{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:35XKAWGMIVU3BZK2QTPMBBPI2K","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":"b759f2516cef9292d08a11ed1736a23e0a990835b4440529b70a06269da32fc7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T00:39:43Z","title_canon_sha256":"cfefbb639a5b43e3c054b45a645216689542f68fcb0b825d640fc936377dd30c"},"schema_version":"1.0","source":{"id":"2505.05704","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05704","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05704v1","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05704","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"pith_short_12","alias_value":"35XKAWGMIVU3","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"pith_short_16","alias_value":"35XKAWGMIVU3BZK2","created_at":"2026-07-05T11:00:46Z"},{"alias_kind":"pith_short_8","alias_value":"35XKAWGM","created_at":"2026-07-05T11:00:46Z"}],"graph_snapshots":[{"event_id":"sha256:30f986fb84a0a4b3e59eb281973fa14cd7bafbec2fdb9d8f2d5f17f76e59ba89","target":"graph","created_at":"2026-07-05T11:00:46Z","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/2505.05704/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised and preference-based fine-tuning techniques have become popular for aligning large language models (LLMs) with user intent and correctness criteria. However, real-world training data often exhibits spurious correlations -- arising from biases, dataset artifacts, or other \"shortcut\" features -- that can compromise a model's performance or generalization. In this paper, we systematically evaluate three post-training algorithms -- Supervised Fine-Tuning (SFT), Direct Preference Optimization (DPO), and KTO (Kahneman-Tversky Optimization) -- across a diverse set of synthetic tasks and sp","authors_text":"Apaar Shanker, George Pu, John Heyer, Julia Shuieh, Prasann Singhal, Samuel Denton","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T00:39:43Z","title":"Assessing Robustness to Spurious Correlations in Post-Training Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05704","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":"sha256:40a0c70cc2f9f08706ac1f4be29650efff40b3ee7316a9bb816adda018ddcd7f","target":"record","created_at":"2026-07-05T11:00:46Z","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":"b759f2516cef9292d08a11ed1736a23e0a990835b4440529b70a06269da32fc7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-09T00:39:43Z","title_canon_sha256":"cfefbb639a5b43e3c054b45a645216689542f68fcb0b825d640fc936377dd30c"},"schema_version":"1.0","source":{"id":"2505.05704","kind":"arxiv","version":1}},"canonical_sha256":"df6ea058cc4569b0e55a84dec085e8d29ab6cf81e305847f20f96de4394929c9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df6ea058cc4569b0e55a84dec085e8d29ab6cf81e305847f20f96de4394929c9","first_computed_at":"2026-07-05T11:00:46.128796Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:00:46.128796Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+STeQYwr4afC4BS15uA2RFrYx32tH8j3D528v1UDs9DSmSxBjKBYpPxd5Sxk9qyGC52BsNa+weERMY8hckRZBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:00:46.129273Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05704","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40a0c70cc2f9f08706ac1f4be29650efff40b3ee7316a9bb816adda018ddcd7f","sha256:30f986fb84a0a4b3e59eb281973fa14cd7bafbec2fdb9d8f2d5f17f76e59ba89"],"state_sha256":"f99db225e2b730f494158b76ed69af18f661e550591ad5dd0f5a8bfd31a9ac2b"}