{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:FWHU4GRSIRWQEY3BRZFTGY4SDT","short_pith_number":"pith:FWHU4GRS","canonical_record":{"source":{"id":"2305.14483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T19:25:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2a1303631a00857a7874600015655f62142032dd4e71e65801a60ed4374c88a2","abstract_canon_sha256":"bfabae8865a7b066c2eacfbec0fc4a4515a46e7370d81773f634804865b158f8"},"schema_version":"1.0"},"canonical_sha256":"2d8f4e1a32446d0263618e4b3363921cfe9d09a154a1579c8b44752c1418205b","source":{"kind":"arxiv","id":"2305.14483","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14483","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14483v1","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14483","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"FWHU4GRSIRWQ","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"FWHU4GRSIRWQEY3B","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"FWHU4GRS","created_at":"2026-07-05T06:13:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:FWHU4GRSIRWQEY3BRZFTGY4SDT","target":"record","payload":{"canonical_record":{"source":{"id":"2305.14483","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T19:25:52Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2a1303631a00857a7874600015655f62142032dd4e71e65801a60ed4374c88a2","abstract_canon_sha256":"bfabae8865a7b066c2eacfbec0fc4a4515a46e7370d81773f634804865b158f8"},"schema_version":"1.0"},"canonical_sha256":"2d8f4e1a32446d0263618e4b3363921cfe9d09a154a1579c8b44752c1418205b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:24.054102Z","signature_b64":"3n6phAVzkG4Ug5yXLz66oybiaNVEWPYuX7veGIK0h6HOYzfK01TxBz6R2+xew89S2Xqu9+BoOk4M7DdOsZNFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2d8f4e1a32446d0263618e4b3363921cfe9d09a154a1579c8b44752c1418205b","last_reissued_at":"2026-07-05T06:13:24.053657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:24.053657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.14483","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pMvA1oLoMlr2JQmhhhi1haHWVWgW0jxTLcq9pMirYssho2UTcgjc1yTp705TGRJG50e82Zn0ra0lgKWm5xzVAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:46:37.829739Z"},"content_sha256":"f3c1e249845999e0e587b9ff9c79dd35883293ccc252e5ae7ae6e56f5108a4d5","schema_version":"1.0","event_id":"sha256:f3c1e249845999e0e587b9ff9c79dd35883293ccc252e5ae7ae6e56f5108a4d5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:FWHU4GRSIRWQEY3BRZFTGY4SDT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Language Model Self-improvement by Reinforcement Learning Contemplation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Jiacheng Xu, Jing-cheng Pang, Kaiyuan Li, Pengyuan Wang, Xiong-Hui Chen, Yang Yu, Zongzhang Zhang","submitted_at":"2023-05-23T19:25:52Z","abstract_excerpt":"Large Language Models (LLMs) have exhibited remarkable performance across various natural language processing (NLP) tasks. However, fine-tuning these models often necessitates substantial supervision, which can be expensive and time-consuming to obtain. This paper introduces a novel unsupervised method called LanguageModel Self-Improvement by Reinforcement Learning Contemplation (SIRLC) that improves LLMs without reliance on external labels. Our approach is grounded in the observation that it is simpler for language models to assess text quality than to generate text. Building on this insight,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14483","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/2305.14483/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:13:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"23cex6L+Vya2ZTXnVUowaKNSTp+TTpmZHIHnPgOdlGt7OyR/uag0ZUlsTwAVaCOQK4TXWlYgzOBA/1qQO8NDCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:46:37.830300Z"},"content_sha256":"18ca68dcff81137cac2fe89714356e3a271ec5a21627ab8afd571864ad8b08f0","schema_version":"1.0","event_id":"sha256:18ca68dcff81137cac2fe89714356e3a271ec5a21627ab8afd571864ad8b08f0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FWHU4GRSIRWQEY3BRZFTGY4SDT/bundle.json","state_url":"https://pith.science/pith/FWHU4GRSIRWQEY3BRZFTGY4SDT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FWHU4GRSIRWQEY3BRZFTGY4SDT/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T19:46:37Z","links":{"resolver":"https://pith.science/pith/FWHU4GRSIRWQEY3BRZFTGY4SDT","bundle":"https://pith.science/pith/FWHU4GRSIRWQEY3BRZFTGY4SDT/bundle.json","state":"https://pith.science/pith/FWHU4GRSIRWQEY3BRZFTGY4SDT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FWHU4GRSIRWQEY3BRZFTGY4SDT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:FWHU4GRSIRWQEY3BRZFTGY4SDT","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"bfabae8865a7b066c2eacfbec0fc4a4515a46e7370d81773f634804865b158f8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T19:25:52Z","title_canon_sha256":"2a1303631a00857a7874600015655f62142032dd4e71e65801a60ed4374c88a2"},"schema_version":"1.0","source":{"id":"2305.14483","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14483","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14483v1","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14483","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_12","alias_value":"FWHU4GRSIRWQ","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_16","alias_value":"FWHU4GRSIRWQEY3B","created_at":"2026-07-05T06:13:24Z"},{"alias_kind":"pith_short_8","alias_value":"FWHU4GRS","created_at":"2026-07-05T06:13:24Z"}],"graph_snapshots":[{"event_id":"sha256:18ca68dcff81137cac2fe89714356e3a271ec5a21627ab8afd571864ad8b08f0","target":"graph","created_at":"2026-07-05T06:13:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2305.14483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have exhibited remarkable performance across various natural language processing (NLP) tasks. However, fine-tuning these models often necessitates substantial supervision, which can be expensive and time-consuming to obtain. This paper introduces a novel unsupervised method called LanguageModel Self-Improvement by Reinforcement Learning Contemplation (SIRLC) that improves LLMs without reliance on external labels. Our approach is grounded in the observation that it is simpler for language models to assess text quality than to generate text. Building on this insight,","authors_text":"Jiacheng Xu, Jing-cheng Pang, Kaiyuan Li, Pengyuan Wang, Xiong-Hui Chen, Yang Yu, Zongzhang Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T19:25:52Z","title":"Language Model Self-improvement by Reinforcement Learning Contemplation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14483","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f3c1e249845999e0e587b9ff9c79dd35883293ccc252e5ae7ae6e56f5108a4d5","target":"record","created_at":"2026-07-05T06:13:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"bfabae8865a7b066c2eacfbec0fc4a4515a46e7370d81773f634804865b158f8","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T19:25:52Z","title_canon_sha256":"2a1303631a00857a7874600015655f62142032dd4e71e65801a60ed4374c88a2"},"schema_version":"1.0","source":{"id":"2305.14483","kind":"arxiv","version":1}},"canonical_sha256":"2d8f4e1a32446d0263618e4b3363921cfe9d09a154a1579c8b44752c1418205b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2d8f4e1a32446d0263618e4b3363921cfe9d09a154a1579c8b44752c1418205b","first_computed_at":"2026-07-05T06:13:24.053657Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:13:24.053657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3n6phAVzkG4Ug5yXLz66oybiaNVEWPYuX7veGIK0h6HOYzfK01TxBz6R2+xew89S2Xqu9+BoOk4M7DdOsZNFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:13:24.054102Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14483","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3c1e249845999e0e587b9ff9c79dd35883293ccc252e5ae7ae6e56f5108a4d5","sha256:18ca68dcff81137cac2fe89714356e3a271ec5a21627ab8afd571864ad8b08f0"],"state_sha256":"12506748e88edf594259c6e07096cf4f312d1b76c94fe41848a0430af0b3f719"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DPc9woV/4gI17es5tWVb8+wSaH3uYds1O/3k8e/mnocw13moNybMSp72Nknw8RVy81VhyHmOsXf9tb/UV2pvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:46:37.838472Z","bundle_sha256":"c188bd3e49d0fa90aa40e571993b9bed6c3c190f7e900a032f5a21c473f252cc"}}