{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7BYVYXIW6FXAYZ3R5VCVCNNW2A","short_pith_number":"pith:7BYVYXIW","schema_version":"1.0","canonical_sha256":"f8715c5d16f16e0c6771ed455135b6d01209e9c03ad9c1cd5443009906dc6a57","source":{"kind":"arxiv","id":"2605.16650","version":1},"attestation_state":"computed","paper":{"title":"SKG-Eval: Stateful Evaluation of Multi-Turn Dialogue via Incremental Semantic Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Avijit Shil, Suman Samui","submitted_at":"2026-05-15T21:39:48Z","abstract_excerpt":"Evaluating multi-turn dialogue systems remains challenging because response quality depends not only on the current prompt, but also on previously established entities, claims, and conversational commitments. Existing automatic evaluators, including LLM-as-a-judge frameworks and embedding-based metrics, largely rely on flat or turn-isolated representations, making them less effective at detecting long-range issues such as contradiction, topic drift, and entity inconsistency. To address this, we propose SKG-Eval, a quasi-deterministic and interpretable framework that models dialogue as an evolv"},"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":"2605.16650","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-15T21:39:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3d789d5a5f4c1989d31bf4c0d27d005715b1f9a680ec90a9df8530274e8c2721","abstract_canon_sha256":"8c31cd2642ae2f3830726a2b3abb4608c6dee3f1f4ee2e7f1f1c99e18df580d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:34.318634Z","signature_b64":"wa7ouA4e/Y4Mxq/NIzmIU88tgAN/3NqROVOvqF4rVv64/73BYwQx5k2UwGFvCD5AY4Rj+N/NHyavhHNx64SMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8715c5d16f16e0c6771ed455135b6d01209e9c03ad9c1cd5443009906dc6a57","last_reissued_at":"2026-05-20T00:02:34.317938Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:34.317938Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SKG-Eval: Stateful Evaluation of Multi-Turn Dialogue via Incremental Semantic Knowledge Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Avijit Shil, Suman Samui","submitted_at":"2026-05-15T21:39:48Z","abstract_excerpt":"Evaluating multi-turn dialogue systems remains challenging because response quality depends not only on the current prompt, but also on previously established entities, claims, and conversational commitments. Existing automatic evaluators, including LLM-as-a-judge frameworks and embedding-based metrics, largely rely on flat or turn-isolated representations, making them less effective at detecting long-range issues such as contradiction, topic drift, and entity inconsistency. To address this, we propose SKG-Eval, a quasi-deterministic and interpretable framework that models dialogue as an evolv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16650","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/2605.16650/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-19T19:01:56.406112Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T18:33:26.525416Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"a58dcd43f852d306b578b1b8e9fdf21d4a3278eeefa2b679f943d15dcabe69e1"},"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":"2605.16650","created_at":"2026-05-20T00:02:34.318061+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16650v1","created_at":"2026-05-20T00:02:34.318061+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16650","created_at":"2026-05-20T00:02:34.318061+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BYVYXIW6FXA","created_at":"2026-05-20T00:02:34.318061+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BYVYXIW6FXAYZ3R","created_at":"2026-05-20T00:02:34.318061+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BYVYXIW","created_at":"2026-05-20T00:02:34.318061+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/7BYVYXIW6FXAYZ3R5VCVCNNW2A","json":"https://pith.science/pith/7BYVYXIW6FXAYZ3R5VCVCNNW2A.json","graph_json":"https://pith.science/api/pith-number/7BYVYXIW6FXAYZ3R5VCVCNNW2A/graph.json","events_json":"https://pith.science/api/pith-number/7BYVYXIW6FXAYZ3R5VCVCNNW2A/events.json","paper":"https://pith.science/paper/7BYVYXIW"},"agent_actions":{"view_html":"https://pith.science/pith/7BYVYXIW6FXAYZ3R5VCVCNNW2A","download_json":"https://pith.science/pith/7BYVYXIW6FXAYZ3R5VCVCNNW2A.json","view_paper":"https://pith.science/paper/7BYVYXIW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16650&json=true","fetch_graph":"https://pith.science/api/pith-number/7BYVYXIW6FXAYZ3R5VCVCNNW2A/graph.json","fetch_events":"https://pith.science/api/pith-number/7BYVYXIW6FXAYZ3R5VCVCNNW2A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BYVYXIW6FXAYZ3R5VCVCNNW2A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BYVYXIW6FXAYZ3R5VCVCNNW2A/action/storage_attestation","attest_author":"https://pith.science/pith/7BYVYXIW6FXAYZ3R5VCVCNNW2A/action/author_attestation","sign_citation":"https://pith.science/pith/7BYVYXIW6FXAYZ3R5VCVCNNW2A/action/citation_signature","submit_replication":"https://pith.science/pith/7BYVYXIW6FXAYZ3R5VCVCNNW2A/action/replication_record"}},"created_at":"2026-05-20T00:02:34.318061+00:00","updated_at":"2026-05-20T00:02:34.318061+00:00"}