{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PX65HWPZQOMWCRLHZHRXM5QOI2","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":"3d2a2599aff53798a159fcdcc8b8cc4c0946d39c75bc6762aa90bf4370d9cb53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T17:36:36Z","title_canon_sha256":"1b66c6911e4cd963dddebda1ec3733377d8659ac6ff7afcd5f54bbb16ee6d227"},"schema_version":"1.0","source":{"id":"2505.05445","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.05445","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"arxiv_version","alias_value":"2505.05445v2","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05445","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"pith_short_12","alias_value":"PX65HWPZQOMW","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"pith_short_16","alias_value":"PX65HWPZQOMWCRLH","created_at":"2026-07-05T11:40:34Z"},{"alias_kind":"pith_short_8","alias_value":"PX65HWPZ","created_at":"2026-07-05T11:40:34Z"}],"graph_snapshots":[{"event_id":"sha256:c1fde74e3a513cb1f00303d9983b63a693da98db246d8e95b062c42317ceb110","target":"graph","created_at":"2026-07-05T11:40:34Z","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/2505.05445/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The emergence of instruction-tuned large language models (LLMs) has advanced the field of dialogue systems, enabling both realistic user simulations and robust multi-turn conversational agents. However, existing research often evaluates these components in isolation-either focusing on a single user simulator or a specific system design-limiting the generalisability of insights across architectures and configurations. In this work, we propose clem todd (chat-optimized LLMs for task-oriented dialogue systems development), a flexible framework for systematically evaluating dialogue systems under ","authors_text":"Chalamalasetti Kranti, David Schlangen, Sherzod Hakimov","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T17:36:36Z","title":"clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05445","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":"sha256:49a57d4fd3d3a2dc3ad5c7053e9528b2862632530f61624bd288d2ac37976317","target":"record","created_at":"2026-07-05T11:40:34Z","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":"3d2a2599aff53798a159fcdcc8b8cc4c0946d39c75bc6762aa90bf4370d9cb53","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-08T17:36:36Z","title_canon_sha256":"1b66c6911e4cd963dddebda1ec3733377d8659ac6ff7afcd5f54bbb16ee6d227"},"schema_version":"1.0","source":{"id":"2505.05445","kind":"arxiv","version":2}},"canonical_sha256":"7dfdd3d9f98399614567c9e376760e46ab0a9e19251111725182ba5a9f90b674","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7dfdd3d9f98399614567c9e376760e46ab0a9e19251111725182ba5a9f90b674","first_computed_at":"2026-07-05T11:40:34.218838Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:40:34.218838Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DMGsCan+hDJG6ESvybet3yLuwCk/6UcE0WOJWF4pjjIG2uSbdxikneUv5dSmwxPmIrZ9ZuhzIFWHXE1r3zhgBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:40:34.219359Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.05445","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:49a57d4fd3d3a2dc3ad5c7053e9528b2862632530f61624bd288d2ac37976317","sha256:c1fde74e3a513cb1f00303d9983b63a693da98db246d8e95b062c42317ceb110"],"state_sha256":"263da0d024b53159da32b51545f7fa7ff01b28be8b23300be5daab7b17941095"}