{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AXPVJ57AYKDACPUOVPEHWCDZST","short_pith_number":"pith:AXPVJ57A","schema_version":"1.0","canonical_sha256":"05df54f7e0c286013e8eabc87b087994cd6a4f61fc7a3406a9095efedb508dc8","source":{"kind":"arxiv","id":"2502.02028","version":2},"attestation_state":"computed","paper":{"title":"Fine-tuning Language Models for Recipe Generation: A Comparative Analysis and Benchmark Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anneketh Vij, Ayan Bhowmick, Changhao Liu, Edward Shi, Rahul Anil Nair, Theodore Eugene Ho","submitted_at":"2025-02-04T05:25:01Z","abstract_excerpt":"This research presents an exploration and study of the recipe generation task by fine-tuning various very small language models, with a focus on developing robust evaluation metrics and comparing across different language models the open-ended task of recipe generation. This study presents extensive experiments with multiple model architectures, ranging from T5-small (Raffel et al., 2023) and SmolLM-135M(Allal et al., 2024) to Phi-2 (Research, 2023), implementing both traditional NLP metrics and custom domain-specific evaluation metrics. Our novel evaluation framework incorporates recipe-speci"},"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":"2502.02028","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-04T05:25:01Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"12ceb383db180d28cdd5a3fa34af70dfff07109cc47c479093fb2c0745f94d1c","abstract_canon_sha256":"63970f95a5f4f6d8157c8a54e18ad60f815bbb7cc53776447008bd23c0fd245e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:14:50.524763Z","signature_b64":"t94IT6A6tljePivEwN9rf7yiKVuDBVS7r2e00PN+MqLEOF7v3i2B20gCG8+r/bLQFv0BUDcCwp71fZKmNyQMBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"05df54f7e0c286013e8eabc87b087994cd6a4f61fc7a3406a9095efedb508dc8","last_reissued_at":"2026-07-05T10:14:50.524256Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:14:50.524256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fine-tuning Language Models for Recipe Generation: A Comparative Analysis and Benchmark Study","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anneketh Vij, Ayan Bhowmick, Changhao Liu, Edward Shi, Rahul Anil Nair, Theodore Eugene Ho","submitted_at":"2025-02-04T05:25:01Z","abstract_excerpt":"This research presents an exploration and study of the recipe generation task by fine-tuning various very small language models, with a focus on developing robust evaluation metrics and comparing across different language models the open-ended task of recipe generation. This study presents extensive experiments with multiple model architectures, ranging from T5-small (Raffel et al., 2023) and SmolLM-135M(Allal et al., 2024) to Phi-2 (Research, 2023), implementing both traditional NLP metrics and custom domain-specific evaluation metrics. Our novel evaluation framework incorporates recipe-speci"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.02028","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/2502.02028/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":"2502.02028","created_at":"2026-07-05T10:14:50.524319+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.02028v2","created_at":"2026-07-05T10:14:50.524319+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.02028","created_at":"2026-07-05T10:14:50.524319+00:00"},{"alias_kind":"pith_short_12","alias_value":"AXPVJ57AYKDA","created_at":"2026-07-05T10:14:50.524319+00:00"},{"alias_kind":"pith_short_16","alias_value":"AXPVJ57AYKDACPUO","created_at":"2026-07-05T10:14:50.524319+00:00"},{"alias_kind":"pith_short_8","alias_value":"AXPVJ57A","created_at":"2026-07-05T10:14:50.524319+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.14718","citing_title":"The Digital Sous Chef -- A Comparative Study on Fine-Tuning Language Models for Recipe Generation","ref_index":6008,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AXPVJ57AYKDACPUOVPEHWCDZST","json":"https://pith.science/pith/AXPVJ57AYKDACPUOVPEHWCDZST.json","graph_json":"https://pith.science/api/pith-number/AXPVJ57AYKDACPUOVPEHWCDZST/graph.json","events_json":"https://pith.science/api/pith-number/AXPVJ57AYKDACPUOVPEHWCDZST/events.json","paper":"https://pith.science/paper/AXPVJ57A"},"agent_actions":{"view_html":"https://pith.science/pith/AXPVJ57AYKDACPUOVPEHWCDZST","download_json":"https://pith.science/pith/AXPVJ57AYKDACPUOVPEHWCDZST.json","view_paper":"https://pith.science/paper/AXPVJ57A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.02028&json=true","fetch_graph":"https://pith.science/api/pith-number/AXPVJ57AYKDACPUOVPEHWCDZST/graph.json","fetch_events":"https://pith.science/api/pith-number/AXPVJ57AYKDACPUOVPEHWCDZST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AXPVJ57AYKDACPUOVPEHWCDZST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AXPVJ57AYKDACPUOVPEHWCDZST/action/storage_attestation","attest_author":"https://pith.science/pith/AXPVJ57AYKDACPUOVPEHWCDZST/action/author_attestation","sign_citation":"https://pith.science/pith/AXPVJ57AYKDACPUOVPEHWCDZST/action/citation_signature","submit_replication":"https://pith.science/pith/AXPVJ57AYKDACPUOVPEHWCDZST/action/replication_record"}},"created_at":"2026-07-05T10:14:50.524319+00:00","updated_at":"2026-07-05T10:14:50.524319+00:00"}