{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:26I3BZ5XNX33I5G3XPZK5NJADY","short_pith_number":"pith:26I3BZ5X","canonical_record":{"source":{"id":"2507.12507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T17:59:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ed0f8cb14856133ffebcec18e0690680f64ab7838537cd83ececac35c863f63c","abstract_canon_sha256":"feda4c2d42382fd432769855c8a0c91a08139ac650944b02f874a0f11967caa7"},"schema_version":"1.0"},"canonical_sha256":"d791b0e7b76df7b474dbbbf2aeb5201e2365bbde9e1da7a729e57fe71996a913","source":{"kind":"arxiv","id":"2507.12507","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12507","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12507v1","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12507","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"26I3BZ5XNX33","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"pith_short_16","alias_value":"26I3BZ5XNX33I5G3","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"pith_short_8","alias_value":"26I3BZ5X","created_at":"2026-07-05T11:38:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:26I3BZ5XNX33I5G3XPZK5NJADY","target":"record","payload":{"canonical_record":{"source":{"id":"2507.12507","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T17:59:24Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ed0f8cb14856133ffebcec18e0690680f64ab7838537cd83ececac35c863f63c","abstract_canon_sha256":"feda4c2d42382fd432769855c8a0c91a08139ac650944b02f874a0f11967caa7"},"schema_version":"1.0"},"canonical_sha256":"d791b0e7b76df7b474dbbbf2aeb5201e2365bbde9e1da7a729e57fe71996a913","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:33.721740Z","signature_b64":"5QDTIIhTaETgorjrL32A3RdEboVy0DTEvzxuzLkpbu6MLsWH3tKWJ8vbQnTpwFapL7mXn2UrzcV/XwSP92HRCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d791b0e7b76df7b474dbbbf2aeb5201e2365bbde9e1da7a729e57fe71996a913","last_reissued_at":"2026-07-05T11:38:33.721056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:33.721056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.12507","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":"2026-07-05T11:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mI9N4qLtLoD1UxUUpfTijhtPOxa3WHgPpeLCUzwpe2jTkaHPAnAeX2oUXVwRZJlTAyp8qBTtsd7BlUGDAMbgDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:43:10.363201Z"},"content_sha256":"99d01983ae5043d8edcb291852deee73b0b82a25d466f31aaf306d24817ffb08","schema_version":"1.0","event_id":"sha256:99d01983ae5043d8edcb291852deee73b0b82a25d466f31aaf306d24817ffb08"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:26I3BZ5XNX33I5G3XPZK5NJADY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Alexander Bukharin, David Mosallanezhad, Di Zhang, Gerald Shen, Guilin Liu, Hao Zhang, Jan Kautz, Jian Hu, Jiaqi Zeng, Jonas Yang, June Yang, Makesh Narsimhan Sreedhar, Mingjie Liu, Oleksii Kuchaiev, Pavlo Molchanov, Shaokun Zhang, Shizhe Diao, Ximing Lu, Xin Dong, Yejin Choi, Yi Dong, Zhiding Yu","submitted_at":"2025-07-16T17:59:24Z","abstract_excerpt":"Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on complex tasks like mathematics and code generation. These breakthroughs have been driven by large-scale reinforcement learning (RL), particularly when combined with verifiable reward signals that provide objective and grounded supervision. In this report, we investigate the effects of prolonged reinforcement learning on a small language model across a diverse "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12507","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/2507.12507/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":"2026-07-05T11:38:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TaWRfxBqHSd60h3IEMzgxoxzBDDZq4ethLQLNCHDdaR5wviy9gx+DsFE5Bn7yzIHG3gPtxCu5OMlLq7ieQo0AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T13:43:10.363584Z"},"content_sha256":"966e409b78c72b9bee640ce5bcac9529e2c2ea7c730bc5a418288f7db51596d4","schema_version":"1.0","event_id":"sha256:966e409b78c72b9bee640ce5bcac9529e2c2ea7c730bc5a418288f7db51596d4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26I3BZ5XNX33I5G3XPZK5NJADY/bundle.json","state_url":"https://pith.science/pith/26I3BZ5XNX33I5G3XPZK5NJADY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26I3BZ5XNX33I5G3XPZK5NJADY/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