{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YOSWOSHTXOR2L2UITJMDKLFBNB","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":"ea0bdb1833748e4c09a85e56ea469da9a659dbc2abae373775bf20710ecf8c64","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:46:38Z","title_canon_sha256":"a3f24674ad6c83f65d3f1a58255cfadaef4b6330a9f3c487ac95d39052cd417e"},"schema_version":"1.0","source":{"id":"2505.20451","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.20451","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"arxiv_version","alias_value":"2505.20451v1","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20451","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_12","alias_value":"YOSWOSHTXOR2","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_16","alias_value":"YOSWOSHTXOR2L2UI","created_at":"2026-07-05T11:10:12Z"},{"alias_kind":"pith_short_8","alias_value":"YOSWOSHT","created_at":"2026-07-05T11:10:12Z"}],"graph_snapshots":[{"event_id":"sha256:1cb3dc40383674e6739fa700425111c1b93a7e3d307b5208b6530553fc4777f2","target":"graph","created_at":"2026-07-05T11:10:12Z","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/2505.20451/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Today, large language models are widely used as judges to evaluate responses from other language models. Hence, it is imperative to benchmark and improve these LLM-judges on real-world language model usage: a typical human-assistant conversation is lengthy, and shows significant diversity in topics, intents, and requirements across turns, e.g. social interactions, task requests, feedback. We present Amulet, a framework that leverages pertinent linguistic concepts of dialog-acts and maxims to improve the accuracy of LLM-judges on preference data with complex, multi-turn conversational context. ","authors_text":"Anurag Mudgil, Brihi Joshi, Sahana Ramnath, Skyler Hallinan, Xiang Ren","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:46:38Z","title":"Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20451","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":"sha256:73224dfd3c68b7bd2e27e8cb8023a2ce2bbd2a942282662d72467a61230a5ac3","target":"record","created_at":"2026-07-05T11:10:12Z","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":"ea0bdb1833748e4c09a85e56ea469da9a659dbc2abae373775bf20710ecf8c64","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:46:38Z","title_canon_sha256":"a3f24674ad6c83f65d3f1a58255cfadaef4b6330a9f3c487ac95d39052cd417e"},"schema_version":"1.0","source":{"id":"2505.20451","kind":"arxiv","version":1}},"canonical_sha256":"c3a56748f3bba3a5ea889a58352ca1684bca14f4149894f105a02d1903966298","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c3a56748f3bba3a5ea889a58352ca1684bca14f4149894f105a02d1903966298","first_computed_at":"2026-07-05T11:10:12.677621Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:12.677621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J+58Z/LvnvcUQ3t09BFyjxIToE31QFCk2Dm2EVFH/QLlqOyvIR/9UbLlyE5N7jQju+BVPmUGObL997AawVi3Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:12.678121Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.20451","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73224dfd3c68b7bd2e27e8cb8023a2ce2bbd2a942282662d72467a61230a5ac3","sha256:1cb3dc40383674e6739fa700425111c1b93a7e3d307b5208b6530553fc4777f2"],"state_sha256":"96e8700b845178b2c8f1353a1b62af43ee374de859f9fe8730ab697ebc66d392"}