{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:4LTYRC5JUDHDMSGHSXWTI4BDZC","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":"40d9ea3bebfbb29b55125c5a70bf2cb05d2c692ab5bcb72bad5cf82d84d4aa41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-19T10:59:19Z","title_canon_sha256":"22600d7554e6ead514f4be679e7ac3239c57635fc87ed543f60774bb0ae692c1"},"schema_version":"1.0","source":{"id":"2605.19665","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.19665","created_at":"2026-05-20T01:05:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.19665v1","created_at":"2026-05-20T01:05:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.19665","created_at":"2026-05-20T01:05:56Z"},{"alias_kind":"pith_short_12","alias_value":"4LTYRC5JUDHD","created_at":"2026-05-20T01:05:56Z"},{"alias_kind":"pith_short_16","alias_value":"4LTYRC5JUDHDMSGH","created_at":"2026-05-20T01:05:56Z"},{"alias_kind":"pith_short_8","alias_value":"4LTYRC5J","created_at":"2026-05-20T01:05:56Z"}],"graph_snapshots":[{"event_id":"sha256:8c61fbd8a2c384f89b40a7adca5b598a6868a8cfb0808e222264df25d7842b57","target":"graph","created_at":"2026-05-20T01:05:56Z","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/2605.19665/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pairwise human preference prediction is central to evaluating code-generation systems, where quality often depends on task-specific trade-offs beyond functional correctness. While rubric-based LLM judges improve interpretability by decomposing evaluation into explicit criteria, most existing pipelines remain pointwise: they score each response independently and derive preferences by comparing aggregated scores. We show that this design is poorly matched to pairwise code preference prediction and can underperform a strong monolithic judge. We propose CriterAlign, a criterion-centric framework t","authors_text":"Aleksandar Cvejic, Peter Wonka, Zehui Chen, Zhenyu Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-19T10:59:19Z","title":"CriterAlign: Criterion-Centric Rationale Alignment for Code Preference Judging"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.19665","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":"sha256:0f7882b348ae62f6d5fe100c6f14044fc4a0a93f69cebf8eb21bbcfff1171f6f","target":"record","created_at":"2026-05-20T01:05:56Z","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":"40d9ea3bebfbb29b55125c5a70bf2cb05d2c692ab5bcb72bad5cf82d84d4aa41","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SE","submitted_at":"2026-05-19T10:59:19Z","title_canon_sha256":"22600d7554e6ead514f4be679e7ac3239c57635fc87ed543f60774bb0ae692c1"},"schema_version":"1.0","source":{"id":"2605.19665","kind":"arxiv","version":1}},"canonical_sha256":"e2e7888ba9a0ce3648c795ed347023c88985f8e7ef51fcd84fb7d693101b108f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e2e7888ba9a0ce3648c795ed347023c88985f8e7ef51fcd84fb7d693101b108f","first_computed_at":"2026-05-20T01:05:56.856229Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T01:05:56.856229Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lw5Na+1g/4OPvj61RX7Ypoek6zI/eKQbdJkXh+JVxtdT3AwiekhKPKJGSjem5o0ngycjZhjuDYUQIq3aQXffAg==","signature_status":"signed_v1","signed_at":"2026-05-20T01:05:56.856800Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.19665","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f7882b348ae62f6d5fe100c6f14044fc4a0a93f69cebf8eb21bbcfff1171f6f","sha256:8c61fbd8a2c384f89b40a7adca5b598a6868a8cfb0808e222264df25d7842b57"],"state_sha256":"b2133c0266b3a2c6bfa5f4e2c3758f9693fdd754db3c7d7ec0561760a24cadac"}