{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YJESQQA6NOERO6OVGNNAQKLULO","short_pith_number":"pith:YJESQQA6","canonical_record":{"source":{"id":"2607.21155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T10:37:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc972ca3a393d81768ea5179585b443884a76fbf6eb60d9a8f6e871c64af0159","abstract_canon_sha256":"22865deda6c963c735145918ac37dc072b81854de1c1d498ca22a4a51bc5798a"},"schema_version":"1.0"},"canonical_sha256":"c24928401e6b891779d5335a0829745b9b0da3534867e0357d27e51d415f3d17","source":{"kind":"arxiv","id":"2607.21155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21155","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21155v1","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21155","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"YJESQQA6NOER","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"YJESQQA6NOERO6OV","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"YJESQQA6","created_at":"2026-07-24T01:23:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YJESQQA6NOERO6OVGNNAQKLULO","target":"record","payload":{"canonical_record":{"source":{"id":"2607.21155","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T10:37:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"dc972ca3a393d81768ea5179585b443884a76fbf6eb60d9a8f6e871c64af0159","abstract_canon_sha256":"22865deda6c963c735145918ac37dc072b81854de1c1d498ca22a4a51bc5798a"},"schema_version":"1.0"},"canonical_sha256":"c24928401e6b891779d5335a0829745b9b0da3534867e0357d27e51d415f3d17","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-24T01:23:56.031609Z","signature_b64":"nYUteSRDfJdjf4Y7aMwOTkCtIBgZSWHFekwj8ZtZTHHqIsHbakI91l3iOu4tn39KkHCmZLIOsJGOvhkvUU2BAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c24928401e6b891779d5335a0829745b9b0da3534867e0357d27e51d415f3d17","last_reissued_at":"2026-07-24T01:23:56.030754Z","signature_status":"signed_v1","first_computed_at":"2026-07-24T01:23:56.030754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.21155","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":"2026-07-24T01:23:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GiDUle1eAQh/PubYGyPlqSYgUG9xvywhJFh5iAGv04XgdNudYuKomwMuufsuP0pkgmWh9i8EnA6IZu5EZkixBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:05:41.034044Z"},"content_sha256":"ccd6bb5dac63194611a5bc933b99fdc71c24b111228ddcaadd9cbb0388382302","schema_version":"1.0","event_id":"sha256:ccd6bb5dac63194611a5bc933b99fdc71c24b111228ddcaadd9cbb0388382302"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YJESQQA6NOERO6OVGNNAQKLULO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benno Krojer, Hanseok Oh, Hyunji Lee, Parishad BehnamGhader, Paul Liang, Siva Reddy, Verna Dankers","submitted_at":"2026-07-23T10:37:01Z","abstract_excerpt":"Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression understanding, visual grounding, object recognition, knowledge retrieval, and reasoning-yet existing benchmarks typically report only end-task accuracy, obscuring where failures arise. To analyze the full KI-VQA pipeline, we introduce CRAG-MM-Diagnostics, a diagnostic benchmark with stage-wise data annotations that isol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21155","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/2607.21155/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":"2026-07-24T01:23:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/u43Mwxq30lAxjV2OYnrbcoAW9KE63eoW7xy+n+s6fNfVzKxsMkpL4Y3HuP4N2WVR/aDt8l1HS2Lc5KxRhf+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:05:41.035245Z"},"content_sha256":"f2725667c8261c891fbd24f5678864c9542cd2c7bafb2eefa7c38329ca6a8185","schema_version":"1.0","event_id":"sha256:f2725667c8261c891fbd24f5678864c9542cd2c7bafb2eefa7c38329ca6a8185"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:YJESQQA6NOERO6OVGNNAQKLULO","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.18653/v1/2023.acl-long.546) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Mallen, A., Asai, A., Zhong, V., Das, R., Khashabi, D., Hajishirzi, H.: When not to trust language models: Investigating effectiveness of parametric and non- parametric memories. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Pro- ceed","arxiv_id":"2607.21155","detector":"doi_compliance","evidence":{"ref_index":23,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.18653/v1/2023.acl-","reconstructed_doi":"10.18653/v1/2023.acl-long.546"},"severity":"advisory","ref_index":23,"audited_at":"2026-08-01T08:29:19.729948Z","event_type":"pith.integrity.v1","detected_doi":"10.18653/v1/2023.acl-long.546","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"15a4aae4094b9643d40608564b7367fd09e6df903c13bad9513e18b94dd9b9e6","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":15477,"payload_sha256":"5eea39d393a35463fdf7f2d5e2c049b1a691ea669b21ae8978e7399fe8f21ccf","signature_b64":"3EX2a8PtBk0A0RH8liy0qUvlz/9Hnk6qTicW0GgmwwicsT7GhgiDdy9kdSJIB2Csc1izy3Eqn17DsxIZ7yCxBA==","signing_key_id":"pith-v1