{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ILAOHRUFCD7VLENSJ4AU6DK3OX","short_pith_number":"pith:ILAOHRUF","canonical_record":{"source":{"id":"2505.11628","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:45:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8cebaae1ea276260b3aebcb5a3b579af9da364db99afb09d50d0bc3ac9f626a9","abstract_canon_sha256":"af5d81425e307ab97e081c1b7c5ef1d2e424ab35994a0e160f9b73bac8672138"},"schema_version":"1.0"},"canonical_sha256":"42c0e3c68510ff5591b24f014f0d5b75c0117c6715c07ad3e28395739b0ca254","source":{"kind":"arxiv","id":"2505.11628","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11628","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11628v4","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11628","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"ILAOHRUFCD7V","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"ILAOHRUFCD7VLENS","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"ILAOHRUF","created_at":"2026-05-20T02:05:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ILAOHRUFCD7VLENSJ4AU6DK3OX","target":"record","payload":{"canonical_record":{"source":{"id":"2505.11628","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:45:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8cebaae1ea276260b3aebcb5a3b579af9da364db99afb09d50d0bc3ac9f626a9","abstract_canon_sha256":"af5d81425e307ab97e081c1b7c5ef1d2e424ab35994a0e160f9b73bac8672138"},"schema_version":"1.0"},"canonical_sha256":"42c0e3c68510ff5591b24f014f0d5b75c0117c6715c07ad3e28395739b0ca254","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T02:05:33.475720Z","signature_b64":"XtMmdqKzNtKndl0+7J9js9DlN55N44OqhxfbXGIJzHgwJRSwtfH4aB4S4vLfj1wlyr//zewZzhrOuwKuh3rYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"42c0e3c68510ff5591b24f014f0d5b75c0117c6715c07ad3e28395739b0ca254","last_reissued_at":"2026-05-20T02:05:33.475042Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T02:05:33.475042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.11628","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T02:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WJQgUGcVMoql448WZ5+nCc1A7MEW+Z/OM7aAuX4MM4KxNrg4u6/aqlCoRlfCnMy6j49uRpLn99N7W0AQdqrpAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T22:49:43.725154Z"},"content_sha256":"0ba24ad41c7300903ff32d373856e7e91a46ac3399aa434fdecf289f440ccb0b","schema_version":"1.0","event_id":"sha256:0ba24ad41c7300903ff32d373856e7e91a46ac3399aa434fdecf289f440ccb0b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ILAOHRUFCD7VLENSJ4AU6DK3OX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Critique-Guided Distillation for Robust Reasoning via Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Berkcan Kapusuzoglu, Chia-Hsuan Lee, Sambit Sahu, Supriyo Chakraborty, Zain Sarwar","submitted_at":"2025-05-16T18:45:59Z","abstract_excerpt":"Supervised fine-tuning with expert demonstrations often produces models that imitate outputs without internalizing the reasoning processes needed for robust generalization. While critique-based approaches show promise, training models to generate critiques directly, such as Critique Fine-Tuning (CFT), can lead to output-format drift and degradation of general capabilities. We propose Critique-Guided Distillation (CGD), a training framework that decouples critique consumption from critique generation. During fine-tuning, the student is trained to refine flawed responses conditioned on teacher c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11628","kind":"arxiv","version":4},"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/2505.11628/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":"2026-05-20T02:05:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qKDRpgkh2EWVuJItwKlzbAlP9RdD7rgKbFlHjCgV79K21V2XE6l6Mwt/wtB6kxv3KkHECqvJAgksid8raQVdCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T22:49:43.725907Z"},"content_sha256":"54820a2debe93e82392d099ddd8e91db760efca85df614dee86c22850f858dfd","schema_version":"1.0","event_id":"sha256:54820a2debe93e82392d099ddd8e91db760efca85df614dee86c22850f858dfd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ILAOHRUFCD7VLENSJ4AU6DK3OX/bundle.json","state_url":"https://pith.science/pith/ILAOHRUFCD7VLENSJ4AU6DK3OX