{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FDGUJTSXITSXSOTJ3I644ZAAWU","short_pith_number":"pith:FDGUJTSX","schema_version":"1.0","canonical_sha256":"28cd44ce5744e5793a69da3dce6400b53b2ecb2089a594e4cfff82c270c1bd38","source":{"kind":"arxiv","id":"2508.14718","version":1},"attestation_state":"computed","paper":{"title":"The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ganesh Bagler, Shubham Pundhir","submitted_at":"2025-08-20T13:53:13Z","abstract_excerpt":"We established a rigorous benchmark for text-based recipe generation, a fundamental task in natural language generation. We present a comprehensive comparative study contrasting a fine-tuned GPT-2 large (774M) model against the GPT-2 small (124M) model and traditional LSTM/RNN baselines on the 5-cuisine corpus from RecipeDB. Our key contribution is a targeted tokenization strategy that augments the vocabulary with 23 common fraction tokens and custom structural markers. This approach addresses a critical limitation of generic tokenizers by preserving essential recipe structures and precise num"},"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":"2508.14718","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-20T13:53:13Z","cross_cats_sorted":[],"title_canon_sha256":"2ced4d0fb1ca018191a42a9627c575045b1480a029b53d6fbfc6f6d2f76419ae","abstract_canon_sha256":"6c662f911424e0254e37fec6535d640170e36af979dfc883250da83cd29b0f07"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:37.389747Z","signature_b64":"dqGrc1btNa1LJ3jmI4I25e0zw3jF3ztGCGzpFIxHTllfNHUrbOJ15rpkNfk0eDhgPmo0/XlrWozp4jRyf2cHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28cd44ce5744e5793a69da3dce6400b53b2ecb2089a594e4cfff82c270c1bd38","last_reissued_at":"2026-07-05T11:56:37.389284Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:37.389284Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ganesh Bagler, Shubham Pundhir","submitted_at":"2025-08-20T13:53:13Z","abstract_excerpt":"We established a rigorous benchmark for text-based recipe generation, a fundamental task in natural language generation. We present a comprehensive comparative study contrasting a fine-tuned GPT-2 large (774M) model against the GPT-2 small (124M) model and traditional LSTM/RNN baselines on the 5-cuisine corpus from RecipeDB. Our key contribution is a targeted tokenization strategy that augments the vocabulary with 23 common fraction tokens and custom structural markers. This approach addresses a critical limitation of generic tokenizers by preserving essential recipe structures and precise num"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.14718","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/2508.14718/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":"2508.14718","created_at":"2026-07-05T11:56:37.389354+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.14718v1","created_at":"2026-07-05T11:56:37.389354+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.14718","created_at":"2026-07-05T11:56:37.389354+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDGUJTSXITSX","created_at":"2026-07-05T11:56:37.389354+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDGUJTSXITSXSOTJ","created_at":"2026-07-05T11:56:37.389354+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDGUJTSX","created_at":"2026-07-05T11:56:37.389354+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/FDGUJTSXITSXSOTJ3I644ZAAWU","json":"https://pith.science/pith/FDGUJTSXITSXSOTJ3I644ZAAWU.json","graph_json":"https://pith.science/api/pith-number/FDGUJTSXITSXSOTJ3I644ZAAWU/graph.json","events_json":"https://pith.science/api/pith-number/FDGUJTSXITSXSOTJ3I644ZAAWU/events.json","paper":"https://pith.science/paper/FDGUJTSX"},"agent_actions":{"view_html":"https://pith.science/pith/FDGUJTSXITSXSOTJ3I644ZAAWU","download_json":"https://pith.science/pith/FDGUJTSXITSXSOTJ3I644ZAAWU.json","view_paper":"https://pith.science/paper/FDGUJTSX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.14718&json=true","fetch_graph":"https://pith.science/api/pith-number/FDGUJTSXITSXSOTJ3I644ZAAWU/graph.json","fetch_events":"https://pith.science/api/pith-number/FDGUJTSXITSXSOTJ3I644ZAAWU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDGUJTSXITSXSOTJ3I644ZAAWU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDGUJTSXITSXSOTJ3I644ZAAWU/action/storage_attestation","attest_author":"https://pith.science/pith/FDGUJTSXITSXSOTJ3I644ZAAWU/action/author_attestation","sign_citation":"https://pith.science/pith/FDGUJTSXITSXSOTJ3I644ZAAWU/action/citation_signature","submit_replication":"https://pith.science/pith/FDGUJTSXITSXSOTJ3I644ZAAWU/action/replication_record"}},"created_at":"2026-07-05T11:56:37.389354+00:00","updated_at":"2026-07-05T11:56:37.389354+00:00"}