{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WGZKCZ5BXO4QVFTR42SJKU3QD2","short_pith_number":"pith:WGZKCZ5B","canonical_record":{"source":{"id":"2606.22317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T03:15:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"afa24088e95e328a281f9c785346e94b80d2b77bbde206c2eb86069063230328","abstract_canon_sha256":"0e6fef62464afcc14607c4bc69fed7b8b7cb488873a767a8e88012f11aeedbc4"},"schema_version":"1.0"},"canonical_sha256":"b1b2a167a1bbb90a9671e6a49553701eaf66d6473d5da5da7e1f6e4d2ae82a61","source":{"kind":"arxiv","id":"2606.22317","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22317","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22317v1","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22317","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"pith_short_12","alias_value":"WGZKCZ5BXO4Q","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"pith_short_16","alias_value":"WGZKCZ5BXO4QVFTR","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"pith_short_8","alias_value":"WGZKCZ5B","created_at":"2026-06-23T02:13:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WGZKCZ5BXO4QVFTR42SJKU3QD2","target":"record","payload":{"canonical_record":{"source":{"id":"2606.22317","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T03:15:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"afa24088e95e328a281f9c785346e94b80d2b77bbde206c2eb86069063230328","abstract_canon_sha256":"0e6fef62464afcc14607c4bc69fed7b8b7cb488873a767a8e88012f11aeedbc4"},"schema_version":"1.0"},"canonical_sha256":"b1b2a167a1bbb90a9671e6a49553701eaf66d6473d5da5da7e1f6e4d2ae82a61","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:34.743960Z","signature_b64":"0oEvYXt6Un/YxyRNPol8iu1NffIpe0J6xgmh3w7eCZbWAngfTSZWkatyEiMAIjVCVWLhoeS6hJgYsgPjOYnOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1b2a167a1bbb90a9671e6a49553701eaf66d6473d5da5da7e1f6e4d2ae82a61","last_reissued_at":"2026-06-23T02:13:34.743550Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:34.743550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.22317","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":"2026-06-23T02:13:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"++lzKxt9EbRQadfQSdVYA82cN2ZJYhX2sxp/p9528iI7YzKvi3OltUtZRTNq9NuT2SdKUydw0wN2jzgkKs2iBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T14:10:10.130152Z"},"content_sha256":"9b372ad782aa05002cedfb6fbba6a127fab75f3d5347af2aec6f1b6b6836b73d","schema_version":"1.0","event_id":"sha256:9b372ad782aa05002cedfb6fbba6a127fab75f3d5347af2aec6f1b6b6836b73d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WGZKCZ5BXO4QVFTR42SJKU3QD2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Guocong Li, Jintai Chen, Pengxiang Cai, Qingyuan Zeng, Tianchen Fang, Xiaohan Li","submitted_at":"2026-06-21T03:15:25Z","abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) is widely viewed as a promising path toward continuously improving large language models. Recent works, however, suggest that mainstream RLVR often reallocates sampling probabilities among trajectories already present in the base model: it can improve sampling efficiency, reflected by higher pass@1 scores, but yields limited gains, and can even decrease pass@k scores when k is large, and therefore may fail to expand the base model's reasoning capacity boundary. In this paper, we present a boundary-aware Curriculum RL approach to move beyond"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22317","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/2606.22317/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":"2026-06-23T02:13:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y6+5nhEJ3GZwPvbPKVYYAhCmyQV2l+ZfszGUvNVugaqRB9LPBKbV4hf7dGn4xStxIgev3eWgFU/Dit4BHjrIDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T14:10:10.130539Z"},"content_sha256":"30e7b4b7d0e2aead34c4b14b54ddacb2cc5e65e896883e348c4aa3ecfdf16776","schema_version":"1.0","event_id":"sha256:30e7b4b7d0e2aead34c4b14b54ddacb2cc5e65e896883e348c4aa3ecfdf16776"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WGZKCZ5BXO4QVFTR42SJKU3QD2/bundle.json","state_url":"https://pith.science/pith/WGZKCZ5BXO4QVFTR42SJKU3QD2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