{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:3DTCYULKYVGXK4XWPGLGXWECBR","short_pith_number":"pith:3DTCYULK","canonical_record":{"source":{"id":"2504.14286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-19T13:06:03Z","cross_cats_sorted":[],"title_canon_sha256":"bc275c0153e229821940e265fe4dfe26621ef1ce9137773c4181b33aea0c7b2e","abstract_canon_sha256":"59165306c115a3a92737b3e4d132add337c31405bc06367f3ea5487d46d7a418"},"schema_version":"1.0"},"canonical_sha256":"d8e62c516ac54d7572f679966bd8820c6f13a6f0c057abfb17f2fb907f8c5e9a","source":{"kind":"arxiv","id":"2504.14286","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14286","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14286v2","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14286","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"pith_short_12","alias_value":"3DTCYULKYVGX","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"pith_short_16","alias_value":"3DTCYULKYVGXK4XW","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"pith_short_8","alias_value":"3DTCYULK","created_at":"2026-07-05T10:52:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:3DTCYULKYVGXK4XWPGLGXWECBR","target":"record","payload":{"canonical_record":{"source":{"id":"2504.14286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-19T13:06:03Z","cross_cats_sorted":[],"title_canon_sha256":"bc275c0153e229821940e265fe4dfe26621ef1ce9137773c4181b33aea0c7b2e","abstract_canon_sha256":"59165306c115a3a92737b3e4d132add337c31405bc06367f3ea5487d46d7a418"},"schema_version":"1.0"},"canonical_sha256":"d8e62c516ac54d7572f679966bd8820c6f13a6f0c057abfb17f2fb907f8c5e9a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:23.156239Z","signature_b64":"unxpNb/aRpgv/YAKYzk221d9+1JH5441wyJOAz/5qx9GgUSWpg+wIfEwwSX5G3ob0vH2mwylDccH/6xi+M7XDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8e62c516ac54d7572f679966bd8820c6f13a6f0c057abfb17f2fb907f8c5e9a","last_reissued_at":"2026-07-05T10:52:23.155763Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:23.155763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.14286","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:52:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7jrl3kevOwG0GFGAL2CSVAF/N+3Eg92jxvT+GgV+PjqyBccSpAclSS9za8cKoHNO0Bs/EaB4cVk8zRCz+nOZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:18:52.317828Z"},"content_sha256":"ae05bd5281465e5d4d2232aad255b96d277378cd4ab46b169761bc31a8093330","schema_version":"1.0","event_id":"sha256:ae05bd5281465e5d4d2232aad255b96d277378cd4ab46b169761bc31a8093330"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:3DTCYULKYVGXK4XWPGLGXWECBR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bin Chen, Bing Yu, Chaohang Wen, Chao Wang, Haotian Zhang, Jinghui Wang, Junyi Peng, Minglei Zhang, Shaojie Wang, Shimiao Jiang, Shiqi Kuang, Shouyu Yin, Wenhao Zhuang, Xiaojiang Zhang, Yinghan Cui, Zheng Lin, Zifei Cheng","submitted_at":"2025-04-19T13:06:03Z","abstract_excerpt":"Recent advances of reasoning models, exemplified by OpenAI's o1 and DeepSeek's R1, highlight the significant potential of Reinforcement Learning (RL) to enhance the reasoning capabilities of Large Language Models (LLMs). However, replicating these advancements across diverse domains remains challenging due to limited methodological transparency. In this work, we present two-Staged history-Resampling Policy Optimization (SRPO), which surpasses the performance of DeepSeek-R1-Zero-32B on the AIME24 and LiveCodeBench benchmarks. SRPO achieves this using the same base model as DeepSeek (i.e. Qwen2."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14286","kind":"arxiv","version":2},"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/2504.14286/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":"2026-07-05T10:52:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t0WZg6zw6tyYVb6xreyam3uVgN7HMi9bNpXe/ruK5XME9ueig17WNnyjYkvX8MybilFwWGkF6Xz95UYXZXm6Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T08:18:52.318348Z"},"content_sha256":"a85dead7c117f74e1401487c648cc325df56dbdadaeab78b63635b6602daea61","schema_version":"1.0","event_id":"sha256:a85dead7c117f74e1401487c648cc325df56dbdadaeab78b63635b6602daea61"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3DTCYULKYVGXK4XWPGLGXWECBR/bundle.json","state_url":"https://pith.science/pith/3DTCYULKYVGXK4XWPGLGXWECBR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