{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LLK7TYZXSRII33SIHT4JVMONJ3","short_pith_number":"pith:LLK7TYZX","canonical_record":{"source":{"id":"2508.12790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-18T10:06:08Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8f87e9d165e5ec2859ddecc94483bfa375cb2737ecd356ecf3aac0cd604badda","abstract_canon_sha256":"afe0a52e4d30f07f695c3233e1c4c4362fec67ab7201af40321b3337701dbc2f"},"schema_version":"1.0"},"canonical_sha256":"5ad5f9e33794508dee483cf89ab1cd4ec74e5a35053427d637710f8d7445cbba","source":{"kind":"arxiv","id":"2508.12790","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12790","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12790v1","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12790","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"pith_short_12","alias_value":"LLK7TYZXSRII","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"pith_short_16","alias_value":"LLK7TYZXSRII33SI","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"pith_short_8","alias_value":"LLK7TYZX","created_at":"2026-07-05T11:55:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LLK7TYZXSRII33SIHT4JVMONJ3","target":"record","payload":{"canonical_record":{"source":{"id":"2508.12790","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-18T10:06:08Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"8f87e9d165e5ec2859ddecc94483bfa375cb2737ecd356ecf3aac0cd604badda","abstract_canon_sha256":"afe0a52e4d30f07f695c3233e1c4c4362fec67ab7201af40321b3337701dbc2f"},"schema_version":"1.0"},"canonical_sha256":"5ad5f9e33794508dee483cf89ab1cd4ec74e5a35053427d637710f8d7445cbba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:27.282186Z","signature_b64":"yLLt1ELxzGDDZO5QNa5m9ZY2gxPrLAX2D6KznjkwXnkEa5bNG++MCY401qQz1ZxjLXq8So3WvG4LTISkihanDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5ad5f9e33794508dee483cf89ab1cd4ec74e5a35053427d637710f8d7445cbba","last_reissued_at":"2026-07-05T11:55:27.281686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:27.281686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.12790","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":"2026-07-05T11:55:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0X6gSEDeIaNj8xNgkRE2XV00zzdrW59coaUxVovutLTapSjy4zKlUmSuj3mhnVcPdXLP62nHZVW5E5w+MISpDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T18:58:02.978168Z"},"content_sha256":"4a0b8bb54d5edf0929d3eb05db5692a51bdc2bfc173cbb79fae5a0932db8d745","schema_version":"1.0","event_id":"sha256:4a0b8bb54d5edf0929d3eb05db5692a51bdc2bfc173cbb79fae5a0932db8d745"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LLK7TYZXSRII33SIHT4JVMONJ3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reinforcement Learning with Rubric Anchors","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Guoshan Lu, Haokai Xu, Jianguo Li, Jiaqi Hu, Jiaxin Liu, Junbo Zhao, Peiyi Tu, Ru Peng, Tianyu Zhao, Wenyu Chen, Xiaomeng Hu, Xijun Gu, Yanmei Gu, Yihong Zhuang, Yuanyuan Wang, Yuzhuo Fu, Zenan Huang, Zeyu Qin, Zhanming Shen, Zhengkai Yang, Zhiting Fan","submitted_at":"2025-08-18T10:06:08Z","abstract_excerpt":"Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such as passing unit tests in code generation or matching correct answers in mathematical reasoning. While effective, this requirement largely confines RLVR to domains with automatically checkable outcomes. To overcome this, we extend the RLVR paradigm to open-ended tasks by integrating rubric-based rewards, where carefully designed rubrics serve as structured, m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12790","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/2508.12790/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":"2026-07-05T11:55:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nSdkkP7C6TrrLX05X2AMobPqdYtP03xVyv/IDJcrRDhmv6sKlZ4SV301713nUx+L4yy5TED5VwauU5moKb7wAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T18:58:02.978512Z"},"content_sha256":"808408c07edfad678064ab564442d31ccd78842480e7a13576820dcebdd889cd","schema_version":"1.0","event_id":"sha256:808408c07edfad678064ab564442d31ccd78842480e7a13576820dcebdd889cd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LLK7TYZXSRII33SIHT4JVMONJ3/bundle.json","state_url":"https://pith.science/pith/LLK7TYZXSRII33SIHT4JVMONJ3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LLK7TYZXSRII