{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:IL4XMSSDLTKVRGVAQYAOJRWYIZ","short_pith_number":"pith:IL4XMSSD","schema_version":"1.0","canonical_sha256":"42f9764a435cd5589aa08600e4c6d8467ae5aa7cf1afde2a8fb0d11a555d5b4d","source":{"kind":"arxiv","id":"2501.04675","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhas Kumar, Archita Srivastava, Prabhakar Srinivasan, Rajesh Kumar","submitted_at":"2025-01-08T18:33:17Z","abstract_excerpt":"Chart interpretation is crucial for visual data analysis, but accurately extracting information from charts poses significant challenges for automated models. This study investigates the fine-tuning of DEPLOT, a modality conversion module that translates the image of a plot or chart to a linearized table, on a custom dataset of 50,000 bar charts. The dataset comprises simple, stacked, and grouped bar charts, targeting the unique structural features of these visualizations. The finetuned DEPLOT model is evaluated against its base version using a test set of 1,000 images and two metrics: Relativ"},"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":"2501.04675","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T18:33:17Z","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"title_canon_sha256":"6f8bb210a1db26628d6e4599454ee4806a238e7c4a71ce011b49cc5ac562852c","abstract_canon_sha256":"b243b91f18487f7e119b4e228a327926d548cdf758a378a60f7a82d62122fea9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:38.678361Z","signature_b64":"x+uKU8oP+HFk2K8j8P38Of1ZYF5ru7gBvs3x8JAg8A09n8ar1w4UBz9WsFoEg54xRtxyommWp6dq5z5zxF8+BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42f9764a435cd5589aa08600e4c6d8467ae5aa7cf1afde2a8fb0d11a555d5b4d","last_reissued_at":"2026-07-05T09:58:38.677879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:38.677879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Financial VQA in Vision Language Models using Intermediate Structured Representations","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhas Kumar, Archita Srivastava, Prabhakar Srinivasan, Rajesh Kumar","submitted_at":"2025-01-08T18:33:17Z","abstract_excerpt":"Chart interpretation is crucial for visual data analysis, but accurately extracting information from charts poses significant challenges for automated models. This study investigates the fine-tuning of DEPLOT, a modality conversion module that translates the image of a plot or chart to a linearized table, on a custom dataset of 50,000 bar charts. The dataset comprises simple, stacked, and grouped bar charts, targeting the unique structural features of these visualizations. The finetuned DEPLOT model is evaluated against its base version using a test set of 1,000 images and two metrics: Relativ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04675","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/2501.04675/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":"2501.04675","created_at":"2026-07-05T09:58:38.677938+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04675v1","created_at":"2026-07-05T09:58:38.677938+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04675","created_at":"2026-07-05T09:58:38.677938+00:00"},{"alias_kind":"pith_short_12","alias_value":"IL4XMSSDLTKV","created_at":"2026-07-05T09:58:38.677938+00:00"},{"alias_kind":"pith_short_16","alias_value":"IL4XMSSDLTKVRGVA","created_at":"2026-07-05T09:58:38.677938+00:00"},{"alias_kind":"pith_short_8","alias_value":"IL4XMSSD","created_at":"2026-07-05T09:58:38.677938+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.26462","citing_title":"A Multistage Extraction Pipeline for Long Scanned Financial Documents: An Empirical Study in Industrial KYC Workflows","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IL4XMSSDLTKVRGVAQYAOJRWYIZ","json":"https://pith.science/pith/IL4XMSSDLTKVRGVAQYAOJRWYIZ.json","graph_json":"https://pith.science/api/pith-number/IL4XMSSDLTKVRGVAQYAOJRWYIZ/graph.json","events_json":"https://pith.science/api/pith-number/IL4XMSSDLTKVRGVAQYAOJRWYIZ/events.json","paper":"https://pith.science/paper/IL4XMSSD"},"agent_actions":{"view_html":"https://pith.science/pith/IL4XMSSDLTKVRGVAQYAOJRWYIZ","download_json":"https://pith.science/pith/IL4XMSSDLTKVRGVAQYAOJRWYIZ.json","view_paper":"https://pith.science/paper/IL4XMSSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04675&json=true","fetch_graph":"https://pith.science/api/pith-number/IL4XMSSDLTKVRGVAQYAOJRWYIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/IL4XMSSDLTKVRGVAQYAOJRWYIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IL4XMSSDLTKVRGVAQYAOJRWYIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IL4XMSSDLTKVRGVAQYAOJRWYIZ/action/storage_attestation","attest_author":"https://pith.science/pith/IL4XMSSDLTKVRGVAQYAOJRWYIZ/action/author_attestation","sign_citation":"https://pith.science/pith/IL4XMSSDLTKVRGVAQYAOJRWYIZ/action/citation_signature","submit_replication":"https://pith.science/pith/IL4XMSSDLTKVRGVAQYAOJRWYIZ/action/replication_record"}},"created_at":"2026-07-05T09:58:38.677938+00:00","updated_at":"2026-07-05T09:58:38.677938+00:00"}