{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:XVHEU2CPO774PVYMHEOLAEDG3X","short_pith_number":"pith:XVHEU2CP","canonical_record":{"source":{"id":"2506.05440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T12:43:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cb07904c848930aa0b93dd6a26f6bb1b3220c6145b70efef94172e3b2877cce0","abstract_canon_sha256":"7643541275a28b56649397c465c39c485d21143caee9c4df4d84bf9b849d8201"},"schema_version":"1.0"},"canonical_sha256":"bd4e4a684f77ffc7d70c391cb01066ddc0cd002bda72b2190455a2c55180ba16","source":{"kind":"arxiv","id":"2506.05440","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05440","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05440v1","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05440","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"XVHEU2CPO774","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"XVHEU2CPO774PVYM","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"XVHEU2CP","created_at":"2026-07-05T11:17:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:XVHEU2CPO774PVYMHEOLAEDG3X","target":"record","payload":{"canonical_record":{"source":{"id":"2506.05440","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T12:43:10Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"cb07904c848930aa0b93dd6a26f6bb1b3220c6145b70efef94172e3b2877cce0","abstract_canon_sha256":"7643541275a28b56649397c465c39c485d21143caee9c4df4d84bf9b849d8201"},"schema_version":"1.0"},"canonical_sha256":"bd4e4a684f77ffc7d70c391cb01066ddc0cd002bda72b2190455a2c55180ba16","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:02.743626Z","signature_b64":"6k3gRkZDu9B1Xq5e9SAX6Up6RK0kxTlqnKTEqo7W6TOdF8IQw5ISPFyhISz0L98SWP8cBmNLyAaYBaQxbyKzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd4e4a684f77ffc7d70c391cb01066ddc0cd002bda72b2190455a2c55180ba16","last_reissued_at":"2026-07-05T11:17:02.743115Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:02.743115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.05440","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":"2026-07-05T11:17:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LIq15S+IsFuKFQr+Ygnx1Aq5iw6BIykpzzD172EO7ejq17PeZijsU9dz40GwmSaBeC1E4n4/b3t2YiH99JfECQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:17:37.651845Z"},"content_sha256":"36830193b100645284c9e4a3e847e49e631bfae918b4e351439ec3e8cfa11995","schema_version":"1.0","event_id":"sha256:36830193b100645284c9e4a3e847e49e631bfae918b4e351439ec3e8cfa11995"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:XVHEU2CPO774PVYMHEOLAEDG3X","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Hugues Ali Mehenni, Ludovic Arnould, Salim Khazem","submitted_at":"2025-06-05T12:43:10Z","abstract_excerpt":"Visual Language Models (VLMs) are now sufficiently advanced to support a broad range of applications, including answering complex visual questions, and are increasingly expected to interact with images in varied ways. To evaluate them, current benchmarks often focus on specific domains (e.g., reading charts), constructing datasets of annotated real images paired with pre-defined Multiple Choice Questions (MCQs) to report aggregate accuracy scores. However, such benchmarks entail high annotation costs, risk information leakage, and do not clarify whether failures stem from limitations in visual"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05440","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/2506.05440/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":"2026-07-05T11:17:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4qnoXoZ3xxcKHeWPAKzXU82gDKTaTCA4VjTrBgiIhB2V/OAE0K8wuYOFskBWEhISJ1aZ4O3UTEI8a56qR9sAAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T00:17:37.652371Z"},"content_sha256":"480b37e460263f3286b07b19636007ea7d7274a966bc425f6edb9e1568908208","schema_version":"1.0","event_id":"sha256:480b37e460263f3286b07b19636007ea7d7274a966bc425f6edb9e1568908208"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XVHEU2CPO774PVYMHEOLAEDG3X/bundle.json","state_url":"https://pith.science/pith/XVHEU2CPO774PVYMHEOLAEDG3X/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XVHEU