{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:MKZN3CNFRGJRFZVKCDTNF3XNTX","short_pith_number":"pith:MKZN3CNF","schema_version":"1.0","canonical_sha256":"62b2dd89a5899312e6aa10e6d2eeed9ddd617edc5d42742db04a7d2187a281bf","source":{"kind":"arxiv","id":"2212.10505","version":2},"attestation_state":"computed","paper":{"title":"DePlot: One-shot visual language reasoning by plot-to-table translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chenxi Pang, Fangyu Liu, Francesco Piccinno, Julian Martin Eisenschlos, Kenton Lee, Mandar Joshi, Nigel Collier, Syrine Krichene, Wenhu Chen, Yasemin Altun","submitted_at":"2022-12-20T18:20:50Z","abstract_excerpt":"Visual language such as charts and plots is ubiquitous in the human world. Comprehending plots and charts requires strong reasoning skills. Prior state-of-the-art (SOTA) models require at least tens of thousands of training examples and their reasoning capabilities are still much limited, especially on complex human-written queries. This paper presents the first one-shot solution to visual language reasoning. We decompose the challenge of visual language reasoning into two steps: (1) plot-to-text translation, and (2) reasoning over the translated text. The key in this method is a modality conv"},"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":"2212.10505","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-12-20T18:20:50Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"431dd59f8ebb71ea6470ae62aceaecb548307dcf0f65961b8493a346456c4451","abstract_canon_sha256":"9e15915cc73151408e95ac0679a1b811d0e1c1b05e775d0dd5e9146ec142660c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:18.587931Z","signature_b64":"Ezuuxx2E9JTY7W3pUqj2pPMttpUpKTBZAtMSG3P37cQbk41/fL2J2gNgFIJAxYzMwQXUnqW9762qdyDuytluDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62b2dd89a5899312e6aa10e6d2eeed9ddd617edc5d42742db04a7d2187a281bf","last_reissued_at":"2026-07-05T06:13:18.587437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:18.587437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DePlot: One-shot visual language reasoning by plot-to-table translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Chenxi Pang, Fangyu Liu, Francesco Piccinno, Julian Martin Eisenschlos, Kenton Lee, Mandar Joshi, Nigel Collier, Syrine Krichene, Wenhu Chen, Yasemin Altun","submitted_at":"2022-12-20T18:20:50Z","abstract_excerpt":"Visual language such as charts and plots is ubiquitous in the human world. Comprehending plots and charts requires strong reasoning skills. Prior state-of-the-art (SOTA) models require at least tens of thousands of training examples and their reasoning capabilities are still much limited, especially on complex human-written queries. This paper presents the first one-shot solution to visual language reasoning. We decompose the challenge of visual language reasoning into two steps: (1) plot-to-text translation, and (2) reasoning over the translated text. The key in this method is a modality conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.10505","kind":"arxiv","version":2},"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/2212.10505/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":"2212.10505","created_at":"2026-07-05T06:13:18.587495+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.10505v2","created_at":"2026-07-05T06:13:18.587495+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.10505","created_at":"2026-07-05T06:13:18.587495+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKZN3CNFRGJR","created_at":"2026-07-05T06:13:18.587495+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKZN3CNFRGJRFZVK","created_at":"2026-07-05T06:13:18.587495+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKZN3CNF","created_at":"2026-07-05T06:13:18.587495+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03264","citing_title":"PaddleOCR-VL-1.6: Expanding the Frontier of Document Parsing with Under-Optimized Region Refinement and Progressive Post-Training","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29808","citing_title":"Making Multimodal LLMs Reliable Chart Data Extractors: A Benchmark and Training Framework","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2409.01704","citing_title":"General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2305.18565","citing_title":"PaLI-X: On Scaling up a Multilingual Vision and Language Model","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2305.07895","citing_title":"OCRBench: On the Hidden Mystery of OCR in Large Multimodal Models","ref_index":120,"is_internal_anchor":false},{"citing_arxiv_id":"2602.13232","citing_title":"PlotChain: Deterministic Checkpointed Evaluation of Multimodal LLMs on Engineering Plot Reading","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2603.24326","citing_title":"Boosting Document Parsing Efficiency and Performance with Coarse-to-Fine Visual Processing","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MKZN3CNFRGJRFZVKCDTNF3XNTX","json":"https://pith.science/pith/MKZN3CNFRGJRFZVKCDTNF3XNTX.json","graph_json":"https://pith.science/api/pith-number/MKZN3CNFRGJRFZVKCDTNF3XNTX/graph.json","events_json":"https://pith.science/api/pith-number/MKZN3CNFRGJRFZVKCDTNF3XNTX/events.json","paper":"https://pith.science/paper/MKZN3CNF"},"agent_actions":{"view_html":"https://pith.science/pith/MKZN3CNFRGJRFZVKCDTNF3XNTX","download_json":"https://pith.science/pith/MKZN3CNFRGJRFZVKCDTNF3XNTX.json","view_paper":"https://pith.science/paper/MKZN3CNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.10505&json=true","fetch_graph":"https://pith.science/api/pith-number/MKZN3CNFRGJRFZVKCDTNF3XNTX/graph.json","fetch_events":"https://pith.science/api/pith-number/MKZN3CNFRGJRFZVKCDTNF3XNTX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKZN3CNFRGJRFZVKCDTNF3XNTX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKZN3CNFRGJRFZVKCDTNF3XNTX/action/storage_attestation","attest_author":"https://pith.science/pith/MKZN3CNFRGJRFZVKCDTNF3XNTX/action/author_attestation","sign_citation":"https://pith.science/pith/MKZN3CNFRGJRFZVKCDTNF3XNTX/action/citation_signature","submit_replication":"https://pith.science/pith/MKZN3CNFRGJRFZVKCDTNF3XNTX/action/replication_record"}},"created_at":"2026-07-05T06:13:18.587495+00:00","updated_at":"2026-07-05T06:13:18.587495+00:00"}