{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y7FZ4KGQ7FQAYO5WGG7UG5DE5M","short_pith_number":"pith:Y7FZ4KGQ","schema_version":"1.0","canonical_sha256":"c7cb9e28d0f9600c3bb631bf437464eb2abc7150294a304409803617c2b95338","source":{"kind":"arxiv","id":"2605.27298","version":1},"attestation_state":"computed","paper":{"title":"Self-Ensembling Vision-Language Models for Chart Data Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maimuna S. Majumder, Qianyi Wang, Thomas Berkane","submitted_at":"2026-05-26T17:10:51Z","abstract_excerpt":"Charts effectively convey quantitative information, but the underlying data are often locked in image form, hindering reuse and analysis. Manually digitizing charts is time-consuming and error-prone, motivating automatic chart-to-table extraction. Recent approaches use specialized vision-language models (VLMs), yet performance still lags on charts with many datapoints or substantial stylistic variation. We propose a VLM self-ensembling method that repeatedly samples multiple tabular outputs from the same VLM for a fixed chart image and aggregates them at the level of individual table cells. We"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.27298","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T17:10:51Z","cross_cats_sorted":[],"title_canon_sha256":"94048a2a04892b2e2fb352e092704c8dae573a3aad79917696c9506bfbe3f4e9","abstract_canon_sha256":"a804c9260095d77a5e2c658d8833887fa51d06165f3b0ffd17b305dc2b752b8c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:17.108910Z","signature_b64":"o+W381C3nHx0uE0zzcEZXHVOtpQ73ipsaLiq8QbGHg6Gj4fZVYD1pS6ZZUaviPwmmTo7D082vjpgrIefCvjpCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7cb9e28d0f9600c3bb631bf437464eb2abc7150294a304409803617c2b95338","last_reissued_at":"2026-05-27T02:06:17.108230Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:17.108230Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Self-Ensembling Vision-Language Models for Chart Data Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Maimuna S. Majumder, Qianyi Wang, Thomas Berkane","submitted_at":"2026-05-26T17:10:51Z","abstract_excerpt":"Charts effectively convey quantitative information, but the underlying data are often locked in image form, hindering reuse and analysis. Manually digitizing charts is time-consuming and error-prone, motivating automatic chart-to-table extraction. Recent approaches use specialized vision-language models (VLMs), yet performance still lags on charts with many datapoints or substantial stylistic variation. We propose a VLM self-ensembling method that repeatedly samples multiple tabular outputs from the same VLM for a fixed chart image and aggregates them at the level of individual table cells. We"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27298","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/2605.27298/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.27298","created_at":"2026-05-27T02:06:17.108360+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27298v1","created_at":"2026-05-27T02:06:17.108360+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27298","created_at":"2026-05-27T02:06:17.108360+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y7FZ4KGQ7FQA","created_at":"2026-05-27T02:06:17.108360+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y7FZ4KGQ7FQAYO5W","created_at":"2026-05-27T02:06:17.108360+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y7FZ4KGQ","created_at":"2026-05-27T02:06:17.108360+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M","json":"https://pith.science/pith/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M.json","graph_json":"https://pith.science/api/pith-number/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M/graph.json","events_json":"https://pith.science/api/pith-number/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M/events.json","paper":"https://pith.science/paper/Y7FZ4KGQ"},"agent_actions":{"view_html":"https://pith.science/pith/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M","download_json":"https://pith.science/pith/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M.json","view_paper":"https://pith.science/paper/Y7FZ4KGQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27298&json=true","fetch_graph":"https://pith.science/api/pith-number/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M/graph.json","fetch_events":"https://pith.science/api/pith-number/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M/action/storage_attestation","attest_author":"https://pith.science/pith/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M/action/author_attestation","sign_citation":"https://pith.science/pith/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M/action/citation_signature","submit_replication":"https://pith.science/pith/Y7FZ4KGQ7FQAYO5WGG7UG5DE5M/action/replication_record"}},"created_at":"2026-05-27T02:06:17.108360+00:00","updated_at":"2026-05-27T02:06:17.108360+00:00"}