{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:I7N2KOTXQZM75OC5S4ICJKGX5Y","short_pith_number":"pith:I7N2KOTX","canonical_record":{"source":{"id":"2412.10400","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:10:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"39dece5bc88832d677402dea0de57d2d3b92b033fe24fc3753e2afa7effac6e9","abstract_canon_sha256":"c89932c04b8b40f56f5857ba042ee3fe01baca13e38713e1c14ebacf9090fa8b"},"schema_version":"1.0"},"canonical_sha256":"47dba53a778659feb85d971024a8d7ee3f384fc2b245107b7c6ae53071483d57","source":{"kind":"arxiv","id":"2412.10400","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10400","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10400v3","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10400","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"I7N2KOTXQZM7","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"I7N2KOTXQZM75OC5","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"I7N2KOTX","created_at":"2026-07-05T10:18:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:I7N2KOTXQZM75OC5S4ICJKGX5Y","target":"record","payload":{"canonical_record":{"source":{"id":"2412.10400","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:10:42Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"39dece5bc88832d677402dea0de57d2d3b92b033fe24fc3753e2afa7effac6e9","abstract_canon_sha256":"c89932c04b8b40f56f5857ba042ee3fe01baca13e38713e1c14ebacf9090fa8b"},"schema_version":"1.0"},"canonical_sha256":"47dba53a778659feb85d971024a8d7ee3f384fc2b245107b7c6ae53071483d57","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:46.861572Z","signature_b64":"3jSO6sSn7yJzwJ/5k9mkMLcIpKmpQL/wanxffDIXPHUN+2ZR/cNvwlKNiA8ak/BfQjrJzyFZd5/lMWkgLv8aBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47dba53a778659feb85d971024a8d7ee3f384fc2b245107b7c6ae53071483d57","last_reissued_at":"2026-07-05T10:18:46.861058Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:46.861058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.10400","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RFueSDLjp1BaVw7FPUEMEhcmpBu85P1SFfdReU/ME3w4dOd14Yh2uqQEOfUxQdddrhFgmzFmhdV0vbPk4rVNAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:19:49.093151Z"},"content_sha256":"290534d831d590d6eb7671e00ec11dd9b811e13b7b2622b247cb774258d91535","schema_version":"1.0","event_id":"sha256:290534d831d590d6eb7671e00ec11dd9b811e13b7b2622b247cb774258d91535"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:I7N2KOTXQZM75OC5S4ICJKGX5Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning Enhanced LLMs: A Survey","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eduard Hovy, Fei Wu, Guoyin Wang, Jie Zhang, Jiwei Li, Runyi Hu, Shengyu Zhang, Shuhe Wang, Tianwei Zhang, Xiaoya Li","submitted_at":"2024-12-05T16:10:42Z","abstract_excerpt":"Reinforcement learning (RL) enhanced large language models (LLMs), particularly exemplified by DeepSeek-R1, have exhibited outstanding performance. Despite the effectiveness in improving LLM capabilities, its implementation remains highly complex, requiring complex algorithms, reward modeling strategies, and optimization techniques. This complexity poses challenges for researchers and practitioners in developing a systematic understanding of RL-enhanced LLMs. Moreover, the absence of a comprehensive survey summarizing existing research on RL-enhanced LLMs has limited progress in this domain, h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10400","kind":"arxiv","version":3},"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/2412.10400/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":"2026-07-05T10:18:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xW0oovmXrUSDfBI8n5bDi+MU32TnXTDTFg62qHIxFsUeXrmhtA32yD04KWL5L2tcPl8Sn6tMN9fhOcpFckHcAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:19:49.094152Z"},"content_sha256":"bf19955c63dfbeeca8bafecf5dcc8adc3747a4b9158051427ec067039f1392fa","schema_version":"1.0","event_id":"sha256:bf19955c63dfbeeca8bafecf5dcc8adc3747a4b9158051427ec067039f1392fa"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I7N2KOTXQZM75OC5S4ICJKGX5Y/bundle.json","state_url":"https://pith.science/pith/I7N2KOTXQZM75OC5S4ICJKGX5Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