{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V5URQLT4U5RUKHZT3KAJHI7B6F","short_pith_number":"pith:V5URQLT4","schema_version":"1.0","canonical_sha256":"af69182e7ca763451f33da8093a3e1f1471e3c9cb30a24ad50f6679cedbb8188","source":{"kind":"arxiv","id":"2310.00533","version":4},"attestation_state":"computed","paper":{"title":"SELF: Self-Evolution with Language Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Baojun Wang, Fei Mi, Jianqiao Lu, Lifeng Shang, Qi Zhu, Qun Liu, Wanjun Zhong, Weichao Wang, Wenyong Huang, Xingshan Zeng, Xin Jiang, Yufei Wang","submitted_at":"2023-10-01T00:52:24Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable versatility across various domains. To further advance LLMs, we propose 'SELF' (Self-Evolution with Language Feedback), a novel approach that enables LLMs to self-improve through self-reflection, akin to human learning processes. SELF initiates with a meta-skill learning process that equips the LLMs with capabilities for self-feedback and self-refinement. Subsequently, the model undergoes an iterative process of self-evolution. In each iteration, it utilizes an unlabeled dataset of instructions to generate initial responses. These respo"},"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":"2310.00533","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-01T00:52:24Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"bee42cd9fd8400c4f52c40fd8ed0f0b5ee82cd0d19d55f91c047f7350c1cfef4","abstract_canon_sha256":"6be31b5364bf14b109d3c57f56cf1c79771ab443989b36c73981baaa7b4193d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:02.426353Z","signature_b64":"mn2a/jLaj1MetvSUnSiCvEvoj0VfIkKKNyyodJXSThYjAUFiDET8/uYk4HQFqZPee24F3WXBmTxsIkFHu1olAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af69182e7ca763451f33da8093a3e1f1471e3c9cb30a24ad50f6679cedbb8188","last_reissued_at":"2026-07-05T07:40:02.425695Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:02.425695Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SELF: Self-Evolution with Language Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Baojun Wang, Fei Mi, Jianqiao Lu, Lifeng Shang, Qi Zhu, Qun Liu, Wanjun Zhong, Weichao Wang, Wenyong Huang, Xingshan Zeng, Xin Jiang, Yufei Wang","submitted_at":"2023-10-01T00:52:24Z","abstract_excerpt":"Large Language Models (LLMs) have demonstrated remarkable versatility across various domains. To further advance LLMs, we propose 'SELF' (Self-Evolution with Language Feedback), a novel approach that enables LLMs to self-improve through self-reflection, akin to human learning processes. SELF initiates with a meta-skill learning process that equips the LLMs with capabilities for self-feedback and self-refinement. Subsequently, the model undergoes an iterative process of self-evolution. In each iteration, it utilizes an unlabeled dataset of instructions to generate initial responses. These respo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00533","kind":"arxiv","version":4},"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/2310.00533/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":"2310.00533","created_at":"2026-07-05T07:40:02.425776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.00533v4","created_at":"2026-07-05T07:40:02.425776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00533","created_at":"2026-07-05T07:40:02.425776+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5URQLT4U5RU","created_at":"2026-07-05T07:40:02.425776+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5URQLT4U5RUKHZT","created_at":"2026-07-05T07:40:02.425776+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5URQLT4","created_at":"2026-07-05T07:40:02.425776+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.02372","citing_title":"COMAP: Co-Evolving World Models and Agent Policies for LLM Agents","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V5URQLT4U5RUKHZT3KAJHI7B6F","json":"https://pith.science/pith/V5URQLT4U5RUKHZT3KAJHI7B6F.json","graph_json":"https://pith.science/api/pith-number/V5URQLT4U5RUKHZT3KAJHI7B6F/graph.json","events_json":"https://pith.science/api/pith-number/V5URQLT4U5RUKHZT3KAJHI7B6F/events.json","paper":"https://pith.science/paper/V5URQLT4"},"agent_actions":{"view_html":"https://pith.science/pith/V5URQLT4U5RUKHZT3KAJHI7B6F","download_json":"https://pith.science/pith/V5URQLT4U5RUKHZT3KAJHI7B6F.json","view_paper":"https://pith.science/paper/V5URQLT4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.00533&json=true","fetch_graph":"https://pith.science/api/pith-number/V5URQLT4U5RUKHZT3KAJHI7B6F/graph.json","fetch_events":"https://pith.science/api/pith-number/V5URQLT4U5RUKHZT3KAJHI7B6F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5URQLT4U5RUKHZT3KAJHI7B6F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5URQLT4U5RUKHZT3KAJHI7B6F/action/storage_attestation","attest_author":"https://pith.science/pith/V5URQLT4U5RUKHZT3KAJHI7B6F/action/author_attestation","sign_citation":"https://pith.science/pith/V5URQLT4U5RUKHZT3KAJHI7B6F/action/citation_signature","submit_replication":"https://pith.science/pith/V5URQLT4U5RUKHZT3KAJHI7B6F/action/replication_record"}},"created_at":"2026-07-05T07:40:02.425776+00:00","updated_at":"2026-07-05T07:40:02.425776+00:00"}