{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WBQ6FSERYDHP7KZWEGH4LT3T4Q","short_pith_number":"pith:WBQ6FSER","schema_version":"1.0","canonical_sha256":"b061e2c891c0ceffab36218fc5cf73e40a49b8d4bb56a86d3b985833854b049d","source":{"kind":"arxiv","id":"2505.01073","version":1},"attestation_state":"computed","paper":{"title":"Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hui Wu, Kuihua Huang, Lumin Jiang, Pengfei Li, Runnan Qi, Xian Guo, Xuebo Zhang, Yanan Ni, Zongyuan Li","submitted_at":"2025-05-02T07:25:01Z","abstract_excerpt":"The lack of domain-specific data in the pre-training of Large Language Models (LLMs) severely limits LLM-based decision systems in specialized applications, while post-training a model in the scenarios requires significant computational resources. In this paper, we present Retrial-Augmented Learning (RAL), a reward-free self-supervised learning framework for LLMs that operates without model training. By developing Retrieval-Augmented Generation (RAG) into a module for organizing intermediate data, we realized a three-stage autonomous knowledge generation of proposing a hypothesis, validating t"},"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":"2505.01073","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-02T07:25:01Z","cross_cats_sorted":[],"title_canon_sha256":"95a20ee50583c250c178db728d7126adaeb399009b1c523a310b05aaa0962fc1","abstract_canon_sha256":"3930a1f88b00e3c44dab62f877ab3e754564991847ed1a52b318ad0e4304739d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:57:44.620740Z","signature_b64":"AxafGqjeimOpr/dapm3Kc9bDKUhKq/IGrSkz5m+TSIIAkRzbai9JEsjcpN0Burt3SFkwpkzsxheQL9voh5BTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b061e2c891c0ceffab36218fc5cf73e40a49b8d4bb56a86d3b985833854b049d","last_reissued_at":"2026-07-05T10:57:44.620198Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:57:44.620198Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hui Wu, Kuihua Huang, Lumin Jiang, Pengfei Li, Runnan Qi, Xian Guo, Xuebo Zhang, Yanan Ni, Zongyuan Li","submitted_at":"2025-05-02T07:25:01Z","abstract_excerpt":"The lack of domain-specific data in the pre-training of Large Language Models (LLMs) severely limits LLM-based decision systems in specialized applications, while post-training a model in the scenarios requires significant computational resources. In this paper, we present Retrial-Augmented Learning (RAL), a reward-free self-supervised learning framework for LLMs that operates without model training. By developing Retrieval-Augmented Generation (RAG) into a module for organizing intermediate data, we realized a three-stage autonomous knowledge generation of proposing a hypothesis, validating t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.01073","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/2505.01073/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":"2505.01073","created_at":"2026-07-05T10:57:44.620268+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.01073v1","created_at":"2026-07-05T10:57:44.620268+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.01073","created_at":"2026-07-05T10:57:44.620268+00:00"},{"alias_kind":"pith_short_12","alias_value":"WBQ6FSERYDHP","created_at":"2026-07-05T10:57:44.620268+00:00"},{"alias_kind":"pith_short_16","alias_value":"WBQ6FSERYDHP7KZW","created_at":"2026-07-05T10:57:44.620268+00:00"},{"alias_kind":"pith_short_8","alias_value":"WBQ6FSER","created_at":"2026-07-05T10:57:44.620268+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/WBQ6FSERYDHP7KZWEGH4LT3T4Q","json":"https://pith.science/pith/WBQ6FSERYDHP7KZWEGH4LT3T4Q.json","graph_json":"https://pith.science/api/pith-number/WBQ6FSERYDHP7KZWEGH4LT3T4Q/graph.json","events_json":"https://pith.science/api/pith-number/WBQ6FSERYDHP7KZWEGH4LT3T4Q/events.json","paper":"https://pith.science/paper/WBQ6FSER"},"agent_actions":{"view_html":"https://pith.science/pith/WBQ6FSERYDHP7KZWEGH4LT3T4Q","download_json":"https://pith.science/pith/WBQ6FSERYDHP7KZWEGH4LT3T4Q.json","view_paper":"https://pith.science/paper/WBQ6FSER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.01073&json=true","fetch_graph":"https://pith.science/api/pith-number/WBQ6FSERYDHP7KZWEGH4LT3T4Q/graph.json","fetch_events":"https://pith.science/api/pith-number/WBQ6FSERYDHP7KZWEGH4LT3T4Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WBQ6FSERYDHP7KZWEGH4LT3T4Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WBQ6FSERYDHP7KZWEGH4LT3T4Q/action/storage_attestation","attest_author":"https://pith.science/pith/WBQ6FSERYDHP7KZWEGH4LT3T4Q/action/author_attestation","sign_citation":"https://pith.science/pith/WBQ6FSERYDHP7KZWEGH4LT3T4Q/action/citation_signature","submit_replication":"https://pith.science/pith/WBQ6FSERYDHP7KZWEGH4LT3T4Q/action/replication_record"}},"created_at":"2026-07-05T10:57:44.620268+00:00","updated_at":"2026-07-05T10:57:44.620268+00:00"}