{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:DAEFULCSXXFBW7YJNXE3FESLBB","short_pith_number":"pith:DAEFULCS","canonical_record":{"source":{"id":"2410.10139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T04:15:00Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"94de6ef6f4dede50f1308a6f62773f55c451723a638cb7f42ffa1943d1d86988","abstract_canon_sha256":"fb09e674cf137dad9c049d20779f4d76d618bfd2b1be6f864bf6f7f4e1d1055b"},"schema_version":"1.0"},"canonical_sha256":"18085a2c52bdca1b7f096dc9b2924b086cb969ebc94f591c87939571ad2b720d","source":{"kind":"arxiv","id":"2410.10139","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10139","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10139v2","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10139","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"pith_short_12","alias_value":"DAEFULCSXXFB","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"pith_short_16","alias_value":"DAEFULCSXXFBW7YJ","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"pith_short_8","alias_value":"DAEFULCS","created_at":"2026-07-05T10:41:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:DAEFULCSXXFBW7YJNXE3FESLBB","target":"record","payload":{"canonical_record":{"source":{"id":"2410.10139","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T04:15:00Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"94de6ef6f4dede50f1308a6f62773f55c451723a638cb7f42ffa1943d1d86988","abstract_canon_sha256":"fb09e674cf137dad9c049d20779f4d76d618bfd2b1be6f864bf6f7f4e1d1055b"},"schema_version":"1.0"},"canonical_sha256":"18085a2c52bdca1b7f096dc9b2924b086cb969ebc94f591c87939571ad2b720d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:49.213520Z","signature_b64":"cgFShBRsPpFPxaeYNGk5+K40w10rdm4b1flj7FboBhFtA/SlhcR/Ikm2u8xvW2m1PohhqjTRWmQJ+ChcraeHDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"18085a2c52bdca1b7f096dc9b2924b086cb969ebc94f591c87939571ad2b720d","last_reissued_at":"2026-07-05T10:41:49.213059Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:49.213059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.10139","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":"2026-07-05T10:41:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XmUZHsiJGr6RQBE9QEBxBPtM12+WId29hXmwn9fEG6FvPSmbQacwUlxRVEu2TQkMCNvP6JyGNIzaSiDuu03XBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:34:36.690108Z"},"content_sha256":"50e31918c5f51d560e003b8a9f4b8246a24698ed8672b7b46077fae951dab644","schema_version":"1.0","event_id":"sha256:50e31918c5f51d560e003b8a9f4b8246a24698ed8672b7b46077fae951dab644"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:DAEFULCSXXFBW7YJNXE3FESLBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Chenhang Cui, Huaxiu Yao, Lijuan Wang, Linjie Li, Mingyu Ding, Peng Xia, Shi Qiu, Siwei Han, Wenhao Zheng, Yiyang Zhou, Zhaorun Chen, Zhaoyang Wang","submitted_at":"2024-10-14T04:15:00Z","abstract_excerpt":"Interleaved multimodal comprehension and generation, enabling models to produce and interpret both images and text in arbitrary sequences, have become a pivotal area in multimodal learning. Despite significant advancements, the evaluation of this capability remains insufficient. Existing benchmarks suffer from limitations in data scale, scope, and evaluation depth, while current evaluation metrics are often costly or biased, lacking in reliability for practical applications. To address these challenges, we introduce MMIE, a large-scale knowledge-intensive benchmark for evaluating interleaved m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10139","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/2410.10139/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":"2026-07-05T10:41:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"soV07y7zC/l3eCTStcmFX1IaInpo+I4Hh8uS/J0A6XEt1PfTbqwWhMmTSAMmSEnU1lZMsA8PyyC4i5WXWMnaAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T17:34:36.691084Z"},"content_sha256":"cd9f3049cc48cce8f9291d3e5244ece37e5d556f1cf1fd48d3970f8c3e3ddb19","schema_version":"1.0","event_id":"sha256:cd9f3049cc48cce8f9291d3e5244ece37e5d556f1cf1fd48d3970f8c3e3ddb19"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DAEFULCSXXFBW7YJNXE3FESLBB/bundle.json","state_url":"https://pith.science/pith/DAEFULCSXXFBW7YJNXE3FESLBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