{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NCDLRKUICFOPKIT3TQZF25L4AF","short_pith_number":"pith:NCDLRKUI","schema_version":"1.0","canonical_sha256":"6886b8aa88115cf5227b9c325d757c0176392e3ecb85845f3501ed74af8e9128","source":{"kind":"arxiv","id":"2607.07674","version":1},"attestation_state":"computed","paper":{"title":"Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Vladislav Beliaev","submitted_at":"2026-07-08T17:32:58Z","abstract_excerpt":"Group Relative Policy Optimization (GRPO) stalls on a model's hardest problems: when no rollout in a group succeeds, the group-relative advantages vanish and the problem contributes no gradient, wasting the frontier examples we most want to learn from. Prepending a correct prefix of a reference solution raises the success rate, making prefix length a continuous knob on difficulty. Concurrent methods set the knob once; AdaPrefix-GRPO turns it into a feedback controller: throughout training it adjusts how much of the solution each problem gets, holding its success rate near 50%, where GRPO's gra"},"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":"2607.07674","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-08T17:32:58Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5b98bc2914a72c7a86c37b9e3250ee7ae6c927d850d2315c21a0b4bb28b303e0","abstract_canon_sha256":"b6adff8f9f782c4b4998be51e1dc46c8cf3bcc482a1917e7b7243f4d454fdd5b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:38.711798Z","signature_b64":"odhO5w43G4PZwAhub9HzVCvt4H1YKRALt7gXZVD4X5yAmekQj3Y6g3F1kTvpfHSzvJ/nOl5Zvu0RBXl/r1yjCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6886b8aa88115cf5227b9c325d757c0176392e3ecb85845f3501ed74af8e9128","last_reissued_at":"2026-07-09T01:20:38.711391Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:38.711391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Max Out GRPO Signal: Adaptive Trace Prefix Control for Hard Reasoning Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Vladislav Beliaev","submitted_at":"2026-07-08T17:32:58Z","abstract_excerpt":"Group Relative Policy Optimization (GRPO) stalls on a model's hardest problems: when no rollout in a group succeeds, the group-relative advantages vanish and the problem contributes no gradient, wasting the frontier examples we most want to learn from. Prepending a correct prefix of a reference solution raises the success rate, making prefix length a continuous knob on difficulty. Concurrent methods set the knob once; AdaPrefix-GRPO turns it into a feedback controller: throughout training it adjusts how much of the solution each problem gets, holding its success rate near 50%, where GRPO's gra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07674","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/2607.07674/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":"2607.07674","created_at":"2026-07-09T01:20:38.711453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.07674v1","created_at":"2026-07-09T01:20:38.711453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07674","created_at":"2026-07-09T01:20:38.711453+00:00"},{"alias_kind":"pith_short_12","alias_value":"NCDLRKUICFOP","created_at":"2026-07-09T01:20:38.711453+00:00"},{"alias_kind":"pith_short_16","alias_value":"NCDLRKUICFOPKIT3","created_at":"2026-07-09T01:20:38.711453+00:00"},{"alias_kind":"pith_short_8","alias_value":"NCDLRKUI","created_at":"2026-07-09T01:20:38.711453+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/NCDLRKUICFOPKIT3TQZF25L4AF","json":"https://pith.science/pith/NCDLRKUICFOPKIT3TQZF25L4AF.json","graph_json":"https://pith.science/api/pith-number/NCDLRKUICFOPKIT3TQZF25L4AF/graph.json","events_json":"https://pith.science/api/pith-number/NCDLRKUICFOPKIT3TQZF25L4AF/events.json","paper":"https://pith.science/paper/NCDLRKUI"},"agent_actions":{"view_html":"https://pith.science/pith/NCDLRKUICFOPKIT3TQZF25L4AF","download_json":"https://pith.science/pith/NCDLRKUICFOPKIT3TQZF25L4AF.json","view_paper":"https://pith.science/paper/NCDLRKUI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.07674&json=true","fetch_graph":"https://pith.science/api/pith-number/NCDLRKUICFOPKIT3TQZF25L4AF/graph.json","fetch_events":"https://pith.science/api/pith-number/NCDLRKUICFOPKIT3TQZF25L4AF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NCDLRKUICFOPKIT3TQZF25L4AF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NCDLRKUICFOPKIT3TQZF25L4AF/action/storage_attestation","attest_author":"https://pith.science/pith/NCDLRKUICFOPKIT3TQZF25L4AF/action/author_attestation","sign_citation":"https://pith.science/pith/NCDLRKUICFOPKIT3TQZF25L4AF/action/citation_signature","submit_replication":"https://pith.science/pith/NCDLRKUICFOPKIT3TQZF25L4AF/action/replication_record"}},"created_at":"2026-07-09T01:20:38.711453+00:00","updated_at":"2026-07-09T01:20:38.711453+00:00"}