{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J5UDUKID5O33XT3I4MWTG7ULDL","short_pith_number":"pith:J5UDUKID","canonical_record":{"source":{"id":"2508.20722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-28T12:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"bcddcd8b020addd6fbe514ac58e3f91e7f5120cb25c4b711fe6d200db51bdfe6","abstract_canon_sha256":"f393ddf1dcfb4d47fb280118d000a86224443443939f782024e8222be074e2f0"},"schema_version":"1.0"},"canonical_sha256":"4f683a2903ebb7bbcf68e32d337e8b1ac75aa868f5ac2c71cf1770bc994179e5","source":{"kind":"arxiv","id":"2508.20722","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20722","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20722v1","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20722","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"pith_short_12","alias_value":"J5UDUKID5O33","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"pith_short_16","alias_value":"J5UDUKID5O33XT3I","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"pith_short_8","alias_value":"J5UDUKID","created_at":"2026-07-05T12:01:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J5UDUKID5O33XT3I4MWTG7ULDL","target":"record","payload":{"canonical_record":{"source":{"id":"2508.20722","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-28T12:45:25Z","cross_cats_sorted":[],"title_canon_sha256":"bcddcd8b020addd6fbe514ac58e3f91e7f5120cb25c4b711fe6d200db51bdfe6","abstract_canon_sha256":"f393ddf1dcfb4d47fb280118d000a86224443443939f782024e8222be074e2f0"},"schema_version":"1.0"},"canonical_sha256":"4f683a2903ebb7bbcf68e32d337e8b1ac75aa868f5ac2c71cf1770bc994179e5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:01:09.651018Z","signature_b64":"/x0MhX6N+J2juAQNQkfOstT2aSoLt9NRIYzl4e4P9fq1BVLWnYpw4Y4VDhLAuAFEizgxpd5Rc0LfAPtpmybCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4f683a2903ebb7bbcf68e32d337e8b1ac75aa868f5ac2c71cf1770bc994179e5","last_reissued_at":"2026-07-05T12:01:09.650534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:01:09.650534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.20722","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":"2026-07-05T12:01:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DW4Bc386FRQfJ8GQHct9TMOWoS/U9pUR6591h65B8a3kYfcwOjeZw7EdMF9nzvFr++sqEdT81/Y87lAizvHpBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T22:44:47.110728Z"},"content_sha256":"f091d16a89450481ce385eafd5a6f6dfc1011ea80ea412d720bba1b0d235633c","schema_version":"1.0","event_id":"sha256:f091d16a89450481ce385eafd5a6f6dfc1011ea80ea412d720bba1b0d235633c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J5UDUKID5O33XT3I4MWTG7ULDL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"rStar2-Agent: Agentic Reasoning Technical Report","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bingcheng Dong, Bowen Zhang, Buze Zhang, Fan Yang, Li Lyna Zhang, Mao Yang, Ning Shang, Scarlett Li, Weijiang Xu, Xinyu Guan, XuDong Zhou, Yifei Liu, Ying Xin, Yi Zhu, Ziming Miao","submitted_at":"2025-08-28T12:45:25Z","abstract_excerpt":"We introduce rStar2-Agent, a 14B math reasoning model trained with agentic reinforcement learning to achieve frontier-level performance. Beyond current long CoT, the model demonstrates advanced cognitive behaviors, such as thinking carefully before using Python coding tools and reflecting on code execution feedback to autonomously explore, verify, and refine intermediate steps in complex problem-solving. This capability is enabled through three key innovations that makes agentic RL effective at scale: (i) an efficient RL infrastructure with a reliable Python code environment that supports high"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20722","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/2508.20722/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":"2026-07-05T12:01:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hYphRa6ArJ9oFbGdJBL/XRFgHpkxubaliONpJ2b/zSYXYXduNmN+NjOKQCuTg+zOQCW9PCYLvf0HEx7BqqNHDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-27T22:44:47.111110Z"},"content_sha256":"5860bb10e850d22900777d1ae9be83e81aea5972cf7abf63d8c31de2695e2528","schema_version":"1.0","event_id":"sha256:5860bb10e850d22900777d1ae9be83e81aea5972cf7abf63d8c31de2695e2528"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J5UDUKID5O33XT3I4MWTG7ULDL/bundle.json","state_url":