{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F7NU6YHU2S5BTY7TB6OR5CQV7P","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":"eebda950b4a660dd8c87cf638b7b64bdf2ad08e29ff31f6708ee3739354c7146","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T17:59:30Z","title_canon_sha256":"bfe52e1bb2fe8a74642c3794c994db518ba0e2e1f4a8f6cffbf98a0eaee2c837"},"schema_version":"1.0","source":{"id":"2407.13766","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.13766","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.13766v4","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.13766","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"F7NU6YHU2S5B","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"F7NU6YHU2S5BTY7T","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"F7NU6YHU","created_at":"2026-07-05T10:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:a6602c828cbf67f3846b0f6f4d7409009faf842605ba2f6d87ac78116fe9283a","target":"graph","created_at":"2026-07-05T10:28:19Z","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/2407.13766/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Multimodal Models (LMMs) have made significant strides in visual question-answering for single images. Recent advancements like long-context LMMs have allowed them to ingest larger, or even multiple, images. However, the ability to process a large number of visual tokens does not guarantee effective retrieval and reasoning for multi-image question answering (MIQA), especially in real-world applications like photo album searches or satellite imagery analysis. In this work, we first assess the limitations of current benchmarks for long-context LMMs. We address these limitations by introduc","authors_text":"David M. Chan, Giscard Biamby, Jerome Quenum, Joseph E. Gonzalez, Ritwik Gupta, Trevor Darrell, Tsung-Han Wu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T17:59:30Z","title":"Visual Haystacks: A Vision-Centric Needle-In-A-Haystack Benchmark"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.13766","kind":"arxiv","version":4},"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":"sha256:32f19bf349fbe424d88820761b8d2fbd2f81c3b0ab6a23d9c4b0eb912465128b","target":"record","created_at":"2026-07-05T10:28:19Z","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":"eebda950b4a660dd8c87cf638b7b64bdf2ad08e29ff31f6708ee3739354c7146","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-18T17:59:30Z","title_canon_sha256":"bfe52e1bb2fe8a74642c3794c994db518ba0e2e1f4a8f6cffbf98a0eaee2c837"},"schema_version":"1.0","source":{"id":"2407.13766","kind":"arxiv","version":4}},"canonical_sha256":"2fdb4f60f4d4ba19e3f30f9d1e8a15fbd124c59abf7574c4ba53a18ef5f54e87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2fdb4f60f4d4ba19e3f30f9d1e8a15fbd124c59abf7574c4ba53a18ef5f54e87","first_computed_at":"2026-07-05T10:28:19.289245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:19.289245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NB/ftaSpoepHyk8nGjFiMColYnOe3WXfGS79YEdhYuvnLH2fMl5dtaZyHBe8Z12/DJkLK67I6h8eHXuRi7XpAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:19.289742Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.13766","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:32f19bf349fbe424d88820761b8d2fbd2f81c3b0ab6a23d9c4b0eb912465128b","sha256:a6602c828cbf67f3846b0f6f4d7409009faf842605ba2f6d87ac78116fe9283a"],"state_sha256":"6a385e7d3cdf29b0b4c1f059dfe7187eaabe349c8bff12d0399b0cb1cc4b9fce"}