{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SLS3LWPMUHVWTQ52WRVUVBST2W","short_pith_number":"pith:SLS3LWPM","canonical_record":{"source":{"id":"2605.23454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T10:09:28Z","cross_cats_sorted":[],"title_canon_sha256":"d02a9a14629b2376e0992fc97e01bb8ffa3f2dc493bfc9972e2fad415e32305d","abstract_canon_sha256":"8a3f4a6905bedccba8c2a53dd2039fd374a8cfebaa0450ff3141c574b30da523"},"schema_version":"1.0"},"canonical_sha256":"92e5b5d9eca1eb69c3bab46b4a8653d5820a968bb36f0a35fdb3280e9879da3f","source":{"kind":"arxiv","id":"2605.23454","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23454","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23454v1","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23454","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"pith_short_12","alias_value":"SLS3LWPMUHVW","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"pith_short_16","alias_value":"SLS3LWPMUHVWTQ52","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"pith_short_8","alias_value":"SLS3LWPM","created_at":"2026-05-25T02:01:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SLS3LWPMUHVWTQ52WRVUVBST2W","target":"record","payload":{"canonical_record":{"source":{"id":"2605.23454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T10:09:28Z","cross_cats_sorted":[],"title_canon_sha256":"d02a9a14629b2376e0992fc97e01bb8ffa3f2dc493bfc9972e2fad415e32305d","abstract_canon_sha256":"8a3f4a6905bedccba8c2a53dd2039fd374a8cfebaa0450ff3141c574b30da523"},"schema_version":"1.0"},"canonical_sha256":"92e5b5d9eca1eb69c3bab46b4a8653d5820a968bb36f0a35fdb3280e9879da3f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:01:55.040186Z","signature_b64":"iLmYhRRTpgMTH5DuiE29rMsJrwgA6E933EfAsp6Mda9DLpHw8yrQeZ8kz0UV6MSVkyzOT7uz+TLQi7T1RS0ZCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"92e5b5d9eca1eb69c3bab46b4a8653d5820a968bb36f0a35fdb3280e9879da3f","last_reissued_at":"2026-05-25T02:01:55.039556Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:01:55.039556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.23454","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":"2026-05-25T02:01:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k09QlL/N5r6PiiuwWGwj8dZjazhTdXKu0ia+DNqDcXKheJN1uw9nEB/x9e/0y1CQC/ItDUlzZqSrF84adWoVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:44:20.264094Z"},"content_sha256":"0e420e9c605700bda8c20656a52b7f7591864d3fa8b35decf9bcbddac6c41e57","schema_version":"1.0","event_id":"sha256:0e420e9c605700bda8c20656a52b7f7591864d3fa8b35decf9bcbddac6c41e57"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SLS3LWPMUHVWTQ52WRVUVBST2W","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dayiheng Liu, Fuli Feng, Keqin Bao, Moxin Li, Wenjie Wang, Xiaoyuan Li, Yichang Zhang, Yubo Ma","submitted_at":"2026-05-22T10:09:28Z","abstract_excerpt":"Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubric-based RL remains challenging: existing approaches often rely on expert-written rubrics and manually constructed question sets, while fixed task-level rubrics may fail to capture the evaluation requirements of individual questions. We propose ARES (Automated Rubric synthEsis for Scalable RL), a framework for automatically constructing rubric-based RL data at scale. Starting from raw pretraining documents, ARES conv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23454","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/2605.23454/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":"2026-05-25T02:01:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EB8zgf2OY7fBC4YtP8PYDammaEHpXETgNgD2yKGj2Ck2R9NQXqZBoLuAsuBiSohS0xQ9dhsnqO9aTPwh34kVDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T09:44:20.264947Z"},"content_sha256":"38a3198fe9a7d07e390525733ee7ef1577a147a6726fa1f894bbb4b18de544e3","schema_version":"1.0","event_id":"sha256:38a3198fe9a7d07e390525733ee7ef1577a147a6726fa1f894bbb4b18de544e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SLS3LWPMUHVWTQ52WRVUVBST2W/bundle.json","state_url":"https://pith.science/pith/SLS3LWPMUHVWTQ52WRVUVBST2W/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SLS