{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZQ53ZETLI3TH7O6W4FDROAG3AY","short_pith_number":"pith:ZQ53ZETL","schema_version":"1.0","canonical_sha256":"cc3bbc926b46e67fbbd6e1471700db062f10d115313f418d9688f71e21881a55","source":{"kind":"arxiv","id":"2506.06175","version":1},"attestation_state":"computed","paper":{"title":"Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony Rios, James Ford","submitted_at":"2025-06-06T15:39:17Z","abstract_excerpt":"Large language models can translate natural-language chart descriptions into runnable code, yet approximately 15\\% of the generated scripts still fail to execute, even after supervised fine-tuning and reinforcement learning. We investigate whether this persistent error rate stems from model limitations or from reliance on a single-prompt design. To explore this, we propose a lightweight multi-agent pipeline that separates drafting, execution, repair, and judgment, using only an off-the-shelf GPT-4o-mini model. On the \\textsc{Text2Chart31} benchmark, our system reduces execution errors to 4.5\\%"},"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":"2506.06175","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-06T15:39:17Z","cross_cats_sorted":[],"title_canon_sha256":"53b426bab9394d72f8d5f5c7058b95bfb5202d9001960ad16a0731508a639253","abstract_canon_sha256":"ebadd46e264471478ea417cb85f81c4ab8811744ae61ce2bbe9cd77c47c53814"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:17:26.930273Z","signature_b64":"zCSK9IECcfgf61ztwwXMGGn3/4NPenlR5/BZ4aX60X5CaCet2LgV7fSOSHUnH451B1oIn1d7HuNCixsNWuAiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc3bbc926b46e67fbbd6e1471700db062f10d115313f418d9688f71e21881a55","last_reissued_at":"2026-07-05T11:17:26.929287Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:17:26.929287Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Does It Run and Is That Enough? Revisiting Text-to-Chart Generation with a Multi-Agent Approach","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anthony Rios, James Ford","submitted_at":"2025-06-06T15:39:17Z","abstract_excerpt":"Large language models can translate natural-language chart descriptions into runnable code, yet approximately 15\\% of the generated scripts still fail to execute, even after supervised fine-tuning and reinforcement learning. We investigate whether this persistent error rate stems from model limitations or from reliance on a single-prompt design. To explore this, we propose a lightweight multi-agent pipeline that separates drafting, execution, repair, and judgment, using only an off-the-shelf GPT-4o-mini model. On the \\textsc{Text2Chart31} benchmark, our system reduces execution errors to 4.5\\%"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.06175","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/2506.06175/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":"2506.06175","created_at":"2026-07-05T11:17:26.929358+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.06175v1","created_at":"2026-07-05T11:17:26.929358+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.06175","created_at":"2026-07-05T11:17:26.929358+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZQ53ZETLI3TH","created_at":"2026-07-05T11:17:26.929358+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZQ53ZETLI3TH7O6W","created_at":"2026-07-05T11:17:26.929358+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZQ53ZETL","created_at":"2026-07-05T11:17:26.929358+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/ZQ53ZETLI3TH7O6W4FDROAG3AY","json":"https://pith.science/pith/ZQ53ZETLI3TH7O6W4FDROAG3AY.json","graph_json":"https://pith.science/api/pith-number/ZQ53ZETLI3TH7O6W4FDROAG3AY/graph.json","events_json":"https://pith.science/api/pith-number/ZQ53ZETLI3TH7O6W4FDROAG3AY/events.json","paper":"https://pith.science/paper/ZQ53ZETL"},"agent_actions":{"view_html":"https://pith.science/pith/ZQ53ZETLI3TH7O6W4FDROAG3AY","download_json":"https://pith.science/pith/ZQ53ZETLI3TH7O6W4FDROAG3AY.json","view_paper":"https://pith.science/paper/ZQ53ZETL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.06175&json=true","fetch_graph":"https://pith.science/api/pith-number/ZQ53ZETLI3TH7O6W4FDROAG3AY/graph.json","fetch_events":"https://pith.science/api/pith-number/ZQ53ZETLI3TH7O6W4FDROAG3AY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZQ53ZETLI3TH7O6W4FDROAG3AY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZQ53ZETLI3TH7O6W4FDROAG3AY/action/storage_attestation","attest_author":"https://pith.science/pith/ZQ53ZETLI3TH7O6W4FDROAG3AY/action/author_attestation","sign_citation":"https://pith.science/pith/ZQ53ZETLI3TH7O6W4FDROAG3AY/action/citation_signature","submit_replication":"https://pith.science/pith/ZQ53ZETLI3TH7O6W4FDROAG3AY/action/replication_record"}},"created_at":"2026-07-05T11:17:26.929358+00:00","updated_at":"2026-07-05T11:17:26.929358+00:00"}