{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6ITHSQS7CKUWAENL73W73MIERU","short_pith_number":"pith:6ITHSQS7","canonical_record":{"source":{"id":"2412.14135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-18T18:24:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7e2e56da829f34f1265e87974b4f6b4927a678d9af4d9e13bb036b33d1244b7e","abstract_canon_sha256":"bb57e7a6b32bfafeffd3e5f08ac491e7709c533d52078abddf99c2db76b125e4"},"schema_version":"1.0"},"canonical_sha256":"f22679425f12a96011abfeedfdb1048d1b0ea7862a74e5b6fc11076ad6997aa3","source":{"kind":"arxiv","id":"2412.14135","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14135","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14135v1","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14135","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"6ITHSQS7CKUW","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"pith_short_16","alias_value":"6ITHSQS7CKUWAENL","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"pith_short_8","alias_value":"6ITHSQS7","created_at":"2026-07-05T09:51:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6ITHSQS7CKUWAENL73W73MIERU","target":"record","payload":{"canonical_record":{"source":{"id":"2412.14135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-18T18:24:47Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"7e2e56da829f34f1265e87974b4f6b4927a678d9af4d9e13bb036b33d1244b7e","abstract_canon_sha256":"bb57e7a6b32bfafeffd3e5f08ac491e7709c533d52078abddf99c2db76b125e4"},"schema_version":"1.0"},"canonical_sha256":"f22679425f12a96011abfeedfdb1048d1b0ea7862a74e5b6fc11076ad6997aa3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:51:14.125008Z","signature_b64":"XVKel8buYx6s3Rpy0606aGpXp5WxQufo+wzyL+XAuhAbNfIvVXFFCBjtesM/+EImjA4tffYKwa0iep+ul+8wAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f22679425f12a96011abfeedfdb1048d1b0ea7862a74e5b6fc11076ad6997aa3","last_reissued_at":"2026-07-05T09:51:14.124606Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:51:14.124606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.14135","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":"2026-07-05T09:51:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KgB0WrDbHXO3Szt0vpMAwtfvEE2Lwb42o8ZVToJ279RSHonGmD0E2U0oJ+PFgGi+8SO1Pd4RdYBf00DZpEPqAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:32:31.313138Z"},"content_sha256":"1c9cd8d41838d08db48ba0135ea01308eccbaad5044834dd647718ccd3b31e5d","schema_version":"1.0","event_id":"sha256:1c9cd8d41838d08db48ba0135ea01308eccbaad5044834dd647718ccd3b31e5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6ITHSQS7CKUWAENL73W73MIERU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Bo Wang, Qinyuan Cheng, Qipeng Guo, Shimin Li, Xipeng Qiu, Xuanjing Huang, Yunhua Zhou, Zhangyue Yin, Zhiyuan Zeng","submitted_at":"2024-12-18T18:24:47Z","abstract_excerpt":"OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning ability.OpenAI has claimed that the main techinique behinds o1 is the reinforcement learining. Recent works use alternative approaches like knowledge distillation to imitate o1's reasoning style, but their effectiveness is limited by the capability ceiling of the teacher model. Therefore, this paper analyzes the roadmap to achieving o1 from the perspective of reinforcement learning, focusing on four key components: policy init"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14135","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/2412.14135/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":"2026-07-05T09:51:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aB88Gj4AMHO0iLxP3HKo+TFaa6SCOXm71g8fsKES8zdtdWNnfUABx1IxJhXq1uS/nQI4jUrl7sCREclOebLmAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T08:32:31.313541Z"},"content_sha256":"76560ed52a13c52065815577e7684ddf4147426ef35a7571b1de6ba860376e76","schema_version":"1.0","event_id":"sha256:76560ed52a13c52065815577e7684ddf4147426ef35a7571b1de6ba860376e76"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU/bundle.json","state_url":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6ITHSQS7CKUWAENL73W73MIERU/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