{"as_of":"2026-08-19T05:36:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a8b8b84ca8b68d98f3d683699269a8e344a9c091993eb6ca0444c119e8da2ad6","coverage":[{"denominator":0,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":4,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":4,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T23:08:11.541632Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-16T09:17:40.306983Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2106.03706","last_updated":"2021-07-07T20:33:02Z","snapshot_observed_at":"2026-08-18T20:52:58.497958Z","submitted_at":"2021-06-07T15:17:03Z","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03706","snapshot_observed_at":"2026-08-12T19:44:04.030853Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2411.10416","last_updated":"2024-11-15T18:35:00Z","snapshot_observed_at":"2026-08-16T18:06:29.189458Z","submitted_at":"2024-11-15T18:35:00Z","title":"Towards Automatic Evaluation of Task-Oriented Dialogue Flows","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-12T19:44:04.030853Z"},"links":{"cited_paper":"/paper/2106.03706","citing_paper":"/paper/2411.10416"},"observation_digest":"sha256:46ba1e0e16b23d4f4c8d247014950b63e361a638446abb2f0920cb23b20a1539","observation_id":"d1937a42-aa18-4a11-b9c3-e79e2415899b","resolution":{"observed_at":"2026-08-12T19:44:04.030853Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03706","last_updated":"2021-07-07T20:33:02Z","snapshot_observed_at":"2026-08-18T20:52:58.497958Z","submitted_at":"2021-06-07T15:17:03Z","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03706","snapshot_observed_at":"2026-08-11T17:09:54.164611Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.09269","last_updated":"2024-12-12T13:31:58Z","snapshot_observed_at":"2026-08-16T18:05:14.036161Z","submitted_at":"2024-12-12T13:31:58Z","title":"Towards Understanding the Robustness of LLM-based Evaluations under Perturbations","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-11T17:09:54.164611Z"},"links":{"cited_paper":"/paper/2106.03706","citing_paper":"/paper/2412.09269"},"observation_digest":"sha256:714a1d007fa59d7a4f564ea3a96ce57d00656d8c5d148b70f8f00dcc790110af","observation_id":"fc316826-c338-488b-88c9-a5f96bb579d8","resolution":{"observed_at":"2026-08-11T17:09:54.164611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03706","last_updated":"2021-07-07T20:33:02Z","snapshot_observed_at":"2026-08-18T20:52:58.497958Z","submitted_at":"2021-06-07T15:17:03Z","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03706","snapshot_observed_at":"2026-08-15T23:08:11.541632Z","title":"Yi-Ting Yeh, Maxine Eskénazi, and Shikib Mehri","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.05445","last_updated":"2025-07-21T12:42:09Z","snapshot_observed_at":"2026-08-19T02:35:04.733007Z","submitted_at":"2025-05-08T17:36:36Z","title":"clem:todd: A Framework for the Systematic Benchmarking of LLM-Based Task-Oriented Dialogue System Realisations","version":2},"reference_index":2763,"source":"pdf_text","source_observed_at":"2026-08-15T23:08:11.541632Z"},"links":{"cited_paper":"/paper/2106.03706","citing_paper":"/paper/2505.05445"},"observation_digest":"sha256:b535d7c47b3dd89c1cb61ba53da95b870d030768ea594e4a2afc9513a1ac0710","observation_id":"74478500-8350-4ab8-af79-28af5d0e775e","resolution":{"observed_at":"2026-08-15T23:08:11.541632Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03706","last_updated":"2021-07-07T20:33:02Z","snapshot_observed_at":"2026-08-18T20:52:58.497958Z","submitted_at":"2021-06-07T15:17:03Z","title":"A Comprehensive Assessment of Dialog Evaluation Metrics","version":4},"cited_work":{"arxiv_id":"2106.03706","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2106.03706","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"65b6bea1-3878-4114-9a34-b750c4775ec3","year":2021},"citing_paper":{"arxiv_id":"2604.16310","last_updated":"2026-01-30T15:32:14Z","snapshot_observed_at":"2026-07-06T23:03:39.351412Z","submitted_at":"2026-01-30T15:32:14Z","title":"RAG-DIVE: A Dynamic Approach for Multi-Turn Dialogue Evaluation in Retrieval-Augmented Generation","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-05-16T09:13:55.204404Z"},"links":{"cited_paper":"/paper/2106.03706","citing_paper":"/paper/2604.16310"},"observation_digest":"sha256:0ef249cf706415a851a5bd171fb43b7df323e7e836b8a16095d535ac14ce4887","observation_id":"8b89eae5-98eb-45d6-941c-60f05c24201c","resolution":{"observed_at":"2026-05-16T09:17:40.308681Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2106.03706/citation-record","integrity":"/paper/2106.03706/integrity","json":"/paper/2106.03706/citation-record.json","paper":"/paper/2106.03706"},"outbound":[],"paper":{"arxiv_id":"2106.03706","last_updated":"2021-07-07T20:33:02Z","latest_version":4,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-18T20:52:58.497958Z","submitted_at":"2021-06-07T15:17:03Z","title":"A Comprehensive Assessment of Dialog Evaluation Metrics"},"reference_resolution":{"displayed":0,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":0},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 19 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 4 inbound Pith citation observations for arXiv:2106.03706."}