{"as_of":"2026-08-20T07:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:26ef882aa34cdf4a8c09052343c6c64a23f48549479a3c0c4f93f3de45d330ce","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":11,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":11,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-20T06:33:59.587034+00:00","state":"measured"},{"denominator":11,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":11,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T20:34:54.223392Z","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":"2026-07-04T13:29:51.687574Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-08-11T05:44:00.115811Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2412.17250","last_updated":"2024-12-23T03:49:00Z","snapshot_observed_at":"2026-08-16T20:08:08.807866Z","submitted_at":"2024-12-23T03:49:00Z","title":"SyNeg: LLM-Driven Synthetic Hard-Negatives for Dense Retrieval","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-11T05:44:00.115811Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2412.17250"},"observation_digest":"sha256:f75a3e1cd55f863e19dabf4f1fbe576dbd02916ef8638055254a4355f068cb1a","observation_id":"7bb1e88f-0f45-4896-869b-cedb8b393e95","resolution":{"observed_at":"2026-08-11T05:44:00.115811Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-08-10T21:55:28.493847Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.03475","last_updated":"2025-01-07T02:33:25Z","snapshot_observed_at":"2026-08-19T20:06:25.434649Z","submitted_at":"2025-01-07T02:33:25Z","title":"Reading with Intent -- Neutralizing Intent","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-10T21:55:28.493847Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2501.03475"},"observation_digest":"sha256:436ea2635d35a323ed0e1fa5a1e8d18318ed89fe4c78a721f6b1b0d37d4c6f90","observation_id":"013b96bf-85d5-494d-85d1-7f316087263d","resolution":{"observed_at":"2026-08-10T21:55:28.493847Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-08-10T15:10:28.128645Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2501.14459","last_updated":"2025-01-24T12:42:53Z","snapshot_observed_at":"2026-08-17T23:15:04.836955Z","submitted_at":"2025-01-24T12:42:53Z","title":"Interpretability Analysis of Domain Adapted Dense Retrievers","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-10T15:10:28.128645Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2501.14459"},"observation_digest":"sha256:b49a7675c5d0aec2bd2e07f4e4da97677ba791f43389d34e1b2e2c47b955feee","observation_id":"2895f64c-8281-4521-b1fb-cad455c25334","resolution":{"observed_at":"2026-08-10T15:10:28.128645Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":"2112.07577","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-07-04T13:29:51.687574Z","title":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk","venue":null,"work_id":"88f30337-09f9-46d6-ad48-6f552829ced4","year":2022},"citing_paper":{"arxiv_id":"2504.21015","last_updated":"2026-05-10T18:30:41Z","snapshot_observed_at":"2026-08-19T20:06:26.783892Z","submitted_at":"2025-04-20T08:34:10Z","title":"Don't Retrieve, Generate: Prompting LLMs for Synthetic Training Data in Dense Retrieval","version":4},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-05-22T19:35:02.029358Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2504.21015"},"observation_digest":"sha256:c73e6e07e3ee4799d060b98bbeca35fdffcc229d7cea39c7f795d75f89ef9b90","observation_id":"b5bfeb76-4744-4c5c-9efa-5e1d29cb329c","resolution":{"observed_at":"2026-05-22T19:35:03.933032Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-08-15T20:34:54.223392Z","title":"Gpl: Generative pseudo labeling for unsupervised domain adaptation of dense retrieval.arXiv preprint arXiv:2112.07577, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.12697","last_updated":"2025-05-19T04:37:53Z","snapshot_observed_at":"2026-08-16T06:45:16.946059Z","submitted_at":"2025-05-19T04:37:53Z","title":"Towards A Generalist Code Embedding Model Based On Massive Data Synthesis","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T20:34:54.223392Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2505.12697"},"observation_digest":"sha256:45be4741ab5792c73aaa80c04bef0d420c4d9464faf70bed5329e4ea801473a7","observation_id":"873342c7-56e6-4472-a317-54678523a41c","resolution":{"observed_at":"2026-08-15T20:34:54.223392Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-08-07T13:47:13.039866Z","title":"Gpl: Generative pseudo labeling for unsuper- vised domain adaptation of dense retrieval.arXiv preprint arXiv:2112.07577, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.21010","last_updated":"2025-05-27T10:44:55Z","snapshot_observed_at":"2026-08-17T04:07:34.502399Z","submitted_at":"2025-05-27T10:44:55Z","title":"Unified Alignment Protocol: Making Sense of the Unlabeled Data in New Domains","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T13:47:13.039866Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2505.21010"},"observation_digest":"sha256:bb8590cdd601e67b332a0192f758b474b811bd60065e251b0e5f14710992b43d","observation_id":"9f429c72-e27b-42a8-b0a2-940ba24924bf","resolution":{"observed_at":"2026-08-07T13:47:13.039866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-08-07T12:57:25.443501Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.23059","last_updated":"2025-05-29T04:04:25Z","snapshot_observed_at":"2026-08-12T08:00:22.121091Z","submitted_at":"2025-05-29T04:04:25Z","title":"From