.0","source":{"id":"2504.17447","kind":"arxiv","version":1}},"canonical_sha256":"be039bdcaa10042fa17ee83394863761d4df945f8512edeb5be045557b9c1737","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be039bdcaa10042fa17ee83394863761d4df945f8512edeb5be045557b9c1737","first_computed_at":"2026-07-05T10:53:28.910123Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:53:28.910123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MTHisrFQMAjdbd4skWYE7xyny0iKtfAZQqr+KtpMmppBkTdFclFj3BHNdhZSgJlqYa+cd3Z9rkHzfRjWihptBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:53:28.910697Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.17447","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3de2aaa80b186bfd566279bb18bd3f0f4746f3dcf57e3090b5e4f89cbaaa4a07","sha256:05287b60216e707c7b97118f6d12f45c2f2078d8e94a145d67e956696cfaa62f"],"state_sha256":"5a9c5e5f2a089301187582c8d72cb4767aef285e3a8f6f7296ad94e3547071d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f8+EGWCsTivWtQ0Mzd9eoFHllcxMiaelolsRgyGg2EGyjstmcnSNDvxGVaMQcajRFCbBiRRkvZ+cqWyqrSvLCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T20:34:39.403452Z","bundle_sha256":"e24c2f1aa00c661de9f2358a8757c8b340cfd5079fae944d7945defa0fae3f7a"}}