{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RKRL6VD5FUDXHM5KNNKIGJAEXV","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":"73cd4107708f67ee468f7b724fa6fa602da2c3dcd376bfcfbb40de7b32982f75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-17T18:10:00Z","title_canon_sha256":"078283a79036298b2cf85fe4415b95a3a981fecf3dc46506d1918e49c3831da7"},"schema_version":"1.0","source":{"id":"2602.15778","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.15778","created_at":"2026-06-01T01:03:50Z"},{"alias_kind":"arxiv_version","alias_value":"2602.15778v2","created_at":"2026-06-01T01:03:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.15778","created_at":"2026-06-01T01:03:50Z"},{"alias_kind":"pith_short_12","alias_value":"RKRL6VD5FUDX","created_at":"2026-06-01T01:03:50Z"},{"alias_kind":"pith_short_16","alias_value":"RKRL6VD5FUDXHM5K","created_at":"2026-06-01T01:03:50Z"},{"alias_kind":"pith_short_8","alias_value":"RKRL6VD5","created_at":"2026-06-01T01:03:50Z"}],"graph_snapshots":[{"event_id":"sha256:bb075563537514f43c13c29dbb6f36373096cbd3c474a24d30c3777ade39aedd","target":"graph","created_at":"2026-06-01T01:03:50Z","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/2602.15778/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Evaluating the quality of automatically generated text often relies on LLM-as-a-judge (LLM-judge) methods. While effective, these approaches are computationally expensive and require post-processing. To address these limitations, we build upon ParaPLUIE, a perplexity-based LLM-judge metric that estimates confidence over ``Yes/No'' answers without generating text. We introduce *-PLUIE, task specific prompting variants of ParaPLUIE and evaluate their alignment with human judgement. Our experiments show that personalised *-PLUIE achieves stronger correlations with human ratings while maintaining ","authors_text":"Arnaud Delhay, Daisy Munson, Damien Lolive, Jonathan Chevelu, L\\'eane Jourdan, Pierre Alain, Quentin Lemesle","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-17T18:10:00Z","title":"*-PLUIE: Personalisable metric with Llm Used for Improved Evaluation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.15778","kind":"arxiv","version":2},"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":"sha256:977daf04c7c8c7530065ea3204a7501027a3eff8570de3e67c51891e89557d12","target":"record","created_at":"2026-06-01T01:03:50Z","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":"73cd4107708f67ee468f7b724fa6fa602da2c3dcd376bfcfbb40de7b32982f75","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-02-17T18:10:00Z","title_canon_sha256":"078283a79036298b2cf85fe4415b95a3a981fecf3dc46506d1918e49c3831da7"},"schema_version":"1.0","source":{"id":"2602.15778","kind":"arxiv","version":2}},"canonical_sha256":"8aa2bf547d2d0773b3aa6b54832404bd4a1894f502afa698a0f2264e9f1ddbe4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8aa2bf547d2d0773b3aa6b54832404bd4a1894f502afa698a0f2264e9f1ddbe4","first_computed_at":"2026-06-01T01:03:50.862428Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-01T01:03:50.862428Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qUiCJegsv53oabDmHYwzwuqX3SD1WRQJ7dU1ZRgDlNhMGZeuwUXYuHjS2kEwqCm7CRC0FG88gKWW9xHOtUZZBg==","signature_status":"signed_v1","signed_at":"2026-06-01T01:03:50.863357Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.15778","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:977daf04c7c8c7530065ea3204a7501027a3eff8570de3e67c51891e89557d12","sha256:bb075563537514f43c13c29dbb6f36373096cbd3c474a24d30c3777ade39aedd"],"state_sha256":"40680a6f13d34a76424f0fe430ba2d1d69f01dc2a1c6790eb507ca35be5c36a3"}