{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IBQ35HKHJADZXGHZOMUYEL5RYM","short_pith_number":"pith:IBQ35HKH","schema_version":"1.0","canonical_sha256":"4061be9d4748079b98f97329822fb1c326439333dcd3948388240aced4f9c606","source":{"kind":"arxiv","id":"2603.14217","version":2},"attestation_state":"computed","paper":{"title":"Rethinking Evaluation in Retrieval-Augmented Personalized Dialogue: A Cognitive and Linguistic Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Traum, Tianyi Zhang","submitted_at":"2026-03-15T04:36:16Z","abstract_excerpt":"In cognitive science and linguistic theory, dialogue is not seen as a chain of independent utterances but rather as a joint activity sustained by coherence, consistency, and shared understanding. However, many systems for open-domain and personalized dialogue use surface-level similarity metrics (e.g., BLEU, ROUGE, F1) as one of their main reporting measures, which fail to capture these deeper aspects of conversational quality. We re-examine a notable retrieval-augmented framework for personalized dialogue, LAPDOG, as a case study for evaluation methodology. Using both human and LLM-based judg"},"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":"2603.14217","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-03-15T04:36:16Z","cross_cats_sorted":[],"title_canon_sha256":"5c52b54b9b95b7f2fd53fb98f9d217c7a4f5ad3b267f6ded79fa76e58095f3bb","abstract_canon_sha256":"21d6c4103dad63296dbb82993b77cfdae45fb804050e7ee20aa573b0707459e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:27.854153Z","signature_b64":"pAvGUVIQ0/SZFe2WJMWUSsYWSUCp/AgHfQfW9zc3MaHrJRkEiYr7eCsJtczSo7/6Cnoh5cAYlyNNq1njS1LuDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4061be9d4748079b98f97329822fb1c326439333dcd3948388240aced4f9c606","last_reissued_at":"2026-07-02T00:18:27.853355Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:27.853355Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Evaluation in Retrieval-Augmented Personalized Dialogue: A Cognitive and Linguistic Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"David Traum, Tianyi Zhang","submitted_at":"2026-03-15T04:36:16Z","abstract_excerpt":"In cognitive science and linguistic theory, dialogue is not seen as a chain of independent utterances but rather as a joint activity sustained by coherence, consistency, and shared understanding. However, many systems for open-domain and personalized dialogue use surface-level similarity metrics (e.g., BLEU, ROUGE, F1) as one of their main reporting measures, which fail to capture these deeper aspects of conversational quality. We re-examine a notable retrieval-augmented framework for personalized dialogue, LAPDOG, as a case study for evaluation methodology. Using both human and LLM-based judg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.14217","kind":"arxiv","version":2},"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/2603.14217/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":"2603.14217","created_at":"2026-07-02T00:18:27.853470+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.14217v2","created_at":"2026-07-02T00:18:27.853470+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.14217","created_at":"2026-07-02T00:18:27.853470+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBQ35HKHJADZ","created_at":"2026-07-02T00:18:27.853470+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBQ35HKHJADZXGHZ","created_at":"2026-07-02T00:18:27.853470+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBQ35HKH","created_at":"2026-07-02T00:18:27.853470+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.09461","citing_title":"H2HMem: A Multimodal Memory Benchmark for Agents in Human-Human Interactions","ref_index":60,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBQ35HKHJADZXGHZOMUYEL5RYM","json":"https://pith.science/pith/IBQ35HKHJADZXGHZOMUYEL5RYM.json","graph_json":"https://pith.science/api/pith-number/IBQ35HKHJADZXGHZOMUYEL5RYM/graph.json","events_json":"https://pith.science/api/pith-number/IBQ35HKHJADZXGHZOMUYEL5RYM/events.json","paper":"https://pith.science/paper/IBQ35HKH"},"agent_actions":{"view_html":"https://pith.science/pith/IBQ35HKHJADZXGHZOMUYEL5RYM","download_json":"https://pith.science/pith/IBQ35HKHJADZXGHZOMUYEL5RYM.json","view_paper":"https://pith.science/paper/IBQ35HKH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.14217&json=true","fetch_graph":"https://pith.science/api/pith-number/IBQ35HKHJADZXGHZOMUYEL5RYM/graph.json","fetch_events":"https://pith.science/api/pith-number/IBQ35HKHJADZXGHZOMUYEL5RYM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBQ35HKHJADZXGHZOMUYEL5RYM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBQ35HKHJADZXGHZOMUYEL5RYM/action/storage_attestation","attest_author":"https://pith.science/pith/IBQ35HKHJADZXGHZOMUYEL5RYM/action/author_attestation","sign_citation":"https://pith.science/pith/IBQ35HKHJADZXGHZOMUYEL5RYM/action/citation_signature","submit_replication":"https://pith.science/pith/IBQ35HKHJADZXGHZOMUYEL5RYM/action/replication_record"}},"created_at":"2026-07-02T00:18:27.853470+00:00","updated_at":"2026-07-02T00:18:27.853470+00:00"}