{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:H3IFIZDI77DDPCRI4UBE2R7AHH","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":"74039282b99daea87888763748f8fafbbf1e345e21362814715e16af59dff0db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T16:23:24Z","title_canon_sha256":"12be670d8e171297586108cd955c5b47e74ceee2fcf713f059a21e561b9d363a"},"schema_version":"1.0","source":{"id":"2505.21395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.21395","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"arxiv_version","alias_value":"2505.21395v1","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21395","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"pith_short_12","alias_value":"H3IFIZDI77DD","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"pith_short_16","alias_value":"H3IFIZDI77DDPCRI","created_at":"2026-07-05T11:10:41Z"},{"alias_kind":"pith_short_8","alias_value":"H3IFIZDI","created_at":"2026-07-05T11:10:41Z"}],"graph_snapshots":[{"event_id":"sha256:ade6e4782b79b6aa9f855fe69f10a01f95d9e279b9bff90a252982af8be8687f","target":"graph","created_at":"2026-07-05T11:10:41Z","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/2505.21395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we theoretically study the offline alignment of language models with human preference feedback, under both preference label corruption and privacy protections. To this end, we propose Square$\\chi$PO, a simple one-line change to $\\chi$PO where the standard log-loss is replaced by a new square loss over probability. Thanks to the inherent properties of this new loss, we have advanced the state-of-the-art of differentially private and robust offline direct alignment. Specifically, for the local model of label privacy, Square$\\chi$PO is the first algorithm that attains an optimal ra","authors_text":"Francesco Orabona, Wenqian Weng, Xingyu Zhou, Yulian Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T16:23:24Z","title":"Square$\\chi$PO: Differentially Private and Robust $\\chi^2$-Preference Optimization in Offline Direct Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21395","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":"sha256:688908996a355c37363889daa74730fe1b8de310cd826c680615365b5d514ed2","target":"record","created_at":"2026-07-05T11:10:41Z","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":"74039282b99daea87888763748f8fafbbf1e345e21362814715e16af59dff0db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-27T16:23:24Z","title_canon_sha256":"12be670d8e171297586108cd955c5b47e74ceee2fcf713f059a21e561b9d363a"},"schema_version":"1.0","source":{"id":"2505.21395","kind":"arxiv","version":1}},"canonical_sha256":"3ed0546468ffc6378a28e5024d47e039f2fbef52d5f5f08eb63a74e48bcfe424","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3ed0546468ffc6378a28e5024d47e039f2fbef52d5f5f08eb63a74e48bcfe424","first_computed_at":"2026-07-05T11:10:41.375138Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:41.375138Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"A/a4lswVBX8tFazz5F50I+RXP1O92GnfNl4HmB4TMGLCsWvxKZvV2wDvcra24p5QC7pDDAp77QuuuSC5Ru45Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:41.375677Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.21395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:688908996a355c37363889daa74730fe1b8de310cd826c680615365b5d514ed2","sha256:ade6e4782b79b6aa9f855fe69f10a01f95d9e279b9bff90a252982af8be8687f"],"state_sha256":"fac0f725f4d9ec2113e8d400e23d40c51e67570aeba30f99aaf95646c10ed2bd"}