{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KF5H77DKEOA6BUKU6DD7N2S5DX","short_pith_number":"pith:KF5H77DK","schema_version":"1.0","canonical_sha256":"517a7ffc6a2381e0d154f0c7f6ea5d1decaed6d737e0c4f8cbcde650aa9efe4b","source":{"kind":"arxiv","id":"2607.24833","version":1},"attestation_state":"computed","paper":{"title":"AdaKP: Online Adaptive Knowledge-Point Selection for Reasoning-Oriented Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunqiang Run, Zhenyu Zhao, Zibin Meng","submitted_at":"2026-07-23T15:12:39Z","abstract_excerpt":"Reinforcement learning with verifiable rewards is a powerful paradigm for eliciting reasoning in large language models, yet it suffers from severe reward sparsity on competition-level mathematics. A common remedy injects atomic knowledge points (KPs) - short natural-language hints distilled from gold solutions - into the prompt. Existing methods, however, either fix this selection once offline or merely scale the monolithic quantity of injected text, leaving untouched the most informative axis of choice: which subset of atomic KPs to inject, and when. We introduce AdaKP, an online selector tha"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.24833","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-07-23T15:12:39Z","cross_cats_sorted":[],"title_canon_sha256":"49b61cc8f202a5bb3959b12cbfbeafc8fb9b3baf30be5f6854eeca222dcc701a","abstract_canon_sha256":"ed862a29f5e2abb72b5f9df986e31b1c33b7b38ea146905c7581c1ee665a3975"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T00:24:46.994913Z","signature_b64":"BKWir6WhurcsR5ikUBfeGTuVj0TGFDp4+bfpGwZ39xsxcSswv63ZUSxaM+tr/JJ4IlITMuEAIXiuGZBrPkUKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"517a7ffc6a2381e0d154f0c7f6ea5d1decaed6d737e0c4f8cbcde650aa9efe4b","last_reissued_at":"2026-07-29T00:24:46.994056Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T00:24:46.994056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AdaKP: Online Adaptive Knowledge-Point Selection for Reasoning-Oriented Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chunqiang Run, Zhenyu Zhao, Zibin Meng","submitted_at":"2026-07-23T15:12:39Z","abstract_excerpt":"Reinforcement learning with verifiable rewards is a powerful paradigm for eliciting reasoning in large language models, yet it suffers from severe reward sparsity on competition-level mathematics. A common remedy injects atomic knowledge points (KPs) - short natural-language hints distilled from gold solutions - into the prompt. Existing methods, however, either fix this selection once offline or merely scale the monolithic quantity of injected text, leaving untouched the most informative axis of choice: which subset of atomic KPs to inject, and when. We introduce AdaKP, an online selector tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24833","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/2607.24833/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.24833","created_at":"2026-07-29T00:24:46.994498+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.24833v1","created_at":"2026-07-29T00:24:46.994498+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24833","created_at":"2026-07-29T00:24:46.994498+00:00"},{"alias_kind":"pith_short_12","alias_value":"KF5H77DKEOA6","created_at":"2026-07-29T00:24:46.994498+00:00"},{"alias_kind":"pith_short_16","alias_value":"KF5H77DKEOA6BUKU","created_at":"2026-07-29T00:24:46.994498+00:00"},{"alias_kind":"pith_short_8","alias_value":"KF5H77DK","created_at":"2026-07-29T00:24:46.994498+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KF5H77DKEOA6BUKU6DD7N2S5DX","json":"https://pith.science/pith/KF5H77DKEOA6BUKU6DD7N2S5DX.json","graph_json":"https://pith.science/api/pith-number/KF5H77DKEOA6BUKU6DD7N2S5DX/graph.json","events_json":"https://pith.science/api/pith-number/KF5H77DKEOA6BUKU6DD7N2S5DX/events.json","paper":"https://pith.science/paper/KF5H77DK"},"agent_actions":{"view_html":"https://pith.science/pith/KF5H77DKEOA6BUKU6DD7N2S5DX","download_json":"https://pith.science/pith/KF5H77DKEOA6BUKU6DD7N2S5DX.json","view_paper":"https://pith.science/paper/KF5H77DK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.24833&json=true","fetch_graph":"https://pith.science/api/pith-number/KF5H77DKEOA6BUKU6DD7N2S5DX/graph.json","fetch_events":"https://pith.science/api/pith-number/KF5H77DKEOA6BUKU6DD7N2S5DX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KF5H77DKEOA6BUKU6DD7N2S5DX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KF5H77DKEOA6BUKU6DD7N2S5DX/action/storage_attestation","attest_author":"https://pith.science/pith/KF5H77DKEOA6BUKU6DD7N2S5DX/action/author_attestation","sign_citation":"https://pith.science/pith/KF5H77DKEOA6BUKU6DD7N2S5DX/action/citation_signature","submit_replication":"https://pith.science/pith/KF5H77DKEOA6BUKU6DD7N2S5DX/action/replication_record"}},"created_at":"2026-07-29T00:24:46.994498+00:00","updated_at":"2026-07-29T00:24:46.994498+00:00"}