{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E7WKZCNA2BRVRARBGYHLJUVZUV","short_pith_number":"pith:E7WKZCNA","canonical_record":{"source":{"id":"2501.15109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T07:21:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13143215c9c82b0351a96d857f10c176e59b50b24e1b1adfbb6b541486b1c7d9","abstract_canon_sha256":"d93289248af8c8a8b7546ed76c4a80846bb364183a1007eee7caea655130ad47"},"schema_version":"1.0"},"canonical_sha256":"27ecac89a0d063588221360eb4d2b9a54defdc7a5a2f42ec7c944cd8f05879c4","source":{"kind":"arxiv","id":"2501.15109","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15109","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15109v1","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15109","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"E7WKZCNA2BRV","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"E7WKZCNA2BRVRARB","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"E7WKZCNA","created_at":"2026-07-05T10:05:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E7WKZCNA2BRVRARBGYHLJUVZUV","target":"record","payload":{"canonical_record":{"source":{"id":"2501.15109","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T07:21:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"13143215c9c82b0351a96d857f10c176e59b50b24e1b1adfbb6b541486b1c7d9","abstract_canon_sha256":"d93289248af8c8a8b7546ed76c4a80846bb364183a1007eee7caea655130ad47"},"schema_version":"1.0"},"canonical_sha256":"27ecac89a0d063588221360eb4d2b9a54defdc7a5a2f42ec7c944cd8f05879c4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:24.540065Z","signature_b64":"eLiNkPOoqhIQmOkKzGS4UnQW0BqulENUGq9YoXbjj1uBu75Oq+xK4FkZ3UJMXPAsPXoub7vPfHzpPr/uzmtvBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"27ecac89a0d063588221360eb4d2b9a54defdc7a5a2f42ec7c944cd8f05879c4","last_reissued_at":"2026-07-05T10:05:24.539594Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:24.539594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.15109","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S6TIUih2K+farakBN7+Dpo7t4bit5g/S9GFKoHiPa2PwVKjR3WwVaWfr/nHcKSQA7sZ/0h7osEMHFX4O4sMgAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:54:59.943597Z"},"content_sha256":"1bdbfb744147539997682ec309ffec0c7426d82ed733fdbc73c18d72faec22ec","schema_version":"1.0","event_id":"sha256:1bdbfb744147539997682ec309ffec0c7426d82ed733fdbc73c18d72faec22ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E7WKZCNA2BRVRARBGYHLJUVZUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Clear Preferences Leave Traces: Reference Model-Guided Sampling for Preference Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Dongsub Shim, Honglak Lee, Nirav Diwan, Tolga Ergen","submitted_at":"2025-01-25T07:21:50Z","abstract_excerpt":"Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences between preferred and rejected responses enhance learning performance. Current methods for identifying and obtaining such high-quality samples demand additional resources or external models. We discover that reference model probability space naturally detects high-quality training samples. Using this insight, we present a sampling strategy that achieves con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15109","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/2501.15109/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":"2026-07-05T10:05:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0WmpgoUJS1F8N07xypAv5I5VKmdrI4AxBLvBHQM870bRUsqIhtGLi9lQzunTK+wSOms3IkwbHfuqEdvDfeROAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:54:59.944116Z"},"content_sha256":"925e3209c06bc3a0f08351e345b7fd788c73cfdd2d6306225baa6a4056eb4b33","schema_version":"1.0","event_id":"sha256:925e3209c06bc3a0f08351e345b7fd788c73cfdd2d6306225baa6a4056eb4b33"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E7WKZCNA2BRVRARBGYHLJUVZUV/bundle.json","state_url":"https://pith.science/pith/E7WKZCNA2BRVRARBGYHLJUVZUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E7WKZCNA2BRVRARBGYHLJUVZUV/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":"2026-08-11T13:54