3DTCYULKYVGXK4XWPGLGXWECBR/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":"2026-08-05T08:18:52Z","links":{"resolver":"https://pith.science/pith/3DTCYULKYVGXK4XWPGLGXWECBR","bundle":"https://pith.science/pith/3DTCYULKYVGXK4XWPGLGXWECBR/bundle.json","state":"https://pith.science/pith/3DTCYULKYVGXK4XWPGLGXWECBR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3DTCYULKYVGXK4XWPGLGXWECBR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:3DTCYULKYVGXK4XWPGLGXWECBR","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":"59165306c115a3a92737b3e4d132add337c31405bc06367f3ea5487d46d7a418","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-19T13:06:03Z","title_canon_sha256":"bc275c0153e229821940e265fe4dfe26621ef1ce9137773c4181b33aea0c7b2e"},"schema_version":"1.0","source":{"id":"2504.14286","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.14286","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"arxiv_version","alias_value":"2504.14286v2","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.14286","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"pith_short_12","alias_value":"3DTCYULKYVGX","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"pith_short_16","alias_value":"3DTCYULKYVGXK4XW","created_at":"2026-07-05T10:52:23Z"},{"alias_kind":"pith_short_8","alias_value":"3DTCYULK","created_at":"2026-07-05T10:52:23Z"}],"graph_snapshots":[{"event_id":"sha256:a85dead7c117f74e1401487c648cc325df56dbdadaeab78b63635b6602daea61","target":"graph","created_at":"2026-07-05T10:52:23Z","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/2504.14286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances of reasoning models, exemplified by OpenAI's o1 and DeepSeek's R1, highlight the significant potential of Reinforcement Learning (RL) to enhance the reasoning capabilities of Large Language Models (LLMs). However, replicating these advancements across diverse domains remains challenging due to limited methodological transparency. In this work, we present two-Staged history-Resampling Policy Optimization (SRPO), which surpasses the performance of DeepSeek-R1-Zero-32B on the AIME24 and LiveCodeBench benchmarks. SRPO achieves this using the same base model as DeepSeek (i.e. Qwen2.","authors_text":"Bin Chen, Bing Yu, Chaohang Wen, Chao Wang, Haotian Zhang, Jinghui Wang, Junyi Peng, Minglei Zhang, Shaojie Wang, Shimiao Jiang, Shiqi Kuang, Shouyu Yin, Wenhao Zhuang, Xiaojiang Zhang, Yinghan Cui, Zheng Lin, Zifei Cheng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-19T13:06:03Z","title":"SRPO: A Cross-Domain Implementation of Large-Scale Reinforcement Learning on LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.14286","kind":"arxiv","version":2},"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:ae05bd5281465e5d4d2232aad255b96d277378cd4ab46b169761bc31a8093330","target":"record","created_at":"2026-07-05T10:52:23Z","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":"59165306c115a3a92737b3e4d132add337c31405bc06367f3ea5487d46d7a418","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-19T13:06:03Z","title_canon_sha256":"bc275c0153e229821940e265fe4dfe26621ef1ce9137773c4181b33aea0c7b2e"},"schema_version":"1.0","source":{"id":"2504.14286","kind":"arxiv","version":2}},"canonical_sha256":"d8e62c516ac54d7572f679966bd8820c6f13a6f0c057abfb17f2fb907f8c5e9a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8e62c516ac54d7572f679966bd8820c6f13a6f0c057abfb17f2fb907f8c5e9a","first_computed_at":"2026-07-05T10:52:23.155763Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:23.155763Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"unxpNb/aRpgv/YAKYzk221d9+1JH5441wyJOAz/5qx9GgUSWpg+wIfEwwSX5G3ob0vH2mwylDccH/6xi+M7XDA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:23.156239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.14286","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae05bd5281465e5d4d2232aad255b96d277378cd4ab46b169761bc31a8093330","sha256:a85dead7c117f74e1401487c648cc325df56dbdadaeab78b63635b6602daea61"],"state_sha256":"807241d3a2f8ad70aa93f115f4785c4d28e66331b1d8c57faaba737dddf53977"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"B85lC0M/IS5xhzvlZoVyfJI6fdTppDZ0APCRe++gy8CauE1J2I5yj3XnxuOwREkXwNxow+ZBVxwMAvs8zCmVCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T08:18:52.323302Z","bundle_sha256":"853d0900fc15b3a34fd8cbf010d1c607debbbcf7b1913c0c2ab985f318b4e5cc"}}