Token to Action: State Machine Reasoning to Mitigate Overthinking in Information Retrieval","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T12:57:25.443501Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2505.23059"},"observation_digest":"sha256:ee2a426ea914bf4c0b3cd374431f774ce660db4c9d2d5cce71f67370719c53a4","observation_id":"2df3b569-de6c-4746-9b88-90c0c388d0fa","resolution":{"observed_at":"2026-08-07T12:57:25.443501Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-08-07T11:39:46.532542Z","title":"arXiv preprint arXiv:2112.07577","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.01877","last_updated":"2025-06-02T17:06:35Z","snapshot_observed_at":"2026-08-18T16:46:01.214499Z","submitted_at":"2025-06-02T17:06:35Z","title":"When Should Dense Retrievers Be Updated in Evolving Corpora? Detecting Out-of-Distribution Corpora Using GradNormIR","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T11:39:46.532542Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2506.01877"},"observation_digest":"sha256:800ca28ab9dfd97afc57f4bc03438365411c28defb49a049e775df665e276a1d","observation_id":"80ada7e7-e338-4e80-8931-a54464ce4362","resolution":{"observed_at":"2026-08-07T11:39:46.532542Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":"2112.07577","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-07-04T13:29:51.687574Z","title":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk","venue":null,"work_id":"88f30337-09f9-46d6-ad48-6f552829ced4","year":2022},"citing_paper":{"arxiv_id":"2604.25142","last_updated":"2026-04-28T02:43:03Z","snapshot_observed_at":"2026-08-20T07:11:47.459097Z","submitted_at":"2026-04-28T02:43:03Z","title":"UnIte: Uncertainty-based Iterative Document Sampling for Domain Adaptation in Information Retrieval","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-07T15:51:41.243646Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2604.25142"},"observation_digest":"sha256:757b0832183c7025d96182c98a025fd6c788039ffbc6d66068472ef03c59a050","observation_id":"29f1badf-a46c-47f4-bb57-0d51efa64424","resolution":{"observed_at":"2026-05-12T00:06:15.923052Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":"2112.07577","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-07-04T13:29:51.687574Z","title":"Lee Xiong, Chenyan Xiong, Ye Li, Kwok-Fung Tang, Jialin Liu, Paul Bennett, Junaid Ahmed, and Arnold Overwijk","venue":null,"work_id":"88f30337-09f9-46d6-ad48-6f552829ced4","year":2022},"citing_paper":{"arxiv_id":"2606.27291","last_updated":"2026-06-25T17:09:12Z","snapshot_observed_at":"2026-08-17T18:58:43.775992Z","submitted_at":"2026-06-25T17:09:12Z","title":"Designing Reward Signals for Portable Query Generation: A Case Study in Industrial Semantic Job Search","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-26T05:10:59.825246Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2606.27291"},"observation_digest":"sha256:ea0cddf9104e223da20743a083ef9fabf7df55c18e4cfd719fece355ecf0f821","observation_id":"3f9d5571-ad4e-4d05-94d2-f0d4aedbdffa","resolution":{"observed_at":"2026-07-04T13:29:51.689191Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-20T06:33:59.587034+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07577","snapshot_observed_at":"2026-08-01T14:30:35.141673Z","title":"GPL: Generative Pseudo Labeling for Unsu- pervised Domain Adaptation of Dense Retrieval,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.18756","last_updated":"2026-07-21T06:25:46Z","snapshot_observed_at":"2026-08-18T09:55:20.224453Z","submitted_at":"2026-07-21T06:25:46Z","title":"RAGAL: A Frugal, Fully Local Retrieval-Augmented Assistant for Technical Support at a Government Agency","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T14:30:35.141673Z"},"links":{"cited_paper":"/paper/2112.07577","citing_paper":"/paper/2607.18756"},"observation_digest":"sha256:4d29c0f0e7aa976cae4e98bb7c44efa661bd355f7f54457464fe415487d61a49","observation_id":"1132ebc8-669b-438b-9602-395a41e38998","resolution":{"observed_at":"2026-08-01T14:30:35.141673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2112.07577/citation-record","integrity":"/paper/2112.07577/integrity","json":"/paper/2112.07577/citation-record.json","paper":"/paper/2112.07577"},"outbound":[],"paper":{"arxiv_id":"2112.07577","last_updated":"2022-04-25T16:32:24Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-19T20:06:00.883810Z","submitted_at":"2021-12-14T17:34:43Z","title":"GPL: Generative Pseudo Labeling for Unsupervised Domain Adaptation of Dense Retrieval"},"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":"2026-08-20T06:33:59.587034+00:00","source":"crossref"},{"observed_at":"2026-08-20T06:33:54.927442+00:00","source":"retraction_watch"}],"thesis":"As of 20 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 11 inbound Pith citation observations for arXiv:2112.07577."}