{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LBLRW6OY2N2XC4YJ4X4B5PCPTA","short_pith_number":"pith:LBLRW6OY","schema_version":"1.0","canonical_sha256":"58571b79d8d375717309e5f81ebc4f982df956c2ffb0321f6f7fdf3a20bc33be","source":{"kind":"arxiv","id":"2607.09338","version":1},"attestation_state":"computed","paper":{"title":"Towards Detecting Inconsistencies in End-to-end Generated TODs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.CL","authors_text":"Bernardo Magnini, Giovanni Bonetta, Tiziano Labruna","submitted_at":"2026-07-10T12:19:59Z","abstract_excerpt":"Generative AI is profoundly transforming the core technologies behind conversational systems, shifting from component-based to end-to-end approaches. However, Large Language Models (LLMs) may still generate inconsistencies, a critical issue particularly in Task-Oriented Dialogues (TODs), where system responses must strictly adhere to information from a domain knowledge base (e.g., restaurants in a city). A single hallucination (e.g., suggesting a non-existent restaurant) can lead to severe task failures. We investigate a method for automatically detecting inconsistencies by conceptualizing TOD"},"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":"2607.09338","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-10T12:19:59Z","cross_cats_sorted":["cs.SC"],"title_canon_sha256":"27b06bf0312d4987f1f4b053302d3deb293fb5d4fbfaa95fdc87032d5e2b1518","abstract_canon_sha256":"5bc36c606aab2f345edc4e02ff9b54fba7173e86374b1d6eae61ac71d1958e12"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T01:19:03.705926Z","signature_b64":"0vjJnBEjQxFkPKJS9golfm47kqlVsIwIy/kMe5quiuBcigmLVVQ1cfYGkMQCDGCqwIEhi/VDgp3BlFCW4RsKBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58571b79d8d375717309e5f81ebc4f982df956c2ffb0321f6f7fdf3a20bc33be","last_reissued_at":"2026-07-13T01:19:03.704403Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T01:19:03.704403Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Detecting Inconsistencies in End-to-end Generated TODs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SC"],"primary_cat":"cs.CL","authors_text":"Bernardo Magnini, Giovanni Bonetta, Tiziano Labruna","submitted_at":"2026-07-10T12:19:59Z","abstract_excerpt":"Generative AI is profoundly transforming the core technologies behind conversational systems, shifting from component-based to end-to-end approaches. However, Large Language Models (LLMs) may still generate inconsistencies, a critical issue particularly in Task-Oriented Dialogues (TODs), where system responses must strictly adhere to information from a domain knowledge base (e.g., restaurants in a city). A single hallucination (e.g., suggesting a non-existent restaurant) can lead to severe task failures. We investigate a method for automatically detecting inconsistencies by conceptualizing TOD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09338","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/2607.09338/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":"2607.09338","created_at":"2026-07-13T01:19:03.705204+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09338v1","created_at":"2026-07-13T01:19:03.705204+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09338","created_at":"2026-07-13T01:19:03.705204+00:00"},{"alias_kind":"pith_short_12","alias_value":"LBLRW6OY2N2X","created_at":"2026-07-13T01:19:03.705204+00:00"},{"alias_kind":"pith_short_16","alias_value":"LBLRW6OY2N2XC4YJ","created_at":"2026-07-13T01:19:03.705204+00:00"},{"alias_kind":"pith_short_8","alias_value":"LBLRW6OY","created_at":"2026-07-13T01:19:03.705204+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/LBLRW6OY2N2XC4YJ4X4B5PCPTA","json":"https://pith.science/pith/LBLRW6OY2N2XC4YJ4X4B5PCPTA.json","graph_json":"https://pith.science/api/pith-number/LBLRW6OY2N2XC4YJ4X4B5PCPTA/graph.json","events_json":"https://pith.science/api/pith-number/LBLRW6OY2N2XC4YJ4X4B5PCPTA/events.json","paper":"https://pith.science/paper/LBLRW6OY"},"agent_actions":{"view_html":"https://pith.science/pith/LBLRW6OY2N2XC4YJ4X4B5PCPTA","download_json":"https://pith.science/pith/LBLRW6OY2N2XC4YJ4X4B5PCPTA.json","view_paper":"https://pith.science/paper/LBLRW6OY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09338&json=true","fetch_graph":"https://pith.science/api/pith-number/LBLRW6OY2N2XC4YJ4X4B5PCPTA/graph.json","fetch_events":"https://pith.science/api/pith-number/LBLRW6OY2N2XC4YJ4X4B5PCPTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LBLRW6OY2N2XC4YJ4X4B5PCPTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LBLRW6OY2N2XC4YJ4X4B5PCPTA/action/storage_attestation","attest_author":"https://pith.science/pith/LBLRW6OY2N2XC4YJ4X4B5PCPTA/action/author_attestation","sign_citation":"https://pith.science/pith/LBLRW6OY2N2XC4YJ4X4B5PCPTA/action/citation_signature","submit_replication":"https://pith.science/pith/LBLRW6OY2N2XC4YJ4X4B5PCPTA/action/replication_record"}},"created_at":"2026-07-13T01:19:03.705204+00:00","updated_at":"2026-07-13T01:19:03.705204+00:00"}