{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZHGNVQPRMIVU6VXFDYHAIPMWK2","short_pith_number":"pith:ZHGNVQPR","schema_version":"1.0","canonical_sha256":"c9ccdac1f1622b4f56e51e0e043d96568727985f791113e89468d8704eee5d58","source":{"kind":"arxiv","id":"2603.01712","version":2},"attestation_state":"computed","paper":{"title":"FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jiang Bian, Qizheng Li, Weiqing Liu, Xiao Yang, Xu Yang, Yifei Zhang, Zhuo Wang","submitted_at":"2026-03-02T10:37:11Z","abstract_excerpt":"Fine-tuning large language models for vertical domains remains labor-intensive, requiring practitioners to curate data, configure training, and iteratively diagnose model behavior. Despite growing interest in autonomous machine learning and language agents, end-to-end LLM fine-tuning has not been systematically studied as an interactive agent task. We introduce FT-Dojo, an interactive benchmark environment for autonomous LLM fine-tuning, comprising 13 tasks across 5 domains. Rather than a new collection of static datasets, FT-Dojo standardizes a task interface, shared raw-data repository, sand"},"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":"2603.01712","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2026-03-02T10:37:11Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"3763380f7f2131a12d2024a39da407e08785a5556d4665d37d67521035319a4a","abstract_canon_sha256":"e4548072dbb44c0112feca18922176adcc9ef156671126c533c284c6a6d89184"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:05:17.069983Z","signature_b64":"Jto1YEYPux4ZL4W/rjMXB00Oaj5zjF23lgum287BX7PJj2iYWLAoL6cEd31G6vZn/HYXKOXqHI/LBr3CD1ufBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9ccdac1f1622b4f56e51e0e043d96568727985f791113e89468d8704eee5d58","last_reissued_at":"2026-05-21T01:05:17.069341Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:05:17.069341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FT-Dojo: Towards Autonomous LLM Fine-Tuning with Language Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Jiang Bian, Qizheng Li, Weiqing Liu, Xiao Yang, Xu Yang, Yifei Zhang, Zhuo Wang","submitted_at":"2026-03-02T10:37:11Z","abstract_excerpt":"Fine-tuning large language models for vertical domains remains labor-intensive, requiring practitioners to curate data, configure training, and iteratively diagnose model behavior. Despite growing interest in autonomous machine learning and language agents, end-to-end LLM fine-tuning has not been systematically studied as an interactive agent task. We introduce FT-Dojo, an interactive benchmark environment for autonomous LLM fine-tuning, comprising 13 tasks across 5 domains. Rather than a new collection of static datasets, FT-Dojo standardizes a task interface, shared raw-data repository, sand"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.01712","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/2603.01712/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":"2603.01712","created_at":"2026-05-21T01:05:17.069443+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.01712v2","created_at":"2026-05-21T01:05:17.069443+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.01712","created_at":"2026-05-21T01:05:17.069443+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZHGNVQPRMIVU","created_at":"2026-05-21T01:05:17.069443+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZHGNVQPRMIVU6VXF","created_at":"2026-05-21T01:05:17.069443+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZHGNVQPR","created_at":"2026-05-21T01:05:17.069443+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.09791","citing_title":"Pioneer Agent: Continual Improvement of Small Language Models in Production","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZHGNVQPRMIVU6VXFDYHAIPMWK2","json":"https://pith.science/pith/ZHGNVQPRMIVU6VXFDYHAIPMWK2.json","graph_json":"https://pith.science/api/pith-number/ZHGNVQPRMIVU6VXFDYHAIPMWK2/graph.json","events_json":"https://pith.science/api/pith-number/ZHGNVQPRMIVU6VXFDYHAIPMWK2/events.json","paper":"https://pith.science/paper/ZHGNVQPR"},"agent_actions":{"view_html":"https://pith.science/pith/ZHGNVQPRMIVU6VXFDYHAIPMWK2","download_json":"https://pith.science/pith/ZHGNVQPRMIVU6VXFDYHAIPMWK2.json","view_paper":"https://pith.science/paper/ZHGNVQPR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.01712&json=true","fetch_graph":"https://pith.science/api/pith-number/ZHGNVQPRMIVU6VXFDYHAIPMWK2/graph.json","fetch_events":"https://pith.science/api/pith-number/ZHGNVQPRMIVU6VXFDYHAIPMWK2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZHGNVQPRMIVU6VXFDYHAIPMWK2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZHGNVQPRMIVU6VXFDYHAIPMWK2/action/storage_attestation","attest_author":"https://pith.science/pith/ZHGNVQPRMIVU6VXFDYHAIPMWK2/action/author_attestation","sign_citation":"https://pith.science/pith/ZHGNVQPRMIVU6VXFDYHAIPMWK2/action/citation_signature","submit_replication":"https://pith.science/pith/ZHGNVQPRMIVU6VXFDYHAIPMWK2/action/replication_record"}},"created_at":"2026-05-21T01:05:17.069443+00:00","updated_at":"2026-05-21T01:05:17.069443+00:00"}