{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DPXU56C5OQL2KO7HP6DETPPKYU","short_pith_number":"pith:DPXU56C5","canonical_record":{"source":{"id":"2404.18532","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T09:19:05Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"79103ddbf4028d691c489ce354b42d87596dc64d5f2f6d570f2ed250ee7ace3c","abstract_canon_sha256":"83b4be5e8b5e102517ae34c50695cfd4383820c031726c67e5c8492302ecc968"},"schema_version":"1.0"},"canonical_sha256":"1bef4ef85d7417a53be77f8649bdeac52d821660543d11c14ac676cc0ffa4d9d","source":{"kind":"arxiv","id":"2404.18532","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18532","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18532v2","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18532","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"DPXU56C5OQL2","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"DPXU56C5OQL2KO7H","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"DPXU56C5","created_at":"2026-07-05T08:19:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DPXU56C5OQL2KO7HP6DETPPKYU","target":"record","payload":{"canonical_record":{"source":{"id":"2404.18532","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T09:19:05Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"79103ddbf4028d691c489ce354b42d87596dc64d5f2f6d570f2ed250ee7ace3c","abstract_canon_sha256":"83b4be5e8b5e102517ae34c50695cfd4383820c031726c67e5c8492302ecc968"},"schema_version":"1.0"},"canonical_sha256":"1bef4ef85d7417a53be77f8649bdeac52d821660543d11c14ac676cc0ffa4d9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:19:24.514052Z","signature_b64":"ozgghJ0u1U83ArZ+yMdCQ1xiWv6m3lNDQmKDD9tLQnaEW7juBmuDXOAmYWFzi6BrddypKnewnpMtR2GPdlXpAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bef4ef85d7417a53be77f8649bdeac52d821660543d11c14ac676cc0ffa4d9d","last_reissued_at":"2026-07-05T08:19:24.513562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:19:24.513562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.18532","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":"2026-07-05T08:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YHmyRIuYhyaviTaHFEV7B50ExBRxubrp+kpZ41/h5RVap08fJfpB/XKEGMftZt+ztJh/TL5f2SNUSZ9k+Yn/DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:14:25.928877Z"},"content_sha256":"943b7777b2ba1117b22414cd74b537bd026d9c642800bf28a80be0ba62eb086a","schema_version":"1.0","event_id":"sha256:943b7777b2ba1117b22414cd74b537bd026d9c642800bf28a80be0ba62eb086a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DPXU56C5OQL2KO7HP6DETPPKYU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MileBench: Benchmarking MLLMs in Long Context","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Dingjie Song, Fei Yu, Guiming Hardy Chen, Shunian Chen, Xiang Wan","submitted_at":"2024-04-29T09:19:05Z","abstract_excerpt":"Despite the advancements and impressive performance of Multimodal Large Language Models (MLLMs) on benchmarks, their effectiveness in real-world, long-context, and multi-image tasks is unclear due to the benchmarks' limited scope. Existing benchmarks often focus on single-image and short-text samples, and when assessing multi-image tasks, they either limit the image count or focus on specific task (e.g time-series captioning), potentially obscuring the performance challenges of MLLMs. To address these limitations, we introduce MileBench, a pioneering benchmark designed to test the MultImodal L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18532","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/2404.18532/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":"2026-07-05T08:19:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ol/NMQqqU1y1iKdQ+NKMValpiiDf7R4TZx/yDC0Tv8EGuHjtFnqIvoJuaYDCmPJettaMep+iXJaTk3Wu+QL7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T19:14:25.929441Z"},"content_sha256":"c3512c716b82ecd658523b5da5bc4838c1f6b55859dbd9824ce6b45c926a1889","schema_version":"1.0","event_id":"sha256:c3512c716b82ecd658523b5da5bc4838c1f6b55859dbd9824ce6b45c926a1889"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DPXU56C5OQL2KO7HP6DETPPKYU/bundle.json","state_url":"https://pith.science/pith/DPXU56C5OQL2KO7HP6DETPPKYU