3LWPMUHVWTQ52WRVUVBST2W/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":"2026-05-25T09:44:20Z","links":{"resolver":"https://pith.science/pith/SLS3LWPMUHVWTQ52WRVUVBST2W","bundle":"https://pith.science/pith/SLS3LWPMUHVWTQ52WRVUVBST2W/bundle.json","state":"https://pith.science/pith/SLS3LWPMUHVWTQ52WRVUVBST2W/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SLS3LWPMUHVWTQ52WRVUVBST2W/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SLS3LWPMUHVWTQ52WRVUVBST2W","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":"8a3f4a6905bedccba8c2a53dd2039fd374a8cfebaa0450ff3141c574b30da523","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T10:09:28Z","title_canon_sha256":"d02a9a14629b2376e0992fc97e01bb8ffa3f2dc493bfc9972e2fad415e32305d"},"schema_version":"1.0","source":{"id":"2605.23454","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.23454","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"arxiv_version","alias_value":"2605.23454v1","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.23454","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"pith_short_12","alias_value":"SLS3LWPMUHVW","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"pith_short_16","alias_value":"SLS3LWPMUHVWTQ52","created_at":"2026-05-25T02:01:55Z"},{"alias_kind":"pith_short_8","alias_value":"SLS3LWPM","created_at":"2026-05-25T02:01:55Z"}],"graph_snapshots":[{"event_id":"sha256:38a3198fe9a7d07e390525733ee7ef1577a147a6726fa1f894bbb4b18de544e3","target":"graph","created_at":"2026-05-25T02:01:55Z","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/2605.23454/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language models beyond tasks with automatically verifiable answers. However, scaling rubric-based RL remains challenging: existing approaches often rely on expert-written rubrics and manually constructed question sets, while fixed task-level rubrics may fail to capture the evaluation requirements of individual questions. We propose ARES (Automated Rubric synthEsis for Scalable RL), a framework for automatically constructing rubric-based RL data at scale. Starting from raw pretraining documents, ARES conv","authors_text":"Dayiheng Liu, Fuli Feng, Keqin Bao, Moxin Li, Wenjie Wang, Xiaoyuan Li, Yichang Zhang, Yubo Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T10:09:28Z","title":"ARES: Automated Rubric Synthesis for Scalable LLM Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.23454","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":"sha256:0e420e9c605700bda8c20656a52b7f7591864d3fa8b35decf9bcbddac6c41e57","target":"record","created_at":"2026-05-25T02:01:55Z","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":"8a3f4a6905bedccba8c2a53dd2039fd374a8cfebaa0450ff3141c574b30da523","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-22T10:09:28Z","title_canon_sha256":"d02a9a14629b2376e0992fc97e01bb8ffa3f2dc493bfc9972e2fad415e32305d"},"schema_version":"1.0","source":{"id":"2605.23454","kind":"arxiv","version":1}},"canonical_sha256":"92e5b5d9eca1eb69c3bab46b4a8653d5820a968bb36f0a35fdb3280e9879da3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"92e5b5d9eca1eb69c3bab46b4a8653d5820a968bb36f0a35fdb3280e9879da3f","first_computed_at":"2026-05-25T02:01:55.039556Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:01:55.039556Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iLmYhRRTpgMTH5DuiE29rMsJrwgA6E933EfAsp6Mda9DLpHw8yrQeZ8kz0UV6MSVkyzOT7uz+TLQi7T1RS0ZCw==","signature_status":"signed_v1","signed_at":"2026-05-25T02:01:55.040186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.23454","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0e420e9c605700bda8c20656a52b7f7591864d3fa8b35decf9bcbddac6c41e57","sha256:38a3198fe9a7d07e390525733ee7ef1577a147a6726fa1f894bbb4b18de544e3"],"state_sha256":"ec6f2203971b5f91cf952b85a09e9431d1396b84fc20cfb5be4631094b1374d6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q/CUGFrhfpintoSXhyZFx4QCCcLfdBwtAX5VZRpJ3aIyna8S8pE10DWSD9BJOyA6lY6sj5NCKg6zgnVXmudADQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T09:44:20.269050Z","bundle_sha256":"fe67202b9115924bef1c350f64817c5ffde402dd1a430cf36e51378ecc88072f"}}