{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YOSWOSHTXOR2L2UITJMDKLFBNB","short_pith_number":"pith:YOSWOSHT","schema_version":"1.0","canonical_sha256":"c3a56748f3bba3a5ea889a58352ca1684bca14f4149894f105a02d1903966298","source":{"kind":"arxiv","id":"2505.20451","version":1},"attestation_state":"computed","paper":{"title":"Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anurag Mudgil, Brihi Joshi, Sahana Ramnath, Skyler Hallinan, Xiang Ren","submitted_at":"2025-05-26T18:46:38Z","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. "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.20451","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T18:46:38Z","cross_cats_sorted":[],"title_canon_sha256":"a3f24674ad6c83f65d3f1a58255cfadaef4b6330a9f3c487ac95d39052cd417e","abstract_canon_sha256":"ea0bdb1833748e4c09a85e56ea469da9a659dbc2abae373775bf20710ecf8c64"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:12.678121Z","signature_b64":"J+58Z/LvnvcUQ3t09BFyjxIToE31QFCk2Dm2EVFH/QLlqOyvIR/9UbLlyE5N7jQju+BVPmUGObL997AawVi3Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3a56748f3bba3a5ea889a58352ca1684bca14f4149894f105a02d1903966298","last_reissued_at":"2026-07-05T11:10:12.677621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:12.677621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anurag Mudgil, Brihi Joshi, Sahana Ramnath, Skyler Hallinan, Xiang Ren","submitted_at":"2025-05-26T18:46:38Z","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. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20451","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.20451/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.20451","created_at":"2026-07-05T11:10:12.677680+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20451v1","created_at":"2026-07-05T11:10:12.677680+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20451","created_at":"2026-07-05T11:10:12.677680+00:00"},{"alias_kind":"pith_short_12","alias_value":"YOSWOSHTXOR2","created_at":"2026-07-05T11:10:12.677680+00:00"},{"alias_kind":"pith_short_16","alias_value":"YOSWOSHTXOR2L2UI","created_at":"2026-07-05T11:10:12.677680+00:00"},{"alias_kind":"pith_short_8","alias_value":"YOSWOSHT","created_at":"2026-07-05T11:10:12.677680+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YOSWOSHTXOR2L2UITJMDKLFBNB","json":"https://pith.science/pith/YOSWOSHTXOR2L2UITJMDKLFBNB.json","graph_json":"https://pith.science/api/pith-number/YOSWOSHTXOR2L2UITJMDKLFBNB/graph.json","events_json":"https://pith.science/api/pith-number/YOSWOSHTXOR2L2UITJMDKLFBNB/events.json","paper":"https://pith.science/paper/YOSWOSHT"},"agent_actions":{"view_html":"https://pith.science/pith/YOSWOSHTXOR2L2UITJMDKLFBNB","download_json":"https://pith.science/pith/YOSWOSHTXOR2L2UITJMDKLFBNB.json","view_paper":"https://pith.science/paper/YOSWOSHT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20451&json=true","fetch_graph":"https://pith.science/api/pith-number/YOSWOSHTXOR2L2UITJMDKLFBNB/graph.json","fetch_events":"https://pith.science/api/pith-number/YOSWOSHTXOR2L2UITJMDKLFBNB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YOSWOSHTXOR2L2UITJMDKLFBNB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YOSWOSHTXOR2L2UITJMDKLFBNB/action/storage_attestation","attest_author":"https://pith.science/pith/YOSWOSHTXOR2L2UITJMDKLFBNB/action/author_attestation","sign_citation":"https://pith.science/pith/YOSWOSHTXOR2L2UITJMDKLFBNB/action/citation_signature","submit_replication":"https://pith.science/pith/YOSWOSHTXOR2L2UITJMDKLFBNB/action/replication_record"}},"created_at":"2026-07-05T11:10:12.677680+00:00","updated_at":"2026-07-05T11:10:12.677680+00:00"}