{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3MWKSA7IJKVF77MAMVW2L4UZBZ","short_pith_number":"pith:3MWKSA7I","canonical_record":{"source":{"id":"2607.15689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T07:04:31Z","cross_cats_sorted":[],"title_canon_sha256":"470d47dc85d9c8cba0b8ee6c4147f68ff6b8b70d2133333dee0e41883befcb6d","abstract_canon_sha256":"a77ed7e5ac3fd5fa37355727e5bb636453b2795eab86d2338a10860f50d1dfd8"},"schema_version":"1.0"},"canonical_sha256":"db2ca903e84aaa5ffd80656da5f2990e5109aa7ec712965a07266856bc8dcd1a","source":{"kind":"arxiv","id":"2607.15689","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15689","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15689v1","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15689","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"3MWKSA7IJKVF","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"3MWKSA7IJKVF77MA","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"3MWKSA7I","created_at":"2026-07-20T01:19:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3MWKSA7IJKVF77MAMVW2L4UZBZ","target":"record","payload":{"canonical_record":{"source":{"id":"2607.15689","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T07:04:31Z","cross_cats_sorted":[],"title_canon_sha256":"470d47dc85d9c8cba0b8ee6c4147f68ff6b8b70d2133333dee0e41883befcb6d","abstract_canon_sha256":"a77ed7e5ac3fd5fa37355727e5bb636453b2795eab86d2338a10860f50d1dfd8"},"schema_version":"1.0"},"canonical_sha256":"db2ca903e84aaa5ffd80656da5f2990e5109aa7ec712965a07266856bc8dcd1a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-20T01:19:04.499567Z","signature_b64":"YbwZGmG+4Z4qlW8H65FfjpaESeblK7ZvvfqyMVOXMSJh0867ilCyuHf7qTblCg838lM1Btzzw6W+osOZXhkoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"db2ca903e84aaa5ffd80656da5f2990e5109aa7ec712965a07266856bc8dcd1a","last_reissued_at":"2026-07-20T01:19:04.498724Z","signature_status":"signed_v1","first_computed_at":"2026-07-20T01:19:04.498724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.15689","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":"2026-07-20T01:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gt/HnmlGW7O8ur2GiL70JCqmf2+C0AGpOqHGm2bhdtR42Mp7ZyOpMxzc8Q/JjUtd5IEJ0PhsOPr/Oinb827kAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T11:52:43.238219Z"},"content_sha256":"8e3b63e029ab1708dcb0b3865ca9075cd06071ffd4e5dcc6db12d55b1a74fda6","schema_version":"1.0","event_id":"sha256:8e3b63e029ab1708dcb0b3865ca9075cd06071ffd4e5dcc6db12d55b1a74fda6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3MWKSA7IJKVF77MAMVW2L4UZBZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alex Jinpeng Wang, Dongxing Mao, Linjie Li, Ping Yu, Rui Yan, Xiangxi Zheng, Yilin Wang, Yuan Yao, Zhengyuan Yang","submitted_at":"2026-07-17T07:04:31Z","abstract_excerpt":"Understanding long videos with multimodal large language models (MLLMs) requires selecting a compact set of frames from thousands of candidates, yet identifying the right frames seemingly requires understanding the video first. We resolve this circular dependency with a simple observation: cross-modal attention at validation-selected extraction layers in MLLMs already provides query-relevant frame evidence without requiring autoregressive generation. We exploit this property to build DAFS (Dynamic Attention-based Budget-aware Frame Selection), a training-free frame selector. A lightweight MLLM"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15689","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/2607.15689/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":"2026-07-20T01:19:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nGP/LCH2xmwCAWG/TmNloCiDFzdsSSW/g8IKNo+sdgu+9yMSUabThdGlmAoJQRwsDA6eCuaeytybBxnK2XehCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T11:52:43.238686Z"},"content_sha256":"298da70a2047e677070d6bd06ae67a0a1f1587b5ccd0ceca3ae1a4001b22f50c","schema_version":"1.0","event_id":"sha256:298da70a2047e677070d6bd06ae67a0a1f1587b5ccd0ceca3ae1a4001b22f50c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3MWKSA7IJKVF77MAMVW2L4UZBZ/bundle.json","state_url":"https://pith.science/pith/3MWKSA7IJKVF77MAMVW2L4UZBZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3MWKSA7IJKVF77