{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:4XN2YQWHY5TTO5MGZ4ISSNUWQR","short_pith_number":"pith:4XN2YQWH","schema_version":"1.0","canonical_sha256":"e5dbac42c7c767377586cf112936968447181a7842239eea9ef658b36fe60400","source":{"kind":"arxiv","id":"2607.14709","version":1},"attestation_state":"computed","paper":{"title":"Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elana Chen, Erica Zhao, Yun Dong","submitted_at":"2026-07-16T08:18:55Z","abstract_excerpt":"Financial question answering over hybrid tabular and textual data may require multi-source reasoning and precise numerical computation. While large language models (LLMs) can generate intermediate reasoning steps, natural-language rationales remain prone to arithmetic errors, making them an unreliable supervision source for distillation. Building on programmatic distillation, we develop an approach that transfers reliable numerical reasoning from a large teacher model to a compact student using execution-verified Python programs instead of free-form textual rationales. It leverages gold deriva"},"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":"2607.14709","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-16T08:18:55Z","cross_cats_sorted":[],"title_canon_sha256":"fc1bf7bef694906175fef56d8f43f6fec52741d63e39e90d23f90639cccff967","abstract_canon_sha256":"6bb5edbe3a32d74582c7587c42952abc06137e534b2408dce6af0b41949eb81f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:21:26.852648Z","signature_b64":"Rn+EXg1s+44+8ZslRXyyJUYSpAubKxbCASVfiLsZffGvlCfKcRmQfyFP2qK3XQo6UAZOgTRq+NKyghpwmCFXBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e5dbac42c7c767377586cf112936968447181a7842239eea9ef658b36fe60400","last_reissued_at":"2026-07-17T01:21:26.851797Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:21:26.851797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gold-Guided Programmatic Distillation for Financial Reasoning over Hybrid Tables and Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elana Chen, Erica Zhao, Yun Dong","submitted_at":"2026-07-16T08:18:55Z","abstract_excerpt":"Financial question answering over hybrid tabular and textual data may require multi-source reasoning and precise numerical computation. While large language models (LLMs) can generate intermediate reasoning steps, natural-language rationales remain prone to arithmetic errors, making them an unreliable supervision source for distillation. Building on programmatic distillation, we develop an approach that transfers reliable numerical reasoning from a large teacher model to a compact student using execution-verified Python programs instead of free-form textual rationales. It leverages gold deriva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14709","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/2607.14709/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":"2607.14709","created_at":"2026-07-17T01:21:26.852223+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14709v1","created_at":"2026-07-17T01:21:26.852223+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14709","created_at":"2026-07-17T01:21:26.852223+00:00"},{"alias_kind":"pith_short_12","alias_value":"4XN2YQWHY5TT","created_at":"2026-07-17T01:21:26.852223+00:00"},{"alias_kind":"pith_short_16","alias_value":"4XN2YQWHY5TTO5MG","created_at":"2026-07-17T01:21:26.852223+00:00"},{"alias_kind":"pith_short_8","alias_value":"4XN2YQWH","created_at":"2026-07-17T01:21:26.852223+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/4XN2YQWHY5TTO5MGZ4ISSNUWQR","json":"https://pith.science/pith/4XN2YQWHY5TTO5MGZ4ISSNUWQR.json","graph_json":"https://pith.science/api/pith-number/4XN2YQWHY5TTO5MGZ4ISSNUWQR/graph.json","events_json":"https://pith.science/api/pith-number/4XN2YQWHY5TTO5MGZ4ISSNUWQR/events.json","paper":"https://pith.science/paper/4XN2YQWH"},"agent_actions":{"view_html":"https://pith.science/pith/4XN2YQWHY5TTO5MGZ4ISSNUWQR","download_json":"https://pith.science/pith/4XN2YQWHY5TTO5MGZ4ISSNUWQR.json","view_paper":"https://pith.science/paper/4XN2YQWH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14709&json=true","fetch_graph":"https://pith.science/api/pith-number/4XN2YQWHY5TTO5MGZ4ISSNUWQR/graph.json","fetch_events":"https://pith.science/api/pith-number/4XN2YQWHY5TTO5MGZ4ISSNUWQR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4XN2YQWHY5TTO5MGZ4ISSNUWQR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4XN2YQWHY5TTO5MGZ4ISSNUWQR/action/storage_attestation","attest_author":"https://pith.science/pith/4XN2YQWHY5TTO5MGZ4ISSNUWQR/action/author_attestation","sign_citation":"https://pith.science/pith/4XN2YQWHY5TTO5MGZ4ISSNUWQR/action/citation_signature","submit_replication":"https://pith.science/pith/4XN2YQWHY5TTO5MGZ4ISSNUWQR/action/replication_record"}},"created_at":"2026-07-17T01:21:26.852223+00:00","updated_at":"2026-07-17T01:21:26.852223+00:00"}