{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:43EOY5URJSLNCNHVGCGQH7ZZF4","short_pith_number":"pith:43EOY5UR","canonical_record":{"source":{"id":"2505.19360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T23:17:32Z","cross_cats_sorted":[],"title_canon_sha256":"0bea85f4d07e05ce2ee4969b1963b487235ee083fae8f22a4fd3cf65ca7858b4","abstract_canon_sha256":"58d7c7c4d90d2b9dc98b9ecdf8502b281fb2189c09f119a80be0661c7e3a9d72"},"schema_version":"1.0"},"canonical_sha256":"e6c8ec76914c96d134f5308d03ff392f2688058e72eb50b7be4234c5fd652fda","source":{"kind":"arxiv","id":"2505.19360","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19360","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19360v1","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19360","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"43EOY5URJSLN","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"43EOY5URJSLNCNHV","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"43EOY5UR","created_at":"2026-07-05T11:09:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:43EOY5URJSLNCNHVGCGQH7ZZF4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19360","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T23:17:32Z","cross_cats_sorted":[],"title_canon_sha256":"0bea85f4d07e05ce2ee4969b1963b487235ee083fae8f22a4fd3cf65ca7858b4","abstract_canon_sha256":"58d7c7c4d90d2b9dc98b9ecdf8502b281fb2189c09f119a80be0661c7e3a9d72"},"schema_version":"1.0"},"canonical_sha256":"e6c8ec76914c96d134f5308d03ff392f2688058e72eb50b7be4234c5fd652fda","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:29.072048Z","signature_b64":"5uxEAZ0phjKGBenvUMroIKB9ruS9JmY23hTcJHURTsXSEG9DY2QoBNoEHmVw018sumDALAdrLBzWmvkHEGhwAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6c8ec76914c96d134f5308d03ff392f2688058e72eb50b7be4234c5fd652fda","last_reissued_at":"2026-07-05T11:09:29.071618Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:29.071618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19360","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":"2026-07-05T11:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TvmOEY7gJIV2PJ7Mea3Jf36MJp5xfZOdlrEWT6y31kTDy2o0PhL7z9BFeGd/qoNARC0tJNnA0glxqWet5060BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:46:49.866008Z"},"content_sha256":"af1edcfcc60c0a33f49124e98c7cd918aca7218ab348eaa6d38eedff713112fd","schema_version":"1.0","event_id":"sha256:af1edcfcc60c0a33f49124e98c7cd918aca7218ab348eaa6d38eedff713112fd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:43EOY5URJSLNCNHVGCGQH7ZZF4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChartLens: Fine-grained Visual Attribution in Charts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinesh Manocha, Franck Dernoncourt, Manan Suri, Nedim Lipka, Puneet Mathur, Ryan A. Rossi","submitted_at":"2025-05-25T23:17:32Z","abstract_excerpt":"The growing capabilities of multimodal large language models (MLLMs) have advanced tasks like chart understanding. However, these models often suffer from hallucinations, where generated text sequences conflict with the provided visual data. To address this, we introduce Post-Hoc Visual Attribution for Charts, which identifies fine-grained chart elements that validate a given chart-associated response. We propose ChartLens, a novel chart attribution algorithm that uses segmentation-based techniques to identify chart objects and employs set-of-marks prompting with MLLMs for fine-grained visual "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19360","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/2505.19360/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":"2026-07-05T11:09:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rSLUHgn8islcWIyqb1oKmyIPUWum1d4jwzGtNt2g7A4+P9yLG7ZiXLOaPBXRtGgsxCPFpXU0yldBsKJ37bH+DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T11:46:49.866890Z"},"content_sha256":"15005dc17c1b9f275f934a48b2840a65ad84d3b81edf1b2e2c27c34a86c5954f","schema_version":"1.0","event_id":"sha256:15005dc17c1b9f275f934a48b2840a65ad84d3b81edf1b2e2c27c34a86c5954f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/43EOY5URJSLNCNHVGCGQH7ZZF4/bundle.json","state_url":"https://pith.science/pith/43EOY5URJSLNCNHVGCGQH7ZZF4