33SIHT4JVMONJ3/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":"2026-08-01T18:58:02Z","links":{"resolver":"https://pith.science/pith/LLK7TYZXSRII33SIHT4JVMONJ3","bundle":"https://pith.science/pith/LLK7TYZXSRII33SIHT4JVMONJ3/bundle.json","state":"https://pith.science/pith/LLK7TYZXSRII33SIHT4JVMONJ3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LLK7TYZXSRII33SIHT4JVMONJ3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LLK7TYZXSRII33SIHT4JVMONJ3","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":"afe0a52e4d30f07f695c3233e1c4c4362fec67ab7201af40321b3337701dbc2f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-18T10:06:08Z","title_canon_sha256":"8f87e9d165e5ec2859ddecc94483bfa375cb2737ecd356ecf3aac0cd604badda"},"schema_version":"1.0","source":{"id":"2508.12790","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.12790","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"arxiv_version","alias_value":"2508.12790v1","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.12790","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"pith_short_12","alias_value":"LLK7TYZXSRII","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"pith_short_16","alias_value":"LLK7TYZXSRII33SI","created_at":"2026-07-05T11:55:27Z"},{"alias_kind":"pith_short_8","alias_value":"LLK7TYZX","created_at":"2026-07-05T11:55:27Z"}],"graph_snapshots":[{"event_id":"sha256:808408c07edfad678064ab564442d31ccd78842480e7a13576820dcebdd889cd","target":"graph","created_at":"2026-07-05T11:55:27Z","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/2508.12790/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement Learning from Verifiable Rewards (RLVR) has emerged as a powerful paradigm for enhancing Large Language Models (LLMs), exemplified by the success of OpenAI's o-series. In RLVR, rewards are derived from verifiable signals-such as passing unit tests in code generation or matching correct answers in mathematical reasoning. While effective, this requirement largely confines RLVR to domains with automatically checkable outcomes. To overcome this, we extend the RLVR paradigm to open-ended tasks by integrating rubric-based rewards, where carefully designed rubrics serve as structured, m","authors_text":"Guoshan Lu, Haokai Xu, Jianguo Li, Jiaqi Hu, Jiaxin Liu, Junbo Zhao, Peiyi Tu, Ru Peng, Tianyu Zhao, Wenyu Chen, Xiaomeng Hu, Xijun Gu, Yanmei Gu, Yihong Zhuang, Yuanyuan Wang, Yuzhuo Fu, Zenan Huang, Zeyu Qin, Zhanming Shen, Zhengkai Yang, Zhiting Fan","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-18T10:06:08Z","title":"Reinforcement Learning with Rubric Anchors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.12790","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":"sha256:4a0b8bb54d5edf0929d3eb05db5692a51bdc2bfc173cbb79fae5a0932db8d745","target":"record","created_at":"2026-07-05T11:55:27Z","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":"afe0a52e4d30f07f695c3233e1c4c4362fec67ab7201af40321b3337701dbc2f","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-18T10:06:08Z","title_canon_sha256":"8f87e9d165e5ec2859ddecc94483bfa375cb2737ecd356ecf3aac0cd604badda"},"schema_version":"1.0","source":{"id":"2508.12790","kind":"arxiv","version":1}},"canonical_sha256":"5ad5f9e33794508dee483cf89ab1cd4ec74e5a35053427d637710f8d7445cbba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ad5f9e33794508dee483cf89ab1cd4ec74e5a35053427d637710f8d7445cbba","first_computed_at":"2026-07-05T11:55:27.281686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:55:27.281686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yLLt1ELxzGDDZO5QNa5m9ZY2gxPrLAX2D6KznjkwXnkEa5bNG++MCY401qQz1ZxjLXq8So3WvG4LTISkihanDw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:55:27.282186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.12790","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a0b8bb54d5edf0929d3eb05db5692a51bdc2bfc173cbb79fae5a0932db8d745","sha256:808408c07edfad678064ab564442d31ccd78842480e7a13576820dcebdd889cd"],"state_sha256":"58cbc93b978aa31c5b2f951a73232a06a49df9639aac88ae59a9d2b5c3651de0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pDJbptWbtOICQabmdkX5TR8c92FDTg27kJsdHcXZfq1KMPohMlWDSxZAlYhiP+AvYI/4RQXjqpQmXXeeqOStDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T18:58:02.982422Z","bundle_sha256":"c04c9ab0a61254df2eccdc5267e8761cc9b6a2ef12f35fcc7ad8de87870ca60e"}}