I7N2KOTXQZM75OC5S4ICJKGX5Y/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":"2026-08-05T11:19:49Z","links":{"resolver":"https://pith.science/pith/I7N2KOTXQZM75OC5S4ICJKGX5Y","bundle":"https://pith.science/pith/I7N2KOTXQZM75OC5S4ICJKGX5Y/bundle.json","state":"https://pith.science/pith/I7N2KOTXQZM75OC5S4ICJKGX5Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I7N2KOTXQZM75OC5S4ICJKGX5Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:I7N2KOTXQZM75OC5S4ICJKGX5Y","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":"c89932c04b8b40f56f5857ba042ee3fe01baca13e38713e1c14ebacf9090fa8b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:10:42Z","title_canon_sha256":"39dece5bc88832d677402dea0de57d2d3b92b033fe24fc3753e2afa7effac6e9"},"schema_version":"1.0","source":{"id":"2412.10400","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.10400","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"arxiv_version","alias_value":"2412.10400v3","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.10400","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"pith_short_12","alias_value":"I7N2KOTXQZM7","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"pith_short_16","alias_value":"I7N2KOTXQZM75OC5","created_at":"2026-07-05T10:18:46Z"},{"alias_kind":"pith_short_8","alias_value":"I7N2KOTX","created_at":"2026-07-05T10:18:46Z"}],"graph_snapshots":[{"event_id":"sha256:bf19955c63dfbeeca8bafecf5dcc8adc3747a4b9158051427ec067039f1392fa","target":"graph","created_at":"2026-07-05T10:18:46Z","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/2412.10400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning (RL) enhanced large language models (LLMs), particularly exemplified by DeepSeek-R1, have exhibited outstanding performance. Despite the effectiveness in improving LLM capabilities, its implementation remains highly complex, requiring complex algorithms, reward modeling strategies, and optimization techniques. This complexity poses challenges for researchers and practitioners in developing a systematic understanding of RL-enhanced LLMs. Moreover, the absence of a comprehensive survey summarizing existing research on RL-enhanced LLMs has limited progress in this domain, h","authors_text":"Eduard Hovy, Fei Wu, Guoyin Wang, Jie Zhang, Jiwei Li, Runyi Hu, Shengyu Zhang, Shuhe Wang, Tianwei Zhang, Xiaoya Li","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:10:42Z","title":"Reinforcement Learning Enhanced LLMs: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.10400","kind":"arxiv","version":3},"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":"sha256:290534d831d590d6eb7671e00ec11dd9b811e13b7b2622b247cb774258d91535","target":"record","created_at":"2026-07-05T10:18:46Z","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":"c89932c04b8b40f56f5857ba042ee3fe01baca13e38713e1c14ebacf9090fa8b","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-05T16:10:42Z","title_canon_sha256":"39dece5bc88832d677402dea0de57d2d3b92b033fe24fc3753e2afa7effac6e9"},"schema_version":"1.0","source":{"id":"2412.10400","kind":"arxiv","version":3}},"canonical_sha256":"47dba53a778659feb85d971024a8d7ee3f384fc2b245107b7c6ae53071483d57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"47dba53a778659feb85d971024a8d7ee3f384fc2b245107b7c6ae53071483d57","first_computed_at":"2026-07-05T10:18:46.861058Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:18:46.861058Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3jSO6sSn7yJzwJ/5k9mkMLcIpKmpQL/wanxffDIXPHUN+2ZR/cNvwlKNiA8ak/BfQjrJzyFZd5/lMWkgLv8aBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:18:46.861572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.10400","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:290534d831d590d6eb7671e00ec11dd9b811e13b7b2622b247cb774258d91535","sha256:bf19955c63dfbeeca8bafecf5dcc8adc3747a4b9158051427ec067039f1392fa"],"state_sha256":"912847aa853860b02ef3e9bbae4cebb0cafac54daedbcf4b9b54b408d38a2806"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T9DXb8gb2TQtkAyv/kOC05U9J0fZfQ6G/Kd+LrA75jsoh/R7N4dYfrRowjJSQWzKl0LAzVylzaAXNzveLpXVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:19:49.099404Z","bundle_sha256":"7bfb303fde391d88ffdd5ec3850ea9b3648b2e92e8d06a7cccbab626e126e756"}}