{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:67TKQPGGGMV4APJA264ZESE3EQ","short_pith_number":"pith:67TKQPGG","schema_version":"1.0","canonical_sha256":"f7e6a83cc6332bc03d20d7b992489b241867f5f485188251b9a45883043b4064","source":{"kind":"arxiv","id":"2605.18660","version":1},"attestation_state":"computed","paper":{"title":"Evaluating Multi-turn Human-AI Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Shi Ding, Sijian Tan","submitted_at":"2026-05-18T17:08:10Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as collaborative assistants, yet dominant NLP evaluation practices remain centered on aggregate metrics such as accuracy and fluency. These approaches often overlook behaviors that are critical in human-facing settings (e.g., consistency across multiple turns and iterative refinement). In this paper, we examine limitations of current NLP evaluation practices and introduce TCR, a structured framework for evaluating human--AI interaction using educational LLM assistants as an illustrative example. TCR emphasizes dimensions such as transparency, "},"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":"2605.18660","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2026-05-18T17:08:10Z","cross_cats_sorted":[],"title_canon_sha256":"c4a40e3fb322983a56efdffb12f5e3e5a1c8bf8f4be6a76b2e8d5ee9185f0b29","abstract_canon_sha256":"a55c205f5215fc3077d0f8a2dae82679f969074e7f0c55d756a97244ed6191e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:13.273799Z","signature_b64":"P4kqZt/oqKKWnA0EsczinSAB7lXIQbboIxINCD7ehVn6+ZC2kMgQyeIAnrBOBMrLSg+6MUKudA7bDAcEkM3bDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7e6a83cc6332bc03d20d7b992489b241867f5f485188251b9a45883043b4064","last_reissued_at":"2026-05-20T00:06:13.272994Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:13.272994Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evaluating Multi-turn Human-AI Interaction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.HC","authors_text":"Shi Ding, Sijian Tan","submitted_at":"2026-05-18T17:08:10Z","abstract_excerpt":"Large language models (LLMs) are increasingly used as collaborative assistants, yet dominant NLP evaluation practices remain centered on aggregate metrics such as accuracy and fluency. These approaches often overlook behaviors that are critical in human-facing settings (e.g., consistency across multiple turns and iterative refinement). In this paper, we examine limitations of current NLP evaluation practices and introduce TCR, a structured framework for evaluating human--AI interaction using educational LLM assistants as an illustrative example. TCR emphasizes dimensions such as transparency, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18660","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/2605.18660/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.152329Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"be2dca1a638e2ad607a8bf5f2fcebba451c05835f08b286c775733a2931dff84"},"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":"2605.18660","created_at":"2026-05-20T00:06:13.273127+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18660v1","created_at":"2026-05-20T00:06:13.273127+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18660","created_at":"2026-05-20T00:06:13.273127+00:00"},{"alias_kind":"pith_short_12","alias_value":"67TKQPGGGMV4","created_at":"2026-05-20T00:06:13.273127+00:00"},{"alias_kind":"pith_short_16","alias_value":"67TKQPGGGMV4APJA","created_at":"2026-05-20T00:06:13.273127+00:00"},{"alias_kind":"pith_short_8","alias_value":"67TKQPGG","created_at":"2026-05-20T00:06:13.273127+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/67TKQPGGGMV4APJA264ZESE3EQ","json":"https://pith.science/pith/67TKQPGGGMV4APJA264ZESE3EQ.json","graph_json":"https://pith.science/api/pith-number/67TKQPGGGMV4APJA264ZESE3EQ/graph.json","events_json":"https://pith.science/api/pith-number/67TKQPGGGMV4APJA264ZESE3EQ/events.json","paper":"https://pith.science/paper/67TKQPGG"},"agent_actions":{"view_html":"https://pith.science/pith/67TKQPGGGMV4APJA264ZESE3EQ","download_json":"https://pith.science/pith/67TKQPGGGMV4APJA264ZESE3EQ.json","view_paper":"https://pith.science/paper/67TKQPGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18660&json=true","fetch_graph":"https://pith.science/api/pith-number/67TKQPGGGMV4APJA264ZESE3EQ/graph.json","fetch_events":"https://pith.science/api/pith-number/67TKQPGGGMV4APJA264ZESE3EQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/67TKQPGGGMV4APJA264ZESE3EQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/67TKQPGGGMV4APJA264ZESE3EQ/action/storage_attestation","attest_author":"https://pith.science/pith/67TKQPGGGMV4APJA264ZESE3EQ/action/author_attestation","sign_citation":"https://pith.science/pith/67TKQPGGGMV4APJA264ZESE3EQ/action/citation_signature","submit_replication":"https://pith.science/pith/67TKQPGGGMV4APJA264ZESE3EQ/action/replication_record"}},"created_at":"2026-05-20T00:06:13.273127+00:00","updated_at":"2026-05-20T00:06:13.273127+00:00"}