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/43EOY5URJSLNCNHVGCGQH7ZZF4/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":"2026-08-09T11:46:49Z","links":{"resolver":"https://pith.science/pith/43EOY5URJSLNCNHVGCGQH7ZZF4","bundle":"https://pith.science/pith/43EOY5URJSLNCNHVGCGQH7ZZF4/bundle.json","state":"https://pith.science/pith/43EOY5URJSLNCNHVGCGQH7ZZF4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/43EOY5URJSLNCNHVGCGQH7ZZF4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:43EOY5URJSLNCNHVGCGQH7ZZF4","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":"58d7c7c4d90d2b9dc98b9ecdf8502b281fb2189c09f119a80be0661c7e3a9d72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T23:17:32Z","title_canon_sha256":"0bea85f4d07e05ce2ee4969b1963b487235ee083fae8f22a4fd3cf65ca7858b4"},"schema_version":"1.0","source":{"id":"2505.19360","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19360","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19360v1","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19360","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_12","alias_value":"43EOY5URJSLN","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_16","alias_value":"43EOY5URJSLNCNHV","created_at":"2026-07-05T11:09:29Z"},{"alias_kind":"pith_short_8","alias_value":"43EOY5UR","created_at":"2026-07-05T11:09:29Z"}],"graph_snapshots":[{"event_id":"sha256:15005dc17c1b9f275f934a48b2840a65ad84d3b81edf1b2e2c27c34a86c5954f","target":"graph","created_at":"2026-07-05T11:09:29Z","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/2505.19360/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The growing capabilities of multimodal large language models (MLLMs) have advanced tasks like chart understanding. However, these models often suffer from hallucinations, where generated text sequences conflict with the provided visual data. To address this, we introduce Post-Hoc Visual Attribution for Charts, which identifies fine-grained chart elements that validate a given chart-associated response. We propose ChartLens, a novel chart attribution algorithm that uses segmentation-based techniques to identify chart objects and employs set-of-marks prompting with MLLMs for fine-grained visual ","authors_text":"Dinesh Manocha, Franck Dernoncourt, Manan Suri, Nedim Lipka, Puneet Mathur, Ryan A. Rossi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T23:17:32Z","title":"ChartLens: Fine-grained Visual Attribution in Charts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19360","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:af1edcfcc60c0a33f49124e98c7cd918aca7218ab348eaa6d38eedff713112fd","target":"record","created_at":"2026-07-05T11:09:29Z","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":"58d7c7c4d90d2b9dc98b9ecdf8502b281fb2189c09f119a80be0661c7e3a9d72","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-25T23:17:32Z","title_canon_sha256":"0bea85f4d07e05ce2ee4969b1963b487235ee083fae8f22a4fd3cf65ca7858b4"},"schema_version":"1.0","source":{"id":"2505.19360","kind":"arxiv","version":1}},"canonical_sha256":"e6c8ec76914c96d134f5308d03ff392f2688058e72eb50b7be4234c5fd652fda","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6c8ec76914c96d134f5308d03ff392f2688058e72eb50b7be4234c5fd652fda","first_computed_at":"2026-07-05T11:09:29.071618Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:09:29.071618Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5uxEAZ0phjKGBenvUMroIKB9ruS9JmY23hTcJHURTsXSEG9DY2QoBNoEHmVw018sumDALAdrLBzWmvkHEGhwAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:09:29.072048Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19360","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:af1edcfcc60c0a33f49124e98c7cd918aca7218ab348eaa6d38eedff713112fd","sha256:15005dc17c1b9f275f934a48b2840a65ad84d3b81edf1b2e2c27c34a86c5954f"],"state_sha256":"496f310e28ea15aa0bb340e7beeb3338d821300e4f05727ed7c0fccab771e029"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r5KjVaJYoGw9GSCqpcR0Hj+HTETb9aa8Tj3+nHaV+0Lb9Vhv7IkXHlhE9ULc6Bv6/0yaWkFpRvkHUNMNGnl+CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T11:46:49.875021Z","bundle_sha256":"451e24a8707e1bd2c8cf3d8c081118f563d93f3ccaa65ed7ca3736552eeec42e"}}