{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:F4QJDZE4R3LWSUF47AGLVDY2NK","short_pith_number":"pith:F4QJDZE4","canonical_record":{"source":{"id":"2605.27243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T16:24:29Z","cross_cats_sorted":[],"title_canon_sha256":"ba1d0aa120631af5670471841f99b3b33a324457d23d450b1ce4e350e101a2a5","abstract_canon_sha256":"3f75d75e65730a67bfec2efe00a14adb8290018b7760379439a1a6be189390ef"},"schema_version":"1.0"},"canonical_sha256":"2f2091e49c8ed76950bcf80cba8f1a6a929e0214c2f3ee72dcb6aae551540f24","source":{"kind":"arxiv","id":"2605.27243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27243","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27243v1","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27243","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"F4QJDZE4R3LW","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"F4QJDZE4R3LWSUF4","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"F4QJDZE4","created_at":"2026-05-27T02:06:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:F4QJDZE4R3LWSUF47AGLVDY2NK","target":"record","payload":{"canonical_record":{"source":{"id":"2605.27243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T16:24:29Z","cross_cats_sorted":[],"title_canon_sha256":"ba1d0aa120631af5670471841f99b3b33a324457d23d450b1ce4e350e101a2a5","abstract_canon_sha256":"3f75d75e65730a67bfec2efe00a14adb8290018b7760379439a1a6be189390ef"},"schema_version":"1.0"},"canonical_sha256":"2f2091e49c8ed76950bcf80cba8f1a6a929e0214c2f3ee72dcb6aae551540f24","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:07.383035Z","signature_b64":"ExmjDLJNWJDzPL+21httcZsevhn3j+H0bRZTlPZ4VNbHei23MBmFxy3wO9IeHGVFfR+N6mKhmGg42+ScfBF5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f2091e49c8ed76950bcf80cba8f1a6a929e0214c2f3ee72dcb6aae551540f24","last_reissued_at":"2026-05-27T02:06:07.382497Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:07.382497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.27243","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":"2026-05-27T02:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lu2TV1ZVAbh0T0SmbpGltA8bg5wuDBOSeVETXXHsLtiWOuBoCYxNNxt2FM+41JRW/9MFFb1TUkCaCXjWoH32BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:45:27.368832Z"},"content_sha256":"df0c56524df840006daba1d8720ea32ea0f5ec538797ea43003700fbbd8b9d4e","schema_version":"1.0","event_id":"sha256:df0c56524df840006daba1d8720ea32ea0f5ec538797ea43003700fbbd8b9d4e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:F4QJDZE4R3LWSUF47AGLVDY2NK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aaron Branson Cigres Li, Ginny Wong, Haobo Li, Haodong Duan, Lishu Luo, Pasquale Minervini, Simon See, Xiyu Ren, Yangqiu Song, Yiming Du, Yu Zhao, Zhaowei Wang","submitted_at":"2026-05-26T16:24:29Z","abstract_excerpt":"Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories, requiring them to locate relevant evidence across interleaved text and images. Prior work has studied this behavior using retrieval heads in large language models, but its copy-based criterion does not directly apply when evidence appears in images. We introduce a multimodal retrieval head detection method that scores attention from question tokens to textual or visual evidence. With this method, we show that multimodal retrieval heads are sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27243","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/2605.27243/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":"2026-05-27T02:06:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d09l8lo8ikyXg7XqsOH58kIA7Au/X9qe4CdYQOf2aKG1vsLPxWZZ+HnbKMiFAhEImmCJ03xkjMwQzeyFfChbBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T09:45:27.369220Z"},"content_sha256":"a33093651c0c267bfaa5fcccb54af15391868829b0ae015cd34e82acb0c8cc6c","schema_version":"1.0","event_id":"sha256:a33093651c0c267bfaa5fcccb54af15391868829b0ae015cd34e82acb0c8cc6c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F4QJDZE4R3LWSUF47AGLVDY2NK/bundle.json","state_url":"https://pith.science/pith/F4QJDZE4R3LWSUF47AGLVDY2NK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F4QJDZE4R3LWSUF47AGLVDY2NK/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":"2026