{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:S3UN4HPVCGTK22KCWCJAIHPF7L","short_pith_number":"pith:S3UN4HPV","schema_version":"1.0","canonical_sha256":"96e8de1df511a6ad6942b092041de5faf7a7a0e14f1169cad98192e87d4bcb00","source":{"kind":"arxiv","id":"2203.10012","version":1},"attestation_state":"computed","paper":{"title":"Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, David Traum, Dilek Hakkani-Tur, Jan Deriu, Jinho Choi, Kallirroi Georgila, Luis Fernando D'Haro, Maxine Eskenazi, Milica Gasic, Samira Shaikh, Shikib Mehri, Verena Rieser, Yi-Ting Yeh, Yizhe Zhang, Zekang Li, Zhou Yu","submitted_at":"2022-03-18T15:21:11Z","abstract_excerpt":"This is a report on the NSF Future Directions Workshop on Automatic Evaluation of Dialog. The workshop explored the current state of the art along with its limitations and suggested promising directions for future work in this important and very rapidly changing area of research."},"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":"2203.10012","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-18T15:21:11Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"d0d215dbbd93512632d6adf8c56c3e3c832f8012855583df1b83d2fe7ccb754f","abstract_canon_sha256":"56ff2a0af0b6eca734b794dec92ffba0e944a88d18a9ef31fca92755607e98dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:26.882222Z","signature_b64":"eAML2OLE4JYHMCTy7u6LwOJyRjk1UiVIn3eH1AxmJEnh1PEuMcYeGYnH50izuRw3gtf73PuaTIYFFEanpEMWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96e8de1df511a6ad6942b092041de5faf7a7a0e14f1169cad98192e87d4bcb00","last_reissued_at":"2026-07-05T04:06:26.881700Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:26.881700Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Report from the NSF Future Directions Workshop on Automatic Evaluation of Dialog: Research Directions and Challenges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Zhang, David Traum, Dilek Hakkani-Tur, Jan Deriu, Jinho Choi, Kallirroi Georgila, Luis Fernando D'Haro, Maxine Eskenazi, Milica Gasic, Samira Shaikh, Shikib Mehri, Verena Rieser, Yi-Ting Yeh, Yizhe Zhang, Zekang Li, Zhou Yu","submitted_at":"2022-03-18T15:21:11Z","abstract_excerpt":"This is a report on the NSF Future Directions Workshop on Automatic Evaluation of Dialog. The workshop explored the current state of the art along with its limitations and suggested promising directions for future work in this important and very rapidly changing area of research."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.10012","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/2203.10012/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":"2203.10012","created_at":"2026-07-05T04:06:26.881757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.10012v1","created_at":"2026-07-05T04:06:26.881757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.10012","created_at":"2026-07-05T04:06:26.881757+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3UN4HPVCGTK","created_at":"2026-07-05T04:06:26.881757+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3UN4HPVCGTK22KC","created_at":"2026-07-05T04:06:26.881757+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3UN4HPV","created_at":"2026-07-05T04:06:26.881757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20451","citing_title":"Amulet: Putting Complex Multi-Turn Conversations on the Stand with LLM Juries","ref_index":51,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3UN4HPVCGTK22KCWCJAIHPF7L","json":"https://pith.science/pith/S3UN4HPVCGTK22KCWCJAIHPF7L.json","graph_json":"https://pith.science/api/pith-number/S3UN4HPVCGTK22KCWCJAIHPF7L/graph.json","events_json":"https://pith.science/api/pith-number/S3UN4HPVCGTK22KCWCJAIHPF7L/events.json","paper":"https://pith.science/paper/S3UN4HPV"},"agent_actions":{"view_html":"https://pith.science/pith/S3UN4HPVCGTK22KCWCJAIHPF7L","download_json":"https://pith.science/pith/S3UN4HPVCGTK22KCWCJAIHPF7L.json","view_paper":"https://pith.science/paper/S3UN4HPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.10012&json=true","fetch_graph":"https://pith.science/api/pith-number/S3UN4HPVCGTK22KCWCJAIHPF7L/graph.json","fetch_events":"https://pith.science/api/pith-number/S3UN4HPVCGTK22KCWCJAIHPF7L/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3UN4HPVCGTK22KCWCJAIHPF7L/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3UN4HPVCGTK22KCWCJAIHPF7L/action/storage_attestation","attest_author":"https://pith.science/pith/S3UN4HPVCGTK22KCWCJAIHPF7L/action/author_attestation","sign_citation":"https://pith.science/pith/S3UN4HPVCGTK22KCWCJAIHPF7L/action/citation_signature","submit_replication":"https://pith.science/pith/S3UN4HPVCGTK22KCWCJAIHPF7L/action/replication_record"}},"created_at":"2026-07-05T04:06:26.881757+00:00","updated_at":"2026-07-05T04:06:26.881757+00:00"}