{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LZD3HADYG4W7ELFLDWKGDUY4RK","short_pith_number":"pith:LZD3HADY","canonical_record":{"source":{"id":"2508.16949","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-23T08:47:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98cf71f50390447705e89eb4bf5c28dcfa1c9406fc85b2313fe1a3f7634f3964","abstract_canon_sha256":"61e33567b7f2b81637571ec782f35e503117d514c783dc978a5775c9edda24a3"},"schema_version":"1.0"},"canonical_sha256":"5e47b38078372df22cab1d9461d31c8aa74b3d372ab8ea383c82a7d3084069d8","source":{"kind":"arxiv","id":"2508.16949","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.16949","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2508.16949v7","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16949","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"LZD3HADYG4W7","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"LZD3HADYG4W7ELFL","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"LZD3HADY","created_at":"2026-08-04T01:51:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LZD3HADYG4W7ELFLDWKGDUY4RK","target":"record","payload":{"canonical_record":{"source":{"id":"2508.16949","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-23T08:47:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"98cf71f50390447705e89eb4bf5c28dcfa1c9406fc85b2313fe1a3f7634f3964","abstract_canon_sha256":"61e33567b7f2b81637571ec782f35e503117d514c783dc978a5775c9edda24a3"},"schema_version":"1.0"},"canonical_sha256":"5e47b38078372df22cab1d9461d31c8aa74b3d372ab8ea383c82a7d3084069d8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:51:47.725226Z","signature_b64":"fL5TudENkGdjMLzZeTM47vBtwkyRnPyc4sAmm6+QFpmejou77YdUecFBDSyd88T86cy0QQpR04djtiLcDKnGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5e47b38078372df22cab1d9461d31c8aa74b3d372ab8ea383c82a7d3084069d8","last_reissued_at":"2026-08-04T01:51:47.723447Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:51:47.723447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2508.16949","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-08-04T01:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YhZ83QZRn0KckawCGKoDpZbouCD9JKZ7e4Ysu7khxlmVDbh1K+n//3jIJH7f0w7y6D9eMbAHlM3da7rNiFzCDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:12:59.338965Z"},"content_sha256":"01fc8ba720d2085073389b71cde943c0162777f6b24a0e049628f3c8ef24664c","schema_version":"1.0","event_id":"sha256:01fc8ba720d2085073389b71cde943c0162777f6b24a0e049628f3c8ef24664c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LZD3HADYG4W7ELFLDWKGDUY4RK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Hengtong Lu, Jiale Zhao, Jianwei Lv, Jingwen Yang, Kongcheng Zhang, Mingli Song, Shunyu Liu, Sunzhu Li, Tongya Zheng, Wei Chen, Wenkai Fang, Yang Zhou, Yan Xie, Yihe Zhou","submitted_at":"2025-08-23T08:47:31Z","abstract_excerpt":"Recent advances in Large Language Models (LLMs) have underscored the potential of Reinforcement Learning (RL) to facilitate the emergence of reasoning capabilities. Despite the encouraging results, a fundamental dilemma persists as RL improvement relies on learning from high-quality samples, yet the exploration for such samples remains bounded by the inherent limitations of LLMs. This, in effect, creates an undesirable cycle in which what cannot be explored cannot be learned. In this work, we propose Rubric-Scaffolded Reinforcement Learning (RuscaRL), a novel instructional scaffolding framewor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16949","kind":"arxiv","version":7},"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/2508.16949/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":"2026-08-04T01:51:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"emCb8A+pOH2qGGJbpEjBJ9iUDbx6f/t2Jcz0FyCV+lbHuaobGxAZKkGU+dRbmYZNB4XKS0VSeWdB1MRpT/bVAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T03:12:59.339448Z"},"content_sha256":"f43103096e039f71530865ff9717bf4c67e1e0fb0c1590cfe58a5555dde0aa8b","schema_version":"1.0","event_id":"sha256:f43103096e039f71530865ff9717bf4c67e1e0fb0c1590cfe58a5555dde0aa8b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LZD3HADYG4W7ELFLDWKGDUY4RK/bundle.json","state_url":"https://pith.science/pith/LZD3HADYG4W7ELFLDWKGDUY4RK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LZD3HADYG4W7ELFLDWKGDUY4RK/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":"2026-08-05T03:12:59Z","links":{"resolver":"https://pith.science/pith/LZD3HADYG4W7ELFLDWKGDUY4RK","bundle":"https://pith.science/pith/LZD3HADYG4W7ELFLDWKGDUY4RK/bundle.json","state":"https://pith.science/pith/LZD3HADYG4W7ELFLDWKGDUY4RK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LZD3HADYG4W7ELFLDWKGDUY4RK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LZD3HADYG4W7ELFLDWKGDUY4RK","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":"61e33567b7f2b81637571ec782f35e503117d514c783dc978a5775c9edda24a3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-23T08:47:31Z","title_canon_sha256":"98cf71f50390447705e89eb4bf5c28dcfa1c9406fc85b2313fe1a3f7634f3964"},"schema_version":"1.0","source":{"id":"2508.16949","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.16949","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"arxiv_version","alias_value":"2508.16949v7","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16949","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"pith_short_12","alias_value":"LZD3HADYG4W7","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"pith_short_16","alias_value":"LZD3HADYG4W7ELFL","created_at":"2026-08-04T01:51:47Z"},{"alias_kind":"pith_short_8","alias_value":"LZD3HADY","created_at":"2026-08-04T01:51:47Z"}],"graph_snapshots":[{"event_id":"sha256:f43103096e039f71530865ff9717bf4c67e1e0fb0c1590cfe58a5555dde0aa8b","target":"graph","created_at":"2026-08-04T01:51:47Z","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/2508.16949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Large Language Models (LLMs) have underscored the potential of Reinforcement Learning (RL) to facilitate the emergence of reasoning capabilities. Despite the encouraging results, a fundamental dilemma persists as RL improvement relies on learning from high-quality samples, yet the exploration for such samples remains bounded by the inherent limitations of LLMs. This, in effect, creates an undesirable cycle in which what cannot be explored cannot be learned. In this work, we propose Rubric-Scaffolded Reinforcement Learning (RuscaRL), a novel instructional scaffolding framewor","authors_text":"Hengtong Lu, Jiale Zhao, Jianwei Lv, Jingwen Yang, Kongcheng Zhang, Mingli Song, Shunyu Liu, Sunzhu Li, Tongya Zheng, Wei Chen, Wenkai Fang, Yang Zhou, Yan Xie, Yihe Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-23T08:47:31Z","title":"Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for General LLM Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16949","kind":"arxiv","version":7},"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":"sha256:01fc8ba720d2085073389b71cde943c0162777f6b24a0e049628f3c8ef24664c","target":"record","created_at":"2026-08-04T01:51:47Z","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":"61e33567b7f2b81637571ec782f35e503117d514c783dc978a5775c9edda24a3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-23T08:47:31Z","title_canon_sha256":"98cf71f50390447705e89eb4bf5c28dcfa1c9406fc85b2313fe1a3f7634f3964"},"schema_version":"1.0","source":{"id":"2508.16949","kind":"arxiv","version":7}},"canonical_sha256":"5e47b38078372df22cab1d9461d31c8aa74b3d372ab8ea383c82a7d3084069d8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5e47b38078372df22cab1d9461d31c8aa74b3d372ab8ea383c82a7d3084069d8","first_computed_at":"2026-08-04T01:51:47.723447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:51:47.723447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fL5TudENkGdjMLzZeTM47vBtwkyRnPyc4sAmm6+QFpmejou77YdUecFBDSyd88T86cy0QQpR04djtiLcDKnGBA==","signature_status":"signed_v1","signed_at":"2026-08-04T01:51:47.725226Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.16949","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:01fc8ba720d2085073389b71cde943c0162777f6b24a0e049628f3c8ef24664c","sha256:f43103096e039f71530865ff9717bf4c67e1e0fb0c1590cfe58a5555dde0aa8b"],"state_sha256":"b2d53e9a8f708a8f50875c1e0b9b750b52136e390ea1ddbaa2ff33fe28de6395"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3Ok5JtPafOnVuHYfsBPOcZZ/Me7FsQRzpa8wZzQIS7sSpOW+X6xEErBI0TSnjiGApD9PrvUuaN2XEmvhAnxGDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T03:12:59.342504Z","bundle_sha256":"975c3295435af7d29899b65eb9ce1fce65fc75644b24e0252a8d34851b344fc0"}}