-05-28T09:45:27Z","links":{"resolver":"https://pith.science/pith/F4QJDZE4R3LWSUF47AGLVDY2NK","bundle":"https://pith.science/pith/F4QJDZE4R3LWSUF47AGLVDY2NK/bundle.json","state":"https://pith.science/pith/F4QJDZE4R3LWSUF47AGLVDY2NK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F4QJDZE4R3LWSUF47AGLVDY2NK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:F4QJDZE4R3LWSUF47AGLVDY2NK","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":"3f75d75e65730a67bfec2efe00a14adb8290018b7760379439a1a6be189390ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T16:24:29Z","title_canon_sha256":"ba1d0aa120631af5670471841f99b3b33a324457d23d450b1ce4e350e101a2a5"},"schema_version":"1.0","source":{"id":"2605.27243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.27243","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"arxiv_version","alias_value":"2605.27243v1","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27243","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"pith_short_12","alias_value":"F4QJDZE4R3LW","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"pith_short_16","alias_value":"F4QJDZE4R3LWSUF4","created_at":"2026-05-27T02:06:07Z"},{"alias_kind":"pith_short_8","alias_value":"F4QJDZE4","created_at":"2026-05-27T02:06:07Z"}],"graph_snapshots":[{"event_id":"sha256:a33093651c0c267bfaa5fcccb54af15391868829b0ae015cd34e82acb0c8cc6c","target":"graph","created_at":"2026-05-27T02:06:07Z","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/2605.27243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large vision-language models increasingly rely on long-context modeling to reason over documents, hour-level videos, and long-horizon agent trajectories, requiring them to locate relevant evidence across interleaved text and images. Prior work has studied this behavior using retrieval heads in large language models, but its copy-based criterion does not directly apply when evidence appears in images. We introduce a multimodal retrieval head detection method that scores attention from question tokens to textual or visual evidence. With this method, we show that multimodal retrieval heads are sp","authors_text":"Aaron Branson Cigres Li, Ginny Wong, Haobo Li, Haodong Duan, Lishu Luo, Pasquale Minervini, Simon See, Xiyu Ren, Yangqiu Song, Yiming Du, Yu Zhao, Zhaowei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T16:24:29Z","title":"Can Retrieval Heads See Images? Multimodal Retrieval Heads in Long-Context Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27243","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:df0c56524df840006daba1d8720ea32ea0f5ec538797ea43003700fbbd8b9d4e","target":"record","created_at":"2026-05-27T02:06:07Z","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":"3f75d75e65730a67bfec2efe00a14adb8290018b7760379439a1a6be189390ef","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-26T16:24:29Z","title_canon_sha256":"ba1d0aa120631af5670471841f99b3b33a324457d23d450b1ce4e350e101a2a5"},"schema_version":"1.0","source":{"id":"2605.27243","kind":"arxiv","version":1}},"canonical_sha256":"2f2091e49c8ed76950bcf80cba8f1a6a929e0214c2f3ee72dcb6aae551540f24","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f2091e49c8ed76950bcf80cba8f1a6a929e0214c2f3ee72dcb6aae551540f24","first_computed_at":"2026-05-27T02:06:07.382497Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T02:06:07.382497Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ExmjDLJNWJDzPL+21httcZsevhn3j+H0bRZTlPZ4VNbHei23MBmFxy3wO9IeHGVFfR+N6mKhmGg42+ScfBF5Bw==","signature_status":"signed_v1","signed_at":"2026-05-27T02:06:07.383035Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.27243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df0c56524df840006daba1d8720ea32ea0f5ec538797ea43003700fbbd8b9d4e","sha256:a33093651c0c267bfaa5fcccb54af15391868829b0ae015cd34e82acb0c8cc6c"],"state_sha256":"8bfe8f7dbd61557351e2273e893b9802b23be36acea66bc7bd3426a1c51ffa4c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C8O53OS6lcpTDiY/kXrH+uleOpQhvqKeegDL/F0G3gWeDcZjJ8Od/WiiSNHFHmmrXLeNfSlAVI8kGlIpiQJxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T09:45:27.371384Z","bundle_sha256":"997ebf7fa89a4b6894869e78b5d4c6adf5d19f56c09e188e24005332603c427b"}}