{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DTL4V2DFPQ7GLCA7CXTP52D4PE","short_pith_number":"pith:DTL4V2DF","canonical_record":{"source":{"id":"2406.07230","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T13:09:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5c6ea84d2e31fd76ad1e66a864ff8f66a7257e6f884bccc9269e9668ac0b5f6","abstract_canon_sha256":"8746613dec7de29f987707178b991d385504f4dd14411a805be4f16b46a902f1"},"schema_version":"1.0"},"canonical_sha256":"1cd7cae8657c3e65881f15e6fee87c792c82aa1861a175384d0d7cc822801935","source":{"kind":"arxiv","id":"2406.07230","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07230","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07230v2","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07230","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"DTL4V2DFPQ7G","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"DTL4V2DFPQ7GLCA7","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"DTL4V2DF","created_at":"2026-07-05T09:18:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DTL4V2DFPQ7GLCA7CXTP52D4PE","target":"record","payload":{"canonical_record":{"source":{"id":"2406.07230","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T13:09:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a5c6ea84d2e31fd76ad1e66a864ff8f66a7257e6f884bccc9269e9668ac0b5f6","abstract_canon_sha256":"8746613dec7de29f987707178b991d385504f4dd14411a805be4f16b46a902f1"},"schema_version":"1.0"},"canonical_sha256":"1cd7cae8657c3e65881f15e6fee87c792c82aa1861a175384d0d7cc822801935","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:27.047594Z","signature_b64":"arjRuhn0qskDLtIT+wmmv5MJgweUxN1OhG4+Orl1gbbOPxzgNlDC6ipmnFfqoPkqV56B6mIWFuuDba2taLmXDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cd7cae8657c3e65881f15e6fee87c792c82aa1861a175384d0d7cc822801935","last_reissued_at":"2026-07-05T09:18:27.047113Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:27.047113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.07230","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:18:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZlhrpOVzmgJOcnpbNIFbrr00nqkxtJi2qUBKbtn9TLOHSfH9yaHbwytP6L8/iYCImCy967qPVd+3o1yHDrpuDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:37:28.928452Z"},"content_sha256":"157d8733b31c016f2b2b357f266ccd8d324501a2b0898a6deea002ea753e99a9","schema_version":"1.0","event_id":"sha256:157d8733b31c016f2b2b357f266ccd8d324501a2b0898a6deea002ea753e99a9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DTL4V2DFPQ7GLCA7CXTP52D4PE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Needle In A Multimodal Haystack","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jifeng Dai, Kaipeng Zhang, Lewei Lu, Mengkang Hu, Ping Luo, Shuibo Zhang, Shuo Liu, Tiantong Li, Weiyun Wang, Wenhai Wang, Wenqi Shao, Xizhou Zhu, Yiming Ren, Yuchen Duan, Yu Qiao, Zhe Chen","submitted_at":"2024-06-11T13:09:16Z","abstract_excerpt":"With the rapid advancement of multimodal large language models (MLLMs), their evaluation has become increasingly comprehensive. However, understanding long multimodal content, as a foundational ability for real-world applications, remains underexplored. In this work, we present Needle In A Multimodal Haystack (MM-NIAH), the first benchmark specifically designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents. Our benchmark includes three types of evaluation tasks: multimodal retrieval, counting, and reasoning. In each task, the model is requi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07230","kind":"arxiv","version":2},"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/2406.07230/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":"2026-07-05T09:18:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2bX9CZDxLsaep4nskiUge4iLGsY1CL0HK9MzenwHA2LCpi4hIcj/NjkaBkm/l1b3MEePy+VOvnkaWgpCmiBQAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T19:37:28.928830Z"},"content_sha256":"0e1b1ec1ae342d5aa9c9682ed5aba7c1ae84182ac0637f7297bb65a53edb2f80","schema_version":"1.0","event_id":"sha256:0e1b1ec1ae342d5aa9c9682ed5aba7c1ae84182ac0637f7297bb65a53edb2f80"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DTL4V2DFPQ7GLCA7CXTP52D4PE/bundle.json","state_url":"https://pith.science/pith/DTL4V2DFPQ7GLCA7CXTP52D4PE