{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BSYSUPX33HP7ILOERFIPB4YAE6","short_pith_number":"pith:BSYSUPX3","schema_version":"1.0","canonical_sha256":"0cb12a3efbd9dff42dc48950f0f30027ab36e9a35934acaac6b23cb55135ba80","source":{"kind":"arxiv","id":"2605.13136","version":1},"attestation_state":"computed","paper":{"title":"GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"GateKD uses teacher confidence to gate distillation of reasoning steps from large models to smaller ones, creating a closed-loop process that reduces errors.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kasidit Sermsri, Teerapong Panboonyuen","submitted_at":"2026-05-13T08:04:46Z","abstract_excerpt":"Distilling multi-step reasoning abilities from large language models (LLMs) into compact student models remains challenging due to noisy rationales, hallucinated supervision, and static teacher-student interactions. Existing reasoning distillation methods, including mentor-based approaches, predominantly operate in an open-loop manner, implicitly assuming uniform teacher reliability and consequently propagating erroneous intermediate reasoning. We propose GateKD, a confidence-gated closed-loop distillation framework that enables robust reasoning transfer by treating the teacher as a dynamic ga"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.13136","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-13T08:04:46Z","cross_cats_sorted":[],"title_canon_sha256":"9a72cd8b4fa7239c84a95ca9facc737aeed16753d932afddeef172b7f995639a","abstract_canon_sha256":"b76a13b34e46ab8d52afc292ae5135f6fe6ef417210d29709d7f56ffefdf520b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:08:57.580774Z","signature_b64":"dUo0SzNffGLl3/+WVkGEEwmKeG9z9SOr0vcM0HlPN3CoO6bc4kJpxvW1LYqisFIW3YlQ5GmWvrCI97esE1RHCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cb12a3efbd9dff42dc48950f0f30027ab36e9a35934acaac6b23cb55135ba80","last_reissued_at":"2026-05-18T03:08:57.579971Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:08:57.579971Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GateKD: Confidence-Gated Closed-Loop Distillation for Robust Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"GateKD uses teacher confidence to gate distillation of reasoning steps from large models to smaller ones, creating a closed-loop process that reduces errors.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kasidit Sermsri, Teerapong Panboonyuen","submitted_at":"2026-05-13T08:04:46Z","abstract_excerpt":"Distilling multi-step reasoning abilities from large language models (LLMs) into compact student models remains challenging due to noisy rationales, hallucinated supervision, and static teacher-student interactions. Existing reasoning distillation methods, including mentor-based approaches, predominantly operate in an open-loop manner, implicitly assuming uniform teacher reliability and consequently propagating erroneous intermediate reasoning. We propose GateKD, a confidence-gated closed-loop distillation framework that enables robust reasoning transfer by treating the teacher as a dynamic ga"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"GateKD consistently outperforms strong open-loop distillation baselines. Notably, GateKD yields substantial gains in logical and symbolic reasoning, remains robust under low-resource distillation settings, and shows clear performance degradation when any gating component is removed.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That teacher confidence scores reliably indicate the correctness of intermediate reasoning steps and that gating on them does not systematically exclude valid but low-confidence reasoning paths or introduce new selection biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"GateKD introduces a closed-loop distillation framework that uses teacher confidence to gate soft supervision, hidden-state alignment, and attention transfer, outperforming open-loop baselines on reasoning benchmarks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"GateKD uses teacher confidence to gate distillation of reasoning steps from large models to smaller ones, creating a closed-loop process that reduces errors.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"b27e53a85e52a68f82caa63657efc910c4070eb59e79fa4066bcf52877ad06e2"},"source":{"id":"2605.13136","kind":"arxiv","version":1},"verdict":{"id":"06a81d5a-cc8f-4aab-80a4-ffa9c5633377","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:34:04.538199Z","strongest_claim":"GateKD consistently outperforms strong open-loop distillation baselines. Notably, GateKD yields substantial gains in logical and symbolic reasoning, remains robust under low-resource distillation settings, and shows clear performance degradation when any gating component is removed.","one_line_summary":"GateKD introduces a closed-loop distillation framework that uses teacher confidence to gate soft supervision, hidden-state alignment, and attention transfer, outperforming open-loop baselines on reasoning benchmarks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That teacher confidence scores reliably indicate the correctness of intermediate reasoning steps and that gating on them does not systematically exclude valid but low-confidence reasoning paths or introduce new selection biases.","pith_extraction_headline":"GateKD uses teacher confidence to gate distillation of reasoning steps from large models to smaller ones, creating a closed-loop process that reduces errors."},"references":{"count":20,"sample":[{"doi":"","year":2023,"title":"arXiv preprint , volume=","work_id":"dc288403-5d0d-4749-9308-c3c372c523fb","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Findings of the Association for Computational Linguistics: EMNLP 2024 , pages=","work_id":"ab779dd5-c01c-4557-9729-fc685860b623","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"arXiv preprint , volume=","work_id":"d7d5278c-d572-4057-a571-8f1b9803d3b3","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"arXiv preprint , volume=","work_id":"6b894548-f7d0-4a55-8717-6d8cfe9edd4e","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Proceedings of the 2025 International Natural Language Generation Conference , pages=","work_id":"8a512deb-f3ca-43d8-872d-ac45d7aacfb3","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":20,"snapshot_sha256":"d4b0a0ebd48389903f55f9a00c51242cf3dd8ec91a719d40947d176e0f5d0df5","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":"2605.13136","created_at":"2026-05-18T03:08:57.580079+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.13136v1","created_at":"2026-05-18T03:08:57.580079+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13136","created_at":"2026-05-18T03:08:57.580079+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSYSUPX33HP7","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSYSUPX33HP7ILOE","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSYSUPX3","created_at":"2026-05-18T12:33:37.589309+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/BSYSUPX33HP7ILOERFIPB4YAE6","json":"https://pith.science/pith/BSYSUPX33HP7ILOERFIPB4YAE6.json","graph_json":"https://pith.science/api/pith-number/BSYSUPX33HP7ILOERFIPB4YAE6/graph.json","events_json":"https://pith.science/api/pith-number/BSYSUPX33HP7ILOERFIPB4YAE6/events.json","paper":"https://pith.science/paper/BSYSUPX3"},"agent_actions":{"view_html":"https://pith.science/pith/BSYSUPX33HP7ILOERFIPB4YAE6","download_json":"https://pith.science/pith/BSYSUPX33HP7ILOERFIPB4YAE6.json","view_paper":"https://pith.science/paper/BSYSUPX3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.13136&json=true","fetch_graph":"https://pith.science/api/pith-number/BSYSUPX33HP7ILOERFIPB4YAE6/graph.json","fetch_events":"https://pith.science/api/pith-number/BSYSUPX33HP7ILOERFIPB4YAE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSYSUPX33HP7ILOERFIPB4YAE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSYSUPX33HP7ILOERFIPB4YAE6/action/storage_attestation","attest_author":"https://pith.science/pith/BSYSUPX33HP7ILOERFIPB4YAE6/action/author_attestation","sign_citation":"https://pith.science/pith/BSYSUPX33HP7ILOERFIPB4YAE6/action/citation_signature","submit_replication":"https://pith.science/pith/BSYSUPX33HP7ILOERFIPB4YAE6/action/replication_record"}},"created_at":"2026-05-18T03:08:57.580079+00:00","updated_at":"2026-05-18T03:08:57.580079+00:00"}