-2026-05"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-01T08:33:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s5eTi0HU5xGP1PszYStbpsv4s/OvinsNgXzQ6IB/28AUzZT7FPJQpZMN6vTLQvMwOj3vXNVWNyl1oR5NtcLmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T17:05:41.039687Z"},"content_sha256":"f1a99d635d44b744e17f62f282db6281322d617be17ea11305a7af18426fd6bb","schema_version":"1.0","event_id":"sha256:f1a99d635d44b744e17f62f282db6281322d617be17ea11305a7af18426fd6bb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YJESQQA6NOERO6OVGNNAQKLULO/bundle.json","state_url":"https://pith.science/pith/YJESQQA6NOERO6OVGNNAQKLULO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YJESQQA6NOERO6OVGNNAQKLULO/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":"2026-08-14T17:05:41Z","links":{"resolver":"https://pith.science/pith/YJESQQA6NOERO6OVGNNAQKLULO","bundle":"https://pith.science/pith/YJESQQA6NOERO6OVGNNAQKLULO/bundle.json","state":"https://pith.science/pith/YJESQQA6NOERO6OVGNNAQKLULO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YJESQQA6NOERO6OVGNNAQKLULO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YJESQQA6NOERO6OVGNNAQKLULO","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"22865deda6c963c735145918ac37dc072b81854de1c1d498ca22a4a51bc5798a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T10:37:01Z","title_canon_sha256":"dc972ca3a393d81768ea5179585b443884a76fbf6eb60d9a8f6e871c64af0159"},"schema_version":"1.0","source":{"id":"2607.21155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.21155","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"arxiv_version","alias_value":"2607.21155v1","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.21155","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"pith_short_12","alias_value":"YJESQQA6NOER","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"pith_short_16","alias_value":"YJESQQA6NOERO6OV","created_at":"2026-07-24T01:23:56Z"},{"alias_kind":"pith_short_8","alias_value":"YJESQQA6","created_at":"2026-07-24T01:23:56Z"}],"graph_snapshots":[{"event_id":"sha256:f2725667c8261c891fbd24f5678864c9542cd2c7bafb2eefa7c38329ca6a8185","target":"graph","created_at":"2026-07-24T01:23:56Z","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/2607.21155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-Intensive Visual Question Answering (KI-VQA) benchmarks evaluate Vision-Language Models (VLMs) as multimodal knowledge assistants by requiring external information beyond a provided image to answer questions. KI-VQA involves multiple sub-problems -referring expression understanding, visual grounding, object recognition, knowledge retrieval, and reasoning-yet existing benchmarks typically report only end-task accuracy, obscuring where failures arise. To analyze the full KI-VQA pipeline, we introduce CRAG-MM-Diagnostics, a diagnostic benchmark with stage-wise data annotations that isol","authors_text":"Benno Krojer, Hanseok Oh, Hyunji Lee, Parishad BehnamGhader, Paul Liang, Siva Reddy, Verna Dankers","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T10:37:01Z","title":"CRAG-MM-Diagnostics: Enabling Stage-Wise Analysis of Knowledge-Intensive VQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.21155","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:ccd6bb5dac63194611a5bc933b99fdc71c24b111228ddcaadd9cbb0388382302","target":"record","created_at":"2026-07-24T01:23:56Z","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":"22865deda6c963c735145918ac37dc072b81854de1c1d498ca22a4a51bc5798a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-23T10:37:01Z","title_canon_sha256":"dc972ca3a393d81768ea5179585b443884a76fbf6eb60d9a8f6e871c64af0159"},"schema_version":"1.0","source":{"id":"2607.21155","kind":"arxiv","version":1}},"canonical_sha256":"c24928401e6b891779d5335a0829745b9b0da3534867e0357d27e51d415f3d17","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c24928401e6b891779d5335a0829745b9b0da3534867e0357d27e51d415f3d17","first_computed_at":"2026-07-24T01:23:56.030754Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T01:23:56.030754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nYUteSRDfJdjf4Y7aMwOTkCtIBgZSWHFekwj8ZtZTHHqIsHbakI91l3iOu4tn39KkHCmZLIOsJGOvhkvUU2BAg==","signature_status":"signed_v1","signed_at":"2026-07-24T01:23:56.031609Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.21155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccd6bb5dac63194611a5bc933b99fdc71c24b111228ddcaadd9cbb0388382302","sha256:f2725667c8261c891fbd24f5678864c9542cd2c7bafb2eefa7c38329ca6a8185","sha256:f1a99d635d44b744e17f62f282db6281322d617be17ea11305a7af18426fd6bb"],"state_sha256":"f530d68305494412978baf321e3173a53ec2843ea9d1e8a2c5c768fd3cf2c0bb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BoY9pmvfYvYhr5KaSKEF8gh60umTBxpZ/lWosyelA9fLIrdrAuQxbXrK+reqPbb2798Y9UTbGk+y4Osmoa+4Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T17:05:41.043898Z","bundle_sha256":"b1256d0d92c3783bcde63581b683e0ce58d3c593a1042b2034821ab3e4a0c17c"}}