{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GYD5P3Q5XBDDSHNTZR5CXGTVO6","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":"372207c3b9e110cd1aa0db915fe204242db964cecf5a65459244f9dc0137d227","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T14:38:00Z","title_canon_sha256":"55e2cf8075eef22e724150159360e67b2b5d794f569d2806f20e34610efeb276"},"schema_version":"1.0","source":{"id":"2607.18006","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18006","created_at":"2026-07-21T02:22:11Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18006v1","created_at":"2026-07-21T02:22:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18006","created_at":"2026-07-21T02:22:11Z"},{"alias_kind":"pith_short_12","alias_value":"GYD5P3Q5XBDD","created_at":"2026-07-21T02:22:11Z"},{"alias_kind":"pith_short_16","alias_value":"GYD5P3Q5XBDDSHNT","created_at":"2026-07-21T02:22:11Z"},{"alias_kind":"pith_short_8","alias_value":"GYD5P3Q5","created_at":"2026-07-21T02:22:11Z"}],"graph_snapshots":[{"event_id":"sha256:40a52d70d6ea93137f8395011bc4cc676243270e67a4a25c812f680542a92ac8","target":"graph","created_at":"2026-07-21T02:22:11Z","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/2607.18006/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models achieve strong reasoning performance, but often at prohibitive training cost - a challenge that is especially acute for compact models ($\\leq 4 \\, \\mathrm{B}$ parameters) trained under limited budgets. We introduce MADA-RL, a post-training framework that specializes compact models into generator and critic roles and trains them with a debate-aware learning signal, fine-tuning only a small subset of parameters via LoRA adapters. Our central contribution is a counterfactual critic advantage: a dynamic, role-conditioned baseline that redefines the critic's advantage as its r","authors_text":"Cuong Xuan Chu, Evgeny Kharlamov, Martino M. L. Pulici, Volker Tresp, Yunpu Ma, Zifeng Ding","cross_cats":["cs.AI","cs.CL","cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T14:38:00Z","title":"MADA-RL: Multi-Agent Debate-Aware Reinforcement Learning for Parameter-Efficient Reasoning in Compact Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18006","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:f30b600fe62f7021ab5ee7725dec40a9a1bc0366f85abfbdcd79d73bc4bc639f","target":"record","created_at":"2026-07-21T02:22:11Z","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":"372207c3b9e110cd1aa0db915fe204242db964cecf5a65459244f9dc0137d227","cross_cats_sorted":["cs.AI","cs.CL","cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-20T14:38:00Z","title_canon_sha256":"55e2cf8075eef22e724150159360e67b2b5d794f569d2806f20e34610efeb276"},"schema_version":"1.0","source":{"id":"2607.18006","kind":"arxiv","version":1}},"canonical_sha256":"3607d7ee1db846391db3cc7a2b9a7577b46e0d44e8ddf3a81ad8ff3479804e13","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3607d7ee1db846391db3cc7a2b9a7577b46e0d44e8ddf3a81ad8ff3479804e13","first_computed_at":"2026-07-21T02:22:11.466395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:22:11.466395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iHrKYH6O5mRQNAy5XpCgSKOixSOGljHjQ96DSFwTIunQsvn5XnON3F9p11hqO30Qp4jBkSlWUE9GJAT+eEVwDA==","signature_status":"signed_v1","signed_at":"2026-07-21T02:22:11.467239Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18006","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f30b600fe62f7021ab5ee7725dec40a9a1bc0366f85abfbdcd79d73bc4bc639f","sha256:40a52d70d6ea93137f8395011bc4cc676243270e67a4a25c812f680542a92ac8"],"state_sha256":"ae2cd6368c27001b5100edc165a4420d250d097d669509707cc3fd4bd6a5a07a"}