":"2026-08-23T13:43:10Z","links":{"resolver":"https://pith.science/pith/26I3BZ5XNX33I5G3XPZK5NJADY","bundle":"https://pith.science/pith/26I3BZ5XNX33I5G3XPZK5NJADY/bundle.json","state":"https://pith.science/pith/26I3BZ5XNX33I5G3XPZK5NJADY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26I3BZ5XNX33I5G3XPZK5NJADY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:26I3BZ5XNX33I5G3XPZK5NJADY","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":"feda4c2d42382fd432769855c8a0c91a08139ac650944b02f874a0f11967caa7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T17:59:24Z","title_canon_sha256":"ed0f8cb14856133ffebcec18e0690680f64ab7838537cd83ececac35c863f63c"},"schema_version":"1.0","source":{"id":"2507.12507","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12507","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12507v1","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12507","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"pith_short_12","alias_value":"26I3BZ5XNX33","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"pith_short_16","alias_value":"26I3BZ5XNX33I5G3","created_at":"2026-07-05T11:38:33Z"},{"alias_kind":"pith_short_8","alias_value":"26I3BZ5X","created_at":"2026-07-05T11:38:33Z"}],"graph_snapshots":[{"event_id":"sha256:966e409b78c72b9bee640ce5bcac9529e2c2ea7c730bc5a418288f7db51596d4","target":"graph","created_at":"2026-07-05T11:38:33Z","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/2507.12507/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in reasoning-focused language models such as OpenAI's O1 and DeepSeek-R1 have shown that scaling test-time computation-through chain-of-thought reasoning and iterative exploration-can yield substantial improvements on complex tasks like mathematics and code generation. These breakthroughs have been driven by large-scale reinforcement learning (RL), particularly when combined with verifiable reward signals that provide objective and grounded supervision. In this report, we investigate the effects of prolonged reinforcement learning on a small language model across a diverse ","authors_text":"Alexander Bukharin, David Mosallanezhad, Di Zhang, Gerald Shen, Guilin Liu, Hao Zhang, Jan Kautz, Jian Hu, Jiaqi Zeng, Jonas Yang, June Yang, Makesh Narsimhan Sreedhar, Mingjie Liu, Oleksii Kuchaiev, Pavlo Molchanov, Shaokun Zhang, Shizhe Diao, Ximing Lu, Xin Dong, Yejin Choi, Yi Dong, Zhiding Yu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T17:59:24Z","title":"Scaling Up RL: Unlocking Diverse Reasoning in LLMs via Prolonged Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12507","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":"sha256:99d01983ae5043d8edcb291852deee73b0b82a25d466f31aaf306d24817ffb08","target":"record","created_at":"2026-07-05T11:38:33Z","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":"feda4c2d42382fd432769855c8a0c91a08139ac650944b02f874a0f11967caa7","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-16T17:59:24Z","title_canon_sha256":"ed0f8cb14856133ffebcec18e0690680f64ab7838537cd83ececac35c863f63c"},"schema_version":"1.0","source":{"id":"2507.12507","kind":"arxiv","version":1}},"canonical_sha256":"d791b0e7b76df7b474dbbbf2aeb5201e2365bbde9e1da7a729e57fe71996a913","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d791b0e7b76df7b474dbbbf2aeb5201e2365bbde9e1da7a729e57fe71996a913","first_computed_at":"2026-07-05T11:38:33.721056Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:33.721056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5QDTIIhTaETgorjrL32A3RdEboVy0DTEvzxuzLkpbu6MLsWH3tKWJ8vbQnTpwFapL7mXn2UrzcV/XwSP92HRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:33.721740Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12507","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99d01983ae5043d8edcb291852deee73b0b82a25d466f31aaf306d24817ffb08","sha256:966e409b78c72b9bee640ce5bcac9529e2c2ea7c730bc5a418288f7db51596d4"],"state_sha256":"c04c00d3cb8a14988ae2520d133c55943760cce63104cc5948fd4c16eb561adc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"65ZPbZ0pl9/XRs/1gcBIOK4guju+3hyCGQvlEUJiL+i2up4BKRHFIjOt3ZfokjOHWj3t/kr0nhj7/WtFqUlzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T13:43:10.366248Z","bundle_sha256":"b0a25829d0e455a50ab2a67006dc20fc9f8d2ea4a2ad5bbc150f83aad38e9ead"}}