2CPO774PVYMHEOLAEDG3X/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":"2026-08-09T00:17:37Z","links":{"resolver":"https://pith.science/pith/XVHEU2CPO774PVYMHEOLAEDG3X","bundle":"https://pith.science/pith/XVHEU2CPO774PVYMHEOLAEDG3X/bundle.json","state":"https://pith.science/pith/XVHEU2CPO774PVYMHEOLAEDG3X/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XVHEU2CPO774PVYMHEOLAEDG3X/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XVHEU2CPO774PVYMHEOLAEDG3X","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":"7643541275a28b56649397c465c39c485d21143caee9c4df4d84bf9b849d8201","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T12:43:10Z","title_canon_sha256":"cb07904c848930aa0b93dd6a26f6bb1b3220c6145b70efef94172e3b2877cce0"},"schema_version":"1.0","source":{"id":"2506.05440","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05440","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05440v1","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05440","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_12","alias_value":"XVHEU2CPO774","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_16","alias_value":"XVHEU2CPO774PVYM","created_at":"2026-07-05T11:17:02Z"},{"alias_kind":"pith_short_8","alias_value":"XVHEU2CP","created_at":"2026-07-05T11:17:02Z"}],"graph_snapshots":[{"event_id":"sha256:480b37e460263f3286b07b19636007ea7d7274a966bc425f6edb9e1568908208","target":"graph","created_at":"2026-07-05T11:17:02Z","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/2506.05440/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual Language Models (VLMs) are now sufficiently advanced to support a broad range of applications, including answering complex visual questions, and are increasingly expected to interact with images in varied ways. To evaluate them, current benchmarks often focus on specific domains (e.g., reading charts), constructing datasets of annotated real images paired with pre-defined Multiple Choice Questions (MCQs) to report aggregate accuracy scores. However, such benchmarks entail high annotation costs, risk information leakage, and do not clarify whether failures stem from limitations in visual","authors_text":"Hugues Ali Mehenni, Ludovic Arnould, Salim Khazem","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T12:43:10Z","title":"BYO-Eval: Build Your Own Dataset for Fine-Grained Visual Assessment of Multimodal Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05440","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":"sha256:36830193b100645284c9e4a3e847e49e631bfae918b4e351439ec3e8cfa11995","target":"record","created_at":"2026-07-05T11:17:02Z","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":"7643541275a28b56649397c465c39c485d21143caee9c4df4d84bf9b849d8201","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T12:43:10Z","title_canon_sha256":"cb07904c848930aa0b93dd6a26f6bb1b3220c6145b70efef94172e3b2877cce0"},"schema_version":"1.0","source":{"id":"2506.05440","kind":"arxiv","version":1}},"canonical_sha256":"bd4e4a684f77ffc7d70c391cb01066ddc0cd002bda72b2190455a2c55180ba16","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd4e4a684f77ffc7d70c391cb01066ddc0cd002bda72b2190455a2c55180ba16","first_computed_at":"2026-07-05T11:17:02.743115Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:17:02.743115Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6k3gRkZDu9B1Xq5e9SAX6Up6RK0kxTlqnKTEqo7W6TOdF8IQw5ISPFyhISz0L98SWP8cBmNLyAaYBaQxbyKzDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:17:02.743626Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05440","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:36830193b100645284c9e4a3e847e49e631bfae918b4e351439ec3e8cfa11995","sha256:480b37e460263f3286b07b19636007ea7d7274a966bc425f6edb9e1568908208"],"state_sha256":"840a56f059b6b1256d4a4eb97ecf5dba931fc93087d9790949f6c4fbc2897406"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JCkJuPTfoyichsWgLFiJjnrE9P+x2tY7ABE1iKuoDQ1WXAkfMkGafEoBt76/xCm3MNZ7dzwshlIEVm9U/Fu0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T00:17:37.656337Z","bundle_sha256":"dd9cd66acf572a796a3a19e998f561b3e26ecd72619023af06887a31ce038d56"}}