WGZKCZ5BXO4QVFTR42SJKU3QD2/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":"2026-06-30T14:10:10Z","links":{"resolver":"https://pith.science/pith/WGZKCZ5BXO4QVFTR42SJKU3QD2","bundle":"https://pith.science/pith/WGZKCZ5BXO4QVFTR42SJKU3QD2/bundle.json","state":"https://pith.science/pith/WGZKCZ5BXO4QVFTR42SJKU3QD2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WGZKCZ5BXO4QVFTR42SJKU3QD2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WGZKCZ5BXO4QVFTR42SJKU3QD2","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":"0e6fef62464afcc14607c4bc69fed7b8b7cb488873a767a8e88012f11aeedbc4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T03:15:25Z","title_canon_sha256":"afa24088e95e328a281f9c785346e94b80d2b77bbde206c2eb86069063230328"},"schema_version":"1.0","source":{"id":"2606.22317","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.22317","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.22317v1","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.22317","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"pith_short_12","alias_value":"WGZKCZ5BXO4Q","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"pith_short_16","alias_value":"WGZKCZ5BXO4QVFTR","created_at":"2026-06-23T02:13:34Z"},{"alias_kind":"pith_short_8","alias_value":"WGZKCZ5B","created_at":"2026-06-23T02:13:34Z"}],"graph_snapshots":[{"event_id":"sha256:30e7b4b7d0e2aead34c4b14b54ddacb2cc5e65e896883e348c4aa3ecfdf16776","target":"graph","created_at":"2026-06-23T02:13:34Z","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/2606.22317/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reinforcement learning with verifiable rewards (RLVR) is widely viewed as a promising path toward continuously improving large language models. Recent works, however, suggest that mainstream RLVR often reallocates sampling probabilities among trajectories already present in the base model: it can improve sampling efficiency, reflected by higher pass@1 scores, but yields limited gains, and can even decrease pass@k scores when k is large, and therefore may fail to expand the base model's reasoning capacity boundary. In this paper, we present a boundary-aware Curriculum RL approach to move beyond","authors_text":"Guocong Li, Jintai Chen, Pengxiang Cai, Qingyuan Zeng, Tianchen Fang, Xiaohan Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T03:15:25Z","title":"Curriculum Reinforcement Learning Can Incentivize Reasoning Capacity in LLMs Beyond the Base Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.22317","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":"sha256:9b372ad782aa05002cedfb6fbba6a127fab75f3d5347af2aec6f1b6b6836b73d","target":"record","created_at":"2026-06-23T02:13:34Z","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":"0e6fef62464afcc14607c4bc69fed7b8b7cb488873a767a8e88012f11aeedbc4","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-21T03:15:25Z","title_canon_sha256":"afa24088e95e328a281f9c785346e94b80d2b77bbde206c2eb86069063230328"},"schema_version":"1.0","source":{"id":"2606.22317","kind":"arxiv","version":1}},"canonical_sha256":"b1b2a167a1bbb90a9671e6a49553701eaf66d6473d5da5da7e1f6e4d2ae82a61","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b1b2a167a1bbb90a9671e6a49553701eaf66d6473d5da5da7e1f6e4d2ae82a61","first_computed_at":"2026-06-23T02:13:34.743550Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T02:13:34.743550Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0oEvYXt6Un/YxyRNPol8iu1NffIpe0J6xgmh3w7eCZbWAngfTSZWkatyEiMAIjVCVWLhoeS6hJgYsgPjOYnOAQ==","signature_status":"signed_v1","signed_at":"2026-06-23T02:13:34.743960Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.22317","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9b372ad782aa05002cedfb6fbba6a127fab75f3d5347af2aec6f1b6b6836b73d","sha256:30e7b4b7d0e2aead34c4b14b54ddacb2cc5e65e896883e348c4aa3ecfdf16776"],"state_sha256":"3566e14a21bd573c0d76620dde814d8c30c995512d6ae94ba4fa3b87f6cb48fc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7BEyKG2M8ONu87u6pBhZ4n49knD/f9TC1ZNUr1Z/3twaL1N7nD3qFDOSnrhDKk3EzDV8KBji7/axeYc/qB04CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T14:10:10.132565Z","bundle_sha256":"7ff215ba5fa6a5cebe256578b5e71997d3bc94f7dec5424b5f047f8cf7cce3f8"}}