MAMVW2L4UZBZ/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":"2026-08-02T11:52:43Z","links":{"resolver":"https://pith.science/pith/3MWKSA7IJKVF77MAMVW2L4UZBZ","bundle":"https://pith.science/pith/3MWKSA7IJKVF77MAMVW2L4UZBZ/bundle.json","state":"https://pith.science/pith/3MWKSA7IJKVF77MAMVW2L4UZBZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3MWKSA7IJKVF77MAMVW2L4UZBZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3MWKSA7IJKVF77MAMVW2L4UZBZ","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":"a77ed7e5ac3fd5fa37355727e5bb636453b2795eab86d2338a10860f50d1dfd8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T07:04:31Z","title_canon_sha256":"470d47dc85d9c8cba0b8ee6c4147f68ff6b8b70d2133333dee0e41883befcb6d"},"schema_version":"1.0","source":{"id":"2607.15689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.15689","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.15689v1","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.15689","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"pith_short_12","alias_value":"3MWKSA7IJKVF","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"pith_short_16","alias_value":"3MWKSA7IJKVF77MA","created_at":"2026-07-20T01:19:04Z"},{"alias_kind":"pith_short_8","alias_value":"3MWKSA7I","created_at":"2026-07-20T01:19:04Z"}],"graph_snapshots":[{"event_id":"sha256:298da70a2047e677070d6bd06ae67a0a1f1587b5ccd0ceca3ae1a4001b22f50c","target":"graph","created_at":"2026-07-20T01:19:04Z","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/2607.15689/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding long videos with multimodal large language models (MLLMs) requires selecting a compact set of frames from thousands of candidates, yet identifying the right frames seemingly requires understanding the video first. We resolve this circular dependency with a simple observation: cross-modal attention at validation-selected extraction layers in MLLMs already provides query-relevant frame evidence without requiring autoregressive generation. We exploit this property to build DAFS (Dynamic Attention-based Budget-aware Frame Selection), a training-free frame selector. A lightweight MLLM","authors_text":"Alex Jinpeng Wang, Dongxing Mao, Linjie Li, Ping Yu, Rui Yan, Xiangxi Zheng, Yilin Wang, Yuan Yao, Zhengyuan Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T07:04:31Z","title":"Efficient Frame Selection for Long Videos at Test Time with Attention-Based MLLM Selectors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.15689","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":"sha256:8e3b63e029ab1708dcb0b3865ca9075cd06071ffd4e5dcc6db12d55b1a74fda6","target":"record","created_at":"2026-07-20T01:19:04Z","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":"a77ed7e5ac3fd5fa37355727e5bb636453b2795eab86d2338a10860f50d1dfd8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-17T07:04:31Z","title_canon_sha256":"470d47dc85d9c8cba0b8ee6c4147f68ff6b8b70d2133333dee0e41883befcb6d"},"schema_version":"1.0","source":{"id":"2607.15689","kind":"arxiv","version":1}},"canonical_sha256":"db2ca903e84aaa5ffd80656da5f2990e5109aa7ec712965a07266856bc8dcd1a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"db2ca903e84aaa5ffd80656da5f2990e5109aa7ec712965a07266856bc8dcd1a","first_computed_at":"2026-07-20T01:19:04.498724Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-20T01:19:04.498724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YbwZGmG+4Z4qlW8H65FfjpaESeblK7ZvvfqyMVOXMSJh0867ilCyuHf7qTblCg838lM1Btzzw6W+osOZXhkoBA==","signature_status":"signed_v1","signed_at":"2026-07-20T01:19:04.499567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.15689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e3b63e029ab1708dcb0b3865ca9075cd06071ffd4e5dcc6db12d55b1a74fda6","sha256:298da70a2047e677070d6bd06ae67a0a1f1587b5ccd0ceca3ae1a4001b22f50c"],"state_sha256":"97d5ccbb15683264c1967acdc967be45bd719154c348d1ecdc82b55103230c6c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Knb+k+CxXYvVXE5qSnZZ89Isz/aNmH7RLTjfsFQn7tL6FSvZqUwoTRhpjo8EyO+ThtHOw4KUAb6GqSFyU3BKAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T11:52:43.241938Z","bundle_sha256":"6edfc11fcb335197f3ea53d682cc29b7f544cf7f39613d1f61d5c2b1e99c031c"}}