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DTL4V2DFPQ7GLCA7CXTP52D4PE/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":"2026-07-06T19:37:28Z","links":{"resolver":"https://pith.science/pith/DTL4V2DFPQ7GLCA7CXTP52D4PE","bundle":"https://pith.science/pith/DTL4V2DFPQ7GLCA7CXTP52D4PE/bundle.json","state":"https://pith.science/pith/DTL4V2DFPQ7GLCA7CXTP52D4PE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DTL4V2DFPQ7GLCA7CXTP52D4PE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DTL4V2DFPQ7GLCA7CXTP52D4PE","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":"8746613dec7de29f987707178b991d385504f4dd14411a805be4f16b46a902f1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T13:09:16Z","title_canon_sha256":"a5c6ea84d2e31fd76ad1e66a864ff8f66a7257e6f884bccc9269e9668ac0b5f6"},"schema_version":"1.0","source":{"id":"2406.07230","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.07230","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"arxiv_version","alias_value":"2406.07230v2","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07230","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_12","alias_value":"DTL4V2DFPQ7G","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_16","alias_value":"DTL4V2DFPQ7GLCA7","created_at":"2026-07-05T09:18:27Z"},{"alias_kind":"pith_short_8","alias_value":"DTL4V2DF","created_at":"2026-07-05T09:18:27Z"}],"graph_snapshots":[{"event_id":"sha256:0e1b1ec1ae342d5aa9c9682ed5aba7c1ae84182ac0637f7297bb65a53edb2f80","target":"graph","created_at":"2026-07-05T09:18:27Z","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/2406.07230/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid advancement of multimodal large language models (MLLMs), their evaluation has become increasingly comprehensive. However, understanding long multimodal content, as a foundational ability for real-world applications, remains underexplored. In this work, we present Needle In A Multimodal Haystack (MM-NIAH), the first benchmark specifically designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents. Our benchmark includes three types of evaluation tasks: multimodal retrieval, counting, and reasoning. In each task, the model is requi","authors_text":"Jifeng Dai, Kaipeng Zhang, Lewei Lu, Mengkang Hu, Ping Luo, Shuibo Zhang, Shuo Liu, Tiantong Li, Weiyun Wang, Wenhai Wang, Wenqi Shao, Xizhou Zhu, Yiming Ren, Yuchen Duan, Yu Qiao, Zhe Chen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T13:09:16Z","title":"Needle In A Multimodal Haystack"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07230","kind":"arxiv","version":2},"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":"sha256:157d8733b31c016f2b2b357f266ccd8d324501a2b0898a6deea002ea753e99a9","target":"record","created_at":"2026-07-05T09:18:27Z","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":"8746613dec7de29f987707178b991d385504f4dd14411a805be4f16b46a902f1","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-06-11T13:09:16Z","title_canon_sha256":"a5c6ea84d2e31fd76ad1e66a864ff8f66a7257e6f884bccc9269e9668ac0b5f6"},"schema_version":"1.0","source":{"id":"2406.07230","kind":"arxiv","version":2}},"canonical_sha256":"1cd7cae8657c3e65881f15e6fee87c792c82aa1861a175384d0d7cc822801935","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1cd7cae8657c3e65881f15e6fee87c792c82aa1861a175384d0d7cc822801935","first_computed_at":"2026-07-05T09:18:27.047113Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:27.047113Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"arjRuhn0qskDLtIT+wmmv5MJgweUxN1OhG4+Orl1gbbOPxzgNlDC6ipmnFfqoPkqV56B6mIWFuuDba2taLmXDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:27.047594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.07230","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:157d8733b31c016f2b2b357f266ccd8d324501a2b0898a6deea002ea753e99a9","sha256:0e1b1ec1ae342d5aa9c9682ed5aba7c1ae84182ac0637f7297bb65a53edb2f80"],"state_sha256":"0ac19ffda91712c1a4a754761c9d274aed21bee79ff85a036597880235f0e8aa"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B3xhznTrJq5yA3wt4MueMElQ8tWqc3DAyGUXjsVpI5hH9k4RnrtE6+Y5GgVNWtR96aR51dE1llfLz7eJcfUkCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T19:37:28.930941Z","bundle_sha256":"78416acc41d5cdd04f9563df29f4e3c7cddb27eddb37d9b9f1941cef073aa0f7"}}