:59Z","links":{"resolver":"https://pith.science/pith/E7WKZCNA2BRVRARBGYHLJUVZUV","bundle":"https://pith.science/pith/E7WKZCNA2BRVRARBGYHLJUVZUV/bundle.json","state":"https://pith.science/pith/E7WKZCNA2BRVRARBGYHLJUVZUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E7WKZCNA2BRVRARBGYHLJUVZUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E7WKZCNA2BRVRARBGYHLJUVZUV","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":"d93289248af8c8a8b7546ed76c4a80846bb364183a1007eee7caea655130ad47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T07:21:50Z","title_canon_sha256":"13143215c9c82b0351a96d857f10c176e59b50b24e1b1adfbb6b541486b1c7d9"},"schema_version":"1.0","source":{"id":"2501.15109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.15109","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"arxiv_version","alias_value":"2501.15109v1","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.15109","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"pith_short_12","alias_value":"E7WKZCNA2BRV","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"pith_short_16","alias_value":"E7WKZCNA2BRVRARB","created_at":"2026-07-05T10:05:24Z"},{"alias_kind":"pith_short_8","alias_value":"E7WKZCNA","created_at":"2026-07-05T10:05:24Z"}],"graph_snapshots":[{"event_id":"sha256:925e3209c06bc3a0f08351e345b7fd788c73cfdd2d6306225baa6a4056eb4b33","target":"graph","created_at":"2026-07-05T10:05:24Z","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/2501.15109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Preference Optimization (DPO) has emerged as a de-facto approach for aligning language models with human preferences. Recent work has shown DPO's effectiveness relies on training data quality. In particular, clear quality differences between preferred and rejected responses enhance learning performance. Current methods for identifying and obtaining such high-quality samples demand additional resources or external models. We discover that reference model probability space naturally detects high-quality training samples. Using this insight, we present a sampling strategy that achieves con","authors_text":"Dongsub Shim, Honglak Lee, Nirav Diwan, Tolga Ergen","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T07:21:50Z","title":"Clear Preferences Leave Traces: Reference Model-Guided Sampling for Preference Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.15109","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":"sha256:1bdbfb744147539997682ec309ffec0c7426d82ed733fdbc73c18d72faec22ec","target":"record","created_at":"2026-07-05T10:05:24Z","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":"d93289248af8c8a8b7546ed76c4a80846bb364183a1007eee7caea655130ad47","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-25T07:21:50Z","title_canon_sha256":"13143215c9c82b0351a96d857f10c176e59b50b24e1b1adfbb6b541486b1c7d9"},"schema_version":"1.0","source":{"id":"2501.15109","kind":"arxiv","version":1}},"canonical_sha256":"27ecac89a0d063588221360eb4d2b9a54defdc7a5a2f42ec7c944cd8f05879c4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"27ecac89a0d063588221360eb4d2b9a54defdc7a5a2f42ec7c944cd8f05879c4","first_computed_at":"2026-07-05T10:05:24.539594Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:05:24.539594Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eLiNkPOoqhIQmOkKzGS4UnQW0BqulENUGq9YoXbjj1uBu75Oq+xK4FkZ3UJMXPAsPXoub7vPfHzpPr/uzmtvBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:05:24.540065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.15109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1bdbfb744147539997682ec309ffec0c7426d82ed733fdbc73c18d72faec22ec","sha256:925e3209c06bc3a0f08351e345b7fd788c73cfdd2d6306225baa6a4056eb4b33"],"state_sha256":"4d682ccbeab8e4152fb8752a4c920f14ef5c66d45e2cf770ab42a69ab0b63ef1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xbU2FHN0QHYdMVlcFGX61iLJjIedMPlvCrwUHAfVjCNj1FAk094w6zaFx+mBDpnluIIJZTHLy4H8GheLSr9iDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T13:54:59.948974Z","bundle_sha256":"82a587411780a54fe6117e10ffdc260a9a4d1665cb66ed7307ecc6526e862af8"}}