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DPXU56C5OQL2KO7HP6DETPPKYU/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":"2026-08-03T19:14:25Z","links":{"resolver":"https://pith.science/pith/DPXU56C5OQL2KO7HP6DETPPKYU","bundle":"https://pith.science/pith/DPXU56C5OQL2KO7HP6DETPPKYU/bundle.json","state":"https://pith.science/pith/DPXU56C5OQL2KO7HP6DETPPKYU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DPXU56C5OQL2KO7HP6DETPPKYU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DPXU56C5OQL2KO7HP6DETPPKYU","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":"83b4be5e8b5e102517ae34c50695cfd4383820c031726c67e5c8492302ecc968","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T09:19:05Z","title_canon_sha256":"79103ddbf4028d691c489ce354b42d87596dc64d5f2f6d570f2ed250ee7ace3c"},"schema_version":"1.0","source":{"id":"2404.18532","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.18532","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"arxiv_version","alias_value":"2404.18532v2","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18532","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"pith_short_12","alias_value":"DPXU56C5OQL2","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"pith_short_16","alias_value":"DPXU56C5OQL2KO7H","created_at":"2026-07-05T08:19:24Z"},{"alias_kind":"pith_short_8","alias_value":"DPXU56C5","created_at":"2026-07-05T08:19:24Z"}],"graph_snapshots":[{"event_id":"sha256:c3512c716b82ecd658523b5da5bc4838c1f6b55859dbd9824ce6b45c926a1889","target":"graph","created_at":"2026-07-05T08:19:24Z","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/2404.18532/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the advancements and impressive performance of Multimodal Large Language Models (MLLMs) on benchmarks, their effectiveness in real-world, long-context, and multi-image tasks is unclear due to the benchmarks' limited scope. Existing benchmarks often focus on single-image and short-text samples, and when assessing multi-image tasks, they either limit the image count or focus on specific task (e.g time-series captioning), potentially obscuring the performance challenges of MLLMs. To address these limitations, we introduce MileBench, a pioneering benchmark designed to test the MultImodal L","authors_text":"Benyou Wang, Dingjie Song, Fei Yu, Guiming Hardy Chen, Shunian Chen, Xiang Wan","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T09:19:05Z","title":"MileBench: Benchmarking MLLMs in Long Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18532","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":"sha256:943b7777b2ba1117b22414cd74b537bd026d9c642800bf28a80be0ba62eb086a","target":"record","created_at":"2026-07-05T08:19:24Z","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":"83b4be5e8b5e102517ae34c50695cfd4383820c031726c67e5c8492302ecc968","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-29T09:19:05Z","title_canon_sha256":"79103ddbf4028d691c489ce354b42d87596dc64d5f2f6d570f2ed250ee7ace3c"},"schema_version":"1.0","source":{"id":"2404.18532","kind":"arxiv","version":2}},"canonical_sha256":"1bef4ef85d7417a53be77f8649bdeac52d821660543d11c14ac676cc0ffa4d9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1bef4ef85d7417a53be77f8649bdeac52d821660543d11c14ac676cc0ffa4d9d","first_computed_at":"2026-07-05T08:19:24.513562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:19:24.513562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ozgghJ0u1U83ArZ+yMdCQ1xiWv6m3lNDQmKDD9tLQnaEW7juBmuDXOAmYWFzi6BrddypKnewnpMtR2GPdlXpAA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:19:24.514052Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.18532","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:943b7777b2ba1117b22414cd74b537bd026d9c642800bf28a80be0ba62eb086a","sha256:c3512c716b82ecd658523b5da5bc4838c1f6b55859dbd9824ce6b45c926a1889"],"state_sha256":"77992aee266ebf774fcecffe9108ee641d1553f81c2061e4178ef76a5789a79b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"thuZKI73uUqikcKk2U6+WQvsglDBl2JjtZ0UneYlMUlqQDXPxOme38AFFuTwyWrMUtahtt6zkGC6Z6tTIiyDCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T19:14:25.933528Z","bundle_sha256":"cc986b87a08c6a62d3fbc709bf8479ff5300cb57e556ca2e1d0d9c1d432d9165"}}