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ILAOHRUFCD7VLENSJ4AU6DK3OX/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":"2026-05-24T22:49:43Z","links":{"resolver":"https://pith.science/pith/ILAOHRUFCD7VLENSJ4AU6DK3OX","bundle":"https://pith.science/pith/ILAOHRUFCD7VLENSJ4AU6DK3OX/bundle.json","state":"https://pith.science/pith/ILAOHRUFCD7VLENSJ4AU6DK3OX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ILAOHRUFCD7VLENSJ4AU6DK3OX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ILAOHRUFCD7VLENSJ4AU6DK3OX","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":"af5d81425e307ab97e081c1b7c5ef1d2e424ab35994a0e160f9b73bac8672138","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:45:59Z","title_canon_sha256":"8cebaae1ea276260b3aebcb5a3b579af9da364db99afb09d50d0bc3ac9f626a9"},"schema_version":"1.0","source":{"id":"2505.11628","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11628","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11628v4","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11628","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"pith_short_12","alias_value":"ILAOHRUFCD7V","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"pith_short_16","alias_value":"ILAOHRUFCD7VLENS","created_at":"2026-05-20T02:05:33Z"},{"alias_kind":"pith_short_8","alias_value":"ILAOHRUF","created_at":"2026-05-20T02:05:33Z"}],"graph_snapshots":[{"event_id":"sha256:54820a2debe93e82392d099ddd8e91db760efca85df614dee86c22850f858dfd","target":"graph","created_at":"2026-05-20T02:05:33Z","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/2505.11628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised fine-tuning with expert demonstrations often produces models that imitate outputs without internalizing the reasoning processes needed for robust generalization. While critique-based approaches show promise, training models to generate critiques directly, such as Critique Fine-Tuning (CFT), can lead to output-format drift and degradation of general capabilities. We propose Critique-Guided Distillation (CGD), a training framework that decouples critique consumption from critique generation. During fine-tuning, the student is trained to refine flawed responses conditioned on teacher c","authors_text":"Berkcan Kapusuzoglu, Chia-Hsuan Lee, Sambit Sahu, Supriyo Chakraborty, Zain Sarwar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:45:59Z","title":"Critique-Guided Distillation for Robust Reasoning via Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11628","kind":"arxiv","version":4},"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":"sha256:0ba24ad41c7300903ff32d373856e7e91a46ac3399aa434fdecf289f440ccb0b","target":"record","created_at":"2026-05-20T02:05:33Z","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":"af5d81425e307ab97e081c1b7c5ef1d2e424ab35994a0e160f9b73bac8672138","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T18:45:59Z","title_canon_sha256":"8cebaae1ea276260b3aebcb5a3b579af9da364db99afb09d50d0bc3ac9f626a9"},"schema_version":"1.0","source":{"id":"2505.11628","kind":"arxiv","version":4}},"canonical_sha256":"42c0e3c68510ff5591b24f014f0d5b75c0117c6715c07ad3e28395739b0ca254","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"42c0e3c68510ff5591b24f014f0d5b75c0117c6715c07ad3e28395739b0ca254","first_computed_at":"2026-05-20T02:05:33.475042Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T02:05:33.475042Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XtMmdqKzNtKndl0+7J9js9DlN55N44OqhxfbXGIJzHgwJRSwtfH4aB4S4vLfj1wlyr//zewZzhrOuwKuh3rYAg==","signature_status":"signed_v1","signed_at":"2026-05-20T02:05:33.475720Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11628","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ba24ad41c7300903ff32d373856e7e91a46ac3399aa434fdecf289f440ccb0b","sha256:54820a2debe93e82392d099ddd8e91db760efca85df614dee86c22850f858dfd"],"state_sha256":"e9734e602d64e0711da2b35600f17169404e79cdfc27011c4511820527360a14"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a25nD/uWvIksUpyZaL2O9Df7ws1YJN6Ah15vCL1MXvpxk48lxRFMkNhWSB/0ED/nxs2SHKkqfgICsRs/SezABw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T22:49:43.729583Z","bundle_sha256":"e4f14d0f72b4d01accdf612d0f1c2aac68165670ee92f1cf42df7dcba5d9494a"}}