{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5ZF22WC3WCIAXEWE3SLK6SXREK","short_pith_number":"pith:5ZF22WC3","schema_version":"1.0","canonical_sha256":"ee4bad585bb0900b92c4dc96af4af122ab3128e95660f0d1d33b53c18d034696","source":{"kind":"arxiv","id":"2507.10445","version":1},"attestation_state":"computed","paper":{"title":"Referential ambiguity and clarification requests: comparing human and LLM behaviour","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Madge, Massimo Poesio, Matthew Purver","submitted_at":"2025-07-14T16:28:00Z","abstract_excerpt":"In this work we examine LLMs' ability to ask clarification questions in task-oriented dialogues that follow the asynchronous instruction-giver/instruction-follower format. We present a new corpus that combines two existing annotations of the Minecraft Dialogue Corpus -- one for reference and ambiguity in reference, and one for SDRT including clarifications -- into a single common format providing the necessary information to experiment with clarifications and their relation to ambiguity. With this corpus we compare LLM actions with original human-generated clarification questions, examining ho"},"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":"2507.10445","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-14T16:28:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fb3cf70a93c707552b2ab3985b1c7836ce38af1f430a2a32f59a652e1cb158ab","abstract_canon_sha256":"c096a217d4d296bf56c694c9f9bb26b07474491862ab5c8221263bfb420f4635"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:51.357661Z","signature_b64":"aipC8Z2FLwD4SKndlcHrVWqc19q0zcEfsxsQka6kmR9LhWRhrstqio2Pvf87F0uiouRYDYICWRSmf85LAeBSCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee4bad585bb0900b92c4dc96af4af122ab3128e95660f0d1d33b53c18d034696","last_reissued_at":"2026-07-05T11:36:51.357065Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:51.357065Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Referential ambiguity and clarification requests: comparing human and LLM behaviour","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chris Madge, Massimo Poesio, Matthew Purver","submitted_at":"2025-07-14T16:28:00Z","abstract_excerpt":"In this work we examine LLMs' ability to ask clarification questions in task-oriented dialogues that follow the asynchronous instruction-giver/instruction-follower format. We present a new corpus that combines two existing annotations of the Minecraft Dialogue Corpus -- one for reference and ambiguity in reference, and one for SDRT including clarifications -- into a single common format providing the necessary information to experiment with clarifications and their relation to ambiguity. With this corpus we compare LLM actions with original human-generated clarification questions, examining ho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10445","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/2507.10445/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":"2507.10445","created_at":"2026-07-05T11:36:51.357129+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10445v1","created_at":"2026-07-05T11:36:51.357129+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10445","created_at":"2026-07-05T11:36:51.357129+00:00"},{"alias_kind":"pith_short_12","alias_value":"5ZF22WC3WCIA","created_at":"2026-07-05T11:36:51.357129+00:00"},{"alias_kind":"pith_short_16","alias_value":"5ZF22WC3WCIAXEWE","created_at":"2026-07-05T11:36:51.357129+00:00"},{"alias_kind":"pith_short_8","alias_value":"5ZF22WC3","created_at":"2026-07-05T11:36:51.357129+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21296","citing_title":"Discriminatory Compliance: How LLMs Answer Queries from Protected Groups","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09365","citing_title":"Frame of Reference: Addressing the Challenges of Common Ground Representation in Situational Dialogs","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19245","citing_title":"Talking to a Know-It-All GPT or a Second-Guesser Claude? How Repair reveals unreliable Multi-Turn Behavior in LLMs","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5ZF22WC3WCIAXEWE3SLK6SXREK","json":"https://pith.science/pith/5ZF22WC3WCIAXEWE3SLK6SXREK.json","graph_json":"https://pith.science/api/pith-number/5ZF22WC3WCIAXEWE3SLK6SXREK/graph.json","events_json":"https://pith.science/api/pith-number/5ZF22WC3WCIAXEWE3SLK6SXREK/events.json","paper":"https://pith.science/paper/5ZF22WC3"},"agent_actions":{"view_html":"https://pith.science/pith/5ZF22WC3WCIAXEWE3SLK6SXREK","download_json":"https://pith.science/pith/5ZF22WC3WCIAXEWE3SLK6SXREK.json","view_paper":"https://pith.science/paper/5ZF22WC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10445&json=true","fetch_graph":"https://pith.science/api/pith-number/5ZF22WC3WCIAXEWE3SLK6SXREK/graph.json","fetch_events":"https://pith.science/api/pith-number/5ZF22WC3WCIAXEWE3SLK6SXREK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5ZF22WC3WCIAXEWE3SLK6SXREK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5ZF22WC3WCIAXEWE3SLK6SXREK/action/storage_attestation","attest_author":"https://pith.science/pith/5ZF22WC3WCIAXEWE3SLK6SXREK/action/author_attestation","sign_citation":"https://pith.science/pith/5ZF22WC3WCIAXEWE3SLK6SXREK/action/citation_signature","submit_replication":"https://pith.science/pith/5ZF22WC3WCIAXEWE3SLK6SXREK/action/replication_record"}},"created_at":"2026-07-05T11:36:51.357129+00:00","updated_at":"2026-07-05T11:36:51.357129+00:00"}