DAEFULCSXXFBW7YJNXE3FESLBB/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":"2026-08-04T17:34:36Z","links":{"resolver":"https://pith.science/pith/DAEFULCSXXFBW7YJNXE3FESLBB","bundle":"https://pith.science/pith/DAEFULCSXXFBW7YJNXE3FESLBB/bundle.json","state":"https://pith.science/pith/DAEFULCSXXFBW7YJNXE3FESLBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DAEFULCSXXFBW7YJNXE3FESLBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DAEFULCSXXFBW7YJNXE3FESLBB","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":"fb09e674cf137dad9c049d20779f4d76d618bfd2b1be6f864bf6f7f4e1d1055b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T04:15:00Z","title_canon_sha256":"94de6ef6f4dede50f1308a6f62773f55c451723a638cb7f42ffa1943d1d86988"},"schema_version":"1.0","source":{"id":"2410.10139","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.10139","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"arxiv_version","alias_value":"2410.10139v2","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10139","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"pith_short_12","alias_value":"DAEFULCSXXFB","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"pith_short_16","alias_value":"DAEFULCSXXFBW7YJ","created_at":"2026-07-05T10:41:49Z"},{"alias_kind":"pith_short_8","alias_value":"DAEFULCS","created_at":"2026-07-05T10:41:49Z"}],"graph_snapshots":[{"event_id":"sha256:cd9f3049cc48cce8f9291d3e5244ece37e5d556f1cf1fd48d3970f8c3e3ddb19","target":"graph","created_at":"2026-07-05T10:41:49Z","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/2410.10139/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Interleaved multimodal comprehension and generation, enabling models to produce and interpret both images and text in arbitrary sequences, have become a pivotal area in multimodal learning. Despite significant advancements, the evaluation of this capability remains insufficient. Existing benchmarks suffer from limitations in data scale, scope, and evaluation depth, while current evaluation metrics are often costly or biased, lacking in reliability for practical applications. To address these challenges, we introduce MMIE, a large-scale knowledge-intensive benchmark for evaluating interleaved m","authors_text":"Chenhang Cui, Huaxiu Yao, Lijuan Wang, Linjie Li, Mingyu Ding, Peng Xia, Shi Qiu, Siwei Han, Wenhao Zheng, Yiyang Zhou, Zhaorun Chen, Zhaoyang Wang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T04:15:00Z","title":"MMIE: Massive Multimodal Interleaved Comprehension Benchmark for Large Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10139","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":"sha256:50e31918c5f51d560e003b8a9f4b8246a24698ed8672b7b46077fae951dab644","target":"record","created_at":"2026-07-05T10:41:49Z","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":"fb09e674cf137dad9c049d20779f4d76d618bfd2b1be6f864bf6f7f4e1d1055b","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-14T04:15:00Z","title_canon_sha256":"94de6ef6f4dede50f1308a6f62773f55c451723a638cb7f42ffa1943d1d86988"},"schema_version":"1.0","source":{"id":"2410.10139","kind":"arxiv","version":2}},"canonical_sha256":"18085a2c52bdca1b7f096dc9b2924b086cb969ebc94f591c87939571ad2b720d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"18085a2c52bdca1b7f096dc9b2924b086cb969ebc94f591c87939571ad2b720d","first_computed_at":"2026-07-05T10:41:49.213059Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:49.213059Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cgFShBRsPpFPxaeYNGk5+K40w10rdm4b1flj7FboBhFtA/SlhcR/Ikm2u8xvW2m1PohhqjTRWmQJ+ChcraeHDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:49.213520Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.10139","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:50e31918c5f51d560e003b8a9f4b8246a24698ed8672b7b46077fae951dab644","sha256:cd9f3049cc48cce8f9291d3e5244ece37e5d556f1cf1fd48d3970f8c3e3ddb19"],"state_sha256":"cbc25b4d221c9ac8a82160cf9b6e0de369223deaf80f32c96f400a70ea8a5cdc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G1nlDOV5E68rm94Jdb16OPn7H2ri8veYzHb3321GSPdHOEa3AYYevuz5PKCY4ht8+nAxlG1iov25EzbgEodXCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T17:34:36.721295Z","bundle_sha256":"ab1b7ae3dac894ec926516cf95c1986c04723ee9b9f4f7cf06897d9f5735df96"}}