"https://pith.science/pith/J5UDUKID5O33XT3I4MWTG7ULDL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J5UDUKID5O33XT3I4MWTG7ULDL/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":"2026-07-27T22:44:47Z","links":{"resolver":"https://pith.science/pith/J5UDUKID5O33XT3I4MWTG7ULDL","bundle":"https://pith.science/pith/J5UDUKID5O33XT3I4MWTG7ULDL/bundle.json","state":"https://pith.science/pith/J5UDUKID5O33XT3I4MWTG7ULDL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J5UDUKID5O33XT3I4MWTG7ULDL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J5UDUKID5O33XT3I4MWTG7ULDL","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":"f393ddf1dcfb4d47fb280118d000a86224443443939f782024e8222be074e2f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-28T12:45:25Z","title_canon_sha256":"bcddcd8b020addd6fbe514ac58e3f91e7f5120cb25c4b711fe6d200db51bdfe6"},"schema_version":"1.0","source":{"id":"2508.20722","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20722","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20722v1","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20722","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"pith_short_12","alias_value":"J5UDUKID5O33","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"pith_short_16","alias_value":"J5UDUKID5O33XT3I","created_at":"2026-07-05T12:01:09Z"},{"alias_kind":"pith_short_8","alias_value":"J5UDUKID","created_at":"2026-07-05T12:01:09Z"}],"graph_snapshots":[{"event_id":"sha256:5860bb10e850d22900777d1ae9be83e81aea5972cf7abf63d8c31de2695e2528","target":"graph","created_at":"2026-07-05T12:01:09Z","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/2508.20722/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce rStar2-Agent, a 14B math reasoning model trained with agentic reinforcement learning to achieve frontier-level performance. Beyond current long CoT, the model demonstrates advanced cognitive behaviors, such as thinking carefully before using Python coding tools and reflecting on code execution feedback to autonomously explore, verify, and refine intermediate steps in complex problem-solving. This capability is enabled through three key innovations that makes agentic RL effective at scale: (i) an efficient RL infrastructure with a reliable Python code environment that supports high","authors_text":"Bingcheng Dong, Bowen Zhang, Buze Zhang, Fan Yang, Li Lyna Zhang, Mao Yang, Ning Shang, Scarlett Li, Weijiang Xu, Xinyu Guan, XuDong Zhou, Yifei Liu, Ying Xin, Yi Zhu, Ziming Miao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-28T12:45:25Z","title":"rStar2-Agent: Agentic Reasoning Technical Report"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20722","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:f091d16a89450481ce385eafd5a6f6dfc1011ea80ea412d720bba1b0d235633c","target":"record","created_at":"2026-07-05T12:01:09Z","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":"f393ddf1dcfb4d47fb280118d000a86224443443939f782024e8222be074e2f0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-28T12:45:25Z","title_canon_sha256":"bcddcd8b020addd6fbe514ac58e3f91e7f5120cb25c4b711fe6d200db51bdfe6"},"schema_version":"1.0","source":{"id":"2508.20722","kind":"arxiv","version":1}},"canonical_sha256":"4f683a2903ebb7bbcf68e32d337e8b1ac75aa868f5ac2c71cf1770bc994179e5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f683a2903ebb7bbcf68e32d337e8b1ac75aa868f5ac2c71cf1770bc994179e5","first_computed_at":"2026-07-05T12:01:09.650534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:01:09.650534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/x0MhX6N+J2juAQNQkfOstT2aSoLt9NRIYzl4e4P9fq1BVLWnYpw4Y4VDhLAuAFEizgxpd5Rc0LfAPtpmybCDw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:01:09.651018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20722","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f091d16a89450481ce385eafd5a6f6dfc1011ea80ea412d720bba1b0d235633c","sha256:5860bb10e850d22900777d1ae9be83e81aea5972cf7abf63d8c31de2695e2528"],"state_sha256":"495ef9a2c157a4095e0cef7ad4c0ac91867844b605fd0163cd05f58b2f4c235e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"woaO7Bwr21cWRQt7CDV65Thdz9br29Ra6VcsfKG09p/82NNYxV6g8EEMgdWaOuiRma98cJHDTl+X7o0boyXLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-27T22:44:47.113611Z","bundle_sha256":"3978c468a921e0d0f578edd144e04849dd5de28e0261cc0344c793a11e9f1b6d"}}