":"2026-07-06T08:32:31Z","links":{"resolver":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU","bundle":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU/bundle.json","state":"https://pith.science/pith/6ITHSQS7CKUWAENL73W73MIERU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6ITHSQS7CKUWAENL73W73MIERU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6ITHSQS7CKUWAENL73W73MIERU","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":"bb57e7a6b32bfafeffd3e5f08ac491e7709c533d52078abddf99c2db76b125e4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-18T18:24:47Z","title_canon_sha256":"7e2e56da829f34f1265e87974b4f6b4927a678d9af4d9e13bb036b33d1244b7e"},"schema_version":"1.0","source":{"id":"2412.14135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.14135","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"arxiv_version","alias_value":"2412.14135v1","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14135","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"pith_short_12","alias_value":"6ITHSQS7CKUW","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"pith_short_16","alias_value":"6ITHSQS7CKUWAENL","created_at":"2026-07-05T09:51:14Z"},{"alias_kind":"pith_short_8","alias_value":"6ITHSQS7","created_at":"2026-07-05T09:51:14Z"}],"graph_snapshots":[{"event_id":"sha256:76560ed52a13c52065815577e7684ddf4147426ef35a7571b1de6ba860376e76","target":"graph","created_at":"2026-07-05T09:51:14Z","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/2412.14135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"OpenAI o1 represents a significant milestone in Artificial Inteiligence, which achieves expert-level performances on many challanging tasks that require strong reasoning ability.OpenAI has claimed that the main techinique behinds o1 is the reinforcement learining. Recent works use alternative approaches like knowledge distillation to imitate o1's reasoning style, but their effectiveness is limited by the capability ceiling of the teacher model. Therefore, this paper analyzes the roadmap to achieving o1 from the perspective of reinforcement learning, focusing on four key components: policy init","authors_text":"Bo Wang, Qinyuan Cheng, Qipeng Guo, Shimin Li, Xipeng Qiu, Xuanjing Huang, Yunhua Zhou, Zhangyue Yin, Zhiyuan Zeng","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-18T18:24:47Z","title":"Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14135","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":"sha256:1c9cd8d41838d08db48ba0135ea01308eccbaad5044834dd647718ccd3b31e5d","target":"record","created_at":"2026-07-05T09:51:14Z","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":"bb57e7a6b32bfafeffd3e5f08ac491e7709c533d52078abddf99c2db76b125e4","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-12-18T18:24:47Z","title_canon_sha256":"7e2e56da829f34f1265e87974b4f6b4927a678d9af4d9e13bb036b33d1244b7e"},"schema_version":"1.0","source":{"id":"2412.14135","kind":"arxiv","version":1}},"canonical_sha256":"f22679425f12a96011abfeedfdb1048d1b0ea7862a74e5b6fc11076ad6997aa3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f22679425f12a96011abfeedfdb1048d1b0ea7862a74e5b6fc11076ad6997aa3","first_computed_at":"2026-07-05T09:51:14.124606Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:51:14.124606Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XVKel8buYx6s3Rpy0606aGpXp5WxQufo+wzyL+XAuhAbNfIvVXFFCBjtesM/+EImjA4tffYKwa0iep+ul+8wAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:51:14.125008Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.14135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1c9cd8d41838d08db48ba0135ea01308eccbaad5044834dd647718ccd3b31e5d","sha256:76560ed52a13c52065815577e7684ddf4147426ef35a7571b1de6ba860376e76"],"state_sha256":"44a4c5c48bb098d6a545325ce5a86c121042d862ef3b77c97f810cde41767f33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QHalmQR8UUlr3bimmlJLAKJrG65EG6QaDmMnDpGIXqF787VawZT2KtgfH1S5YwECR2iPt9v+ioAhYtWzBUJDDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T08:32:31.315569Z","bundle_sha256":"a3dd60457bd44edb9181ded4fd27da361cdc18d0d6ad349886622e8c0c17998a"}}