{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:WGK73HJAV2BJT2R47P462UT5F6","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":"078edf33ea4a331851a66bbd0d9ea540ee991f15715822b82109901aee32840e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T06:28:14Z","title_canon_sha256":"125b285c2df753ca3febd9564b0d2904b4a39ffef7a3e65b90891f42378811b1"},"schema_version":"1.0","source":{"id":"2505.12754","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12754","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12754v1","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12754","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_12","alias_value":"WGK73HJAV2BJ","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_16","alias_value":"WGK73HJAV2BJT2R4","created_at":"2026-07-05T11:05:09Z"},{"alias_kind":"pith_short_8","alias_value":"WGK73HJA","created_at":"2026-07-05T11:05:09Z"}],"graph_snapshots":[{"event_id":"sha256:065dec8fe57424d9519f3462f34a26f0879352a2e46da9df9a860bfd3fdaeae5","target":"graph","created_at":"2026-07-05T11:05:09Z","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/2505.12754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction data selection aims to identify a high-quality subset from the training set that matches or exceeds the performance of the full dataset on target tasks. Existing methods focus on the instruction-to-response mapping, but neglect the human preference for diverse responses. In this paper, we propose Preference-oriented Data Selection method (ProDS) that scores training samples based on their alignment with preferences observed in the target set. Our key innovation lies in shifting the data selection criteria from merely estimating features for accurate response generation to explicitl","authors_text":"Haoze Zhu, Ruxue Yan, Wenya Guo, Xubo Liu, Xumeng Liu, Ying Zhang, Zhengkun Zhang, Ziyu Lu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T06:28:14Z","title":"ProDS: Preference-oriented Data Selection for Instruction Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12754","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":"sha256:3e5e04b87e6ff8424668f776ca41acb09daee6cec8d7f8c5085cded8b18db5a4","target":"record","created_at":"2026-07-05T11:05:09Z","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":"078edf33ea4a331851a66bbd0d9ea540ee991f15715822b82109901aee32840e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-19T06:28:14Z","title_canon_sha256":"125b285c2df753ca3febd9564b0d2904b4a39ffef7a3e65b90891f42378811b1"},"schema_version":"1.0","source":{"id":"2505.12754","kind":"arxiv","version":1}},"canonical_sha256":"b195fd9d20ae8299ea3cfbf9ed527d2fa124b3c8f1fe27f4fd01fdf0765751db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b195fd9d20ae8299ea3cfbf9ed527d2fa124b3c8f1fe27f4fd01fdf0765751db","first_computed_at":"2026-07-05T11:05:09.151785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:09.151785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"swiamDJE8JmYb8q+sVFn2TBeNbecFYDqqoieUrRJpu/7+QRn85DyjiPg6ZFWg2bV2GzzqwjoeBbpldpaPwdRDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:09.152243Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12754","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e5e04b87e6ff8424668f776ca41acb09daee6cec8d7f8c5085cded8b18db5a4","sha256:065dec8fe57424d9519f3462f34a26f0879352a2e46da9df9a860bfd3fdaeae5"],"state_sha256":"570141faef0ae3d35ab809fb5e07f41f0eb7a2212ddd929334eb57656427bdab"}