{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5LV6H4UTJ52HME6Q2IHXPBTS3B","short_pith_number":"pith:5LV6H4UT","schema_version":"1.0","canonical_sha256":"eaebe3f2934f747613d0d20f778672d864c35ab9c597211178b1ddfaa09e935e","source":{"kind":"arxiv","id":"2501.16524","version":1},"attestation_state":"computed","paper":{"title":"Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aravind Mysore, Atharva Naik, Carolyn Rose, Clayton Marr, Darsh Agrawal, David R Mortensen, Hong Sng, Kalvin Chang, Kexun Zhang, Nathaniel R Robinson, Rebecca Byrnes","submitted_at":"2025-01-27T21:48:39Z","abstract_excerpt":"Historical linguists have long written \"programs\" that convert reconstructed words in an ancestor language into their attested descendants via ordered string rewrite functions (called sound laws) However, writing these programs is time-consuming, motivating the development of automated Sound Law Induction (SLI) which we formulate as Programming by Examples (PBE) with Large Language Models (LLMs) in this paper. While LLMs have been effective for code generation, recent work has shown that PBE is challenging but improvable by fine-tuning, especially with training data drawn from the same distrib"},"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":"2501.16524","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T21:48:39Z","cross_cats_sorted":[],"title_canon_sha256":"ac9cbccb3c6a970e812f4adbaf83fdd39130edaac9cb2acb708f4624b41c2c05","abstract_canon_sha256":"11376e8e6213e0895066bbc7e7e0f6ba365fc4e9bbeaddfc53b31e0e68b84b4f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:14.592225Z","signature_b64":"VZa/KrSuLnciD/OQBh5UZhlszGFUBhdfJyEzfgFT9VYTfjjstAcQy6JiI7OtBmJiJw+UYN8kTI3wt2rTNnnwBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eaebe3f2934f747613d0d20f778672d864c35ab9c597211178b1ddfaa09e935e","last_reissued_at":"2026-07-05T10:06:14.591676Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:14.591676Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Programming by Examples Meets Historical Linguistics: A Large Language Model Based Approach to Sound Law Induction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aravind Mysore, Atharva Naik, Carolyn Rose, Clayton Marr, Darsh Agrawal, David R Mortensen, Hong Sng, Kalvin Chang, Kexun Zhang, Nathaniel R Robinson, Rebecca Byrnes","submitted_at":"2025-01-27T21:48:39Z","abstract_excerpt":"Historical linguists have long written \"programs\" that convert reconstructed words in an ancestor language into their attested descendants via ordered string rewrite functions (called sound laws) However, writing these programs is time-consuming, motivating the development of automated Sound Law Induction (SLI) which we formulate as Programming by Examples (PBE) with Large Language Models (LLMs) in this paper. While LLMs have been effective for code generation, recent work has shown that PBE is challenging but improvable by fine-tuning, especially with training data drawn from the same distrib"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16524","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/2501.16524/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":"2501.16524","created_at":"2026-07-05T10:06:14.591740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16524v1","created_at":"2026-07-05T10:06:14.591740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16524","created_at":"2026-07-05T10:06:14.591740+00:00"},{"alias_kind":"pith_short_12","alias_value":"5LV6H4UTJ52H","created_at":"2026-07-05T10:06:14.591740+00:00"},{"alias_kind":"pith_short_16","alias_value":"5LV6H4UTJ52HME6Q","created_at":"2026-07-05T10:06:14.591740+00:00"},{"alias_kind":"pith_short_8","alias_value":"5LV6H4UT","created_at":"2026-07-05T10:06:14.591740+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/5LV6H4UTJ52HME6Q2IHXPBTS3B","json":"https://pith.science/pith/5LV6H4UTJ52HME6Q2IHXPBTS3B.json","graph_json":"https://pith.science/api/pith-number/5LV6H4UTJ52HME6Q2IHXPBTS3B/graph.json","events_json":"https://pith.science/api/pith-number/5LV6H4UTJ52HME6Q2IHXPBTS3B/events.json","paper":"https://pith.science/paper/5LV6H4UT"},"agent_actions":{"view_html":"https://pith.science/pith/5LV6H4UTJ52HME6Q2IHXPBTS3B","download_json":"https://pith.science/pith/5LV6H4UTJ52HME6Q2IHXPBTS3B.json","view_paper":"https://pith.science/paper/5LV6H4UT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16524&json=true","fetch_graph":"https://pith.science/api/pith-number/5LV6H4UTJ52HME6Q2IHXPBTS3B/graph.json","fetch_events":"https://pith.science/api/pith-number/5LV6H4UTJ52HME6Q2IHXPBTS3B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5LV6H4UTJ52HME6Q2IHXPBTS3B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5LV6H4UTJ52HME6Q2IHXPBTS3B/action/storage_attestation","attest_author":"https://pith.science/pith/5LV6H4UTJ52HME6Q2IHXPBTS3B/action/author_attestation","sign_citation":"https://pith.science/pith/5LV6H4UTJ52HME6Q2IHXPBTS3B/action/citation_signature","submit_replication":"https://pith.science/pith/5LV6H4UTJ52HME6Q2IHXPBTS3B/action/replication_record"}},"created_at":"2026-07-05T10:06:14.591740+00:00","updated_at":"2026-07-05T10:06:14.591740+00:00"}