{"as_of":"2026-08-09T05:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:40bbeb914daae9d1227ef6c4d6661a6296d07c25030e3dd879c963847cf78c5d","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-12T01:57:08.818406Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.03515/citation-record","integrity":"/paper/2607.03515/integrity","json":"/paper/2607.03515/citation-record.json","paper":"/paper/2607.03515"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"and Indyk, P","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:6be7b0d822686a4276bfab7ad83fb068022844513a80278ba9e8adb15d269f9f","observation_id":"a8ac2edc-13b0-4985-b988-128df2343e9b","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"ANN-Benchmarks : A benchmarking tool for approximate nearest neighbor algorithms","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:ce2baeaa92bafc217f723098c8af494f24a6e7bc177cf54bd003a6e5a8b18da7","observation_id":"3062feb2-6f41-4fe9-94a2-8876f2485ab0","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.09268","last_updated":"2018-10-31T14:46:47Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-11-28T18:14:11Z","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.09268","snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"MS MARCO : A human generated machine reading comprehension dataset","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"cited_paper":"/paper/1611.09268","citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:7f01c2e170b8128a13ad68d527ecd9428bb2d12bf360412688b1eb9c5caffcc7","observation_id":"f510c42e-9f27-42b7-835f-a92411b0f218","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":null,"venue":null,"work_id":null,"year":1975},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:6ac71b9667d541a17e5408752ce360cf1838a38822d345fb58c5ab461c7f2bfb","observation_id":"aff107a4-85c2-4c77-b854-475c250be245","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Approximate nearest neighbor search under neural similarity metric for large-scale recommendation","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:41dace566c2681a40ffa7dc37317eaecffd9a7bb2b2efd70884604fb681fe6c7","observation_id":"c23f101b-9251-4acc-9496-ae4c011675ed","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Deep neural networks for YouTube recommendations","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:a01d9a1e2ebffbf76aa028355afb1013d518002739dfd590240d08d2fb2912a3","observation_id":"f615ba05-9a68-47d0-bd5f-7b76b5a576f5","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Approximation by superpositions of a sigmoidal function","venue":null,"work_id":null,"year":1989},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:f424672ca0bfcc1772e075b6d043cad5731b21f0fea14e8a38049e00ee43f348","observation_id":"387e111c-b49b-4a1f-9eaa-982c9a85264b","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"and Freund, Y","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:56f14ee32c32e4e70de83bcf48f9afb71438c3386678027e47e4142b06ca3f40","observation_id":"2945a66e-3928-43bb-af7c-539ec7ad48ae","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"and Sinha, K","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:b5a4f959d6989f629d61505049e8f5e2ac86b470285115f0026eb4f2dc87979a","observation_id":"5bf33c94-3270-4f4f-bb19-07318c6e2ae8","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Deep image retrieval: Learning global representations for image search","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:3f1ba60d1f686cf61704baa2b927948ceac586acfec6e9d489874bec9692f9f8","observation_id":"956c8760-532c-46a4-8bee-667abcd5bd62","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02666","last_updated":"2021-01-22T16:24:52Z","snapshot_observed_at":"2026-08-07T18:01:54.178160Z","submitted_at":"2020-10-06T12:35:53Z","title":"Improving Efficient Neural Ranking Models with Cross-Architecture Knowledge Distillation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02666","snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"a tter, S., Althammer, S., Schr \\","venue":null,"work_id":null,"year":2010},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"cited_paper":"/paper/2010.02666","citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:1b1a2a55e4eb3b6e41ac1b9ef6ea000af6cf268c3845ed63022c80b6fb568574","observation_id":"17252891-d6f1-48ec-af90-a561d9c356bf","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Learning deep structured semantic models for web search using clickthrough data","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:c7073775a508e5910fd8f0f08bd6c8799e59f18c79903eabc97ef0ba934482f0","observation_id":"9c14be38-84c1-4645-aed9-024c25d5c3a0","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Poly-encoders: Architectures and pre-training strategies for fast and accurate multi-sentence scoring","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:9f21b7e31ca19e46c4b3815325b3d7e4a2921fbacec765dd662fefaf376ca353","observation_id":"c0daf305-b04f-4125-970f-e02750852830","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"and Motwani, R","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:468b08bc1fd53b79e0a54d39cef1d69e91cc36ba42960fa79f99b5692ae2a4f4","observation_id":"3b7ff3e1-60c9-402d-aad4-91f5e9ddeebf","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Dense passage retrieval for open-domain question answering","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:920e65b121a28ff06e86714070690ed02c8c65a1243e00a33e2f504feca7fc30","observation_id":"b8aeb0fa-338b-43d5-a8fb-90903ca98e90","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":null,"venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:2c9175f8886290dd5f6a08008db39264ec216c2b31cb658bd6a9c24ff7d00a70","observation_id":"20947a00-aad4-4091-a639-46b9fd04ff5b","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Y., Pinkus, A., and Schocken, S","venue":null,"work_id":null,"year":1993},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:45002e8240848dd4e02491830dfde780b9c4e6556f308a5fbc7fe260659d6149","observation_id":"970d14c9-8140-4f13-acb6-1065893ea0b9","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Trans-Encoder : unsupervised sentence-pair modelling through self- and mutual-distillations","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:6e958fa009cacb102d8c11fe5402443c06317ad130af6dfb8a7d063f38390b07","observation_id":"fcc60458-dd9b-4ca7-95f1-e0a293a10098","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Zero-shot entity linking by reading entity descriptions","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:93bffde3d92a46692fcb4131482614022981f1b92a610d76fe8d4e2cfb3984d5","observation_id":"94b9d362-9618-43ca-863a-5670711a2463","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"TwinBERT : Distilling knowledge to twin-structured compressed BERT models for large-scale retrieval","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:d0cb5867686047f1ca8830c979ce184992e845e2b930002a790cee2f2a7a7165","observation_id":"a2d4bf23-e9d4-4c7e-bb6d-67c11a2f3b8d","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Sparse, dense, and attentional representations for text retrieval","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:7715e2c2fe282ce531964517d41eb4daa7da5ab6ea30bf1a0ae438c54b435dc1","observation_id":"d906465e-a533-4269-8fda-922d27dc93ba","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":null,"venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:e43c64c78b6c955e95133c82ecba815f2a1c4f84bd684d735d51ca956994c557","observation_id":"72b2e64c-cac4-41c0-9ae5-742504f91603","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:0cc0e1db084caf3f68f3f43f6310b45c2f7e9050a604647471ea6d9ef56b9043","observation_id":"a25e9376-f990-481c-b835-37787950f0b2","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.06887","last_updated":"2019-10-18T15:51:55Z","snapshot_observed_at":"2026-08-05T22:40:15.909053Z","submitted_at":"2019-08-19T15:44:24Z","title":"Relevance Proximity Graphs for Fast Relevance Retrieval","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.06887","snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"and Babenko, A","venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"cited_paper":"/paper/1908.06887","citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:a96cf852909305cdffdb7def5cfcecd1da0c6321cf3ac90cf6085c6a5d4fa248","observation_id":"99771677-6763-4882-aa0d-ebcbcf731d82","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Searching in metric spaces by spatial approximation","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:521a5a4f43fa0eb0ccbb77da4cb9e9a9cd3128b3a645f9b1d71b2faf5b9c21bd","observation_id":"d2fd0c63-e7cb-4ccc-9290-4151c39e59b9","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Scikit-learn: Machine learning in P ython","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:f0cd9e099bebb4531359e0cfec4b4497037abefe7604df46b64ab62b349f5431","observation_id":"7cd3311e-a25c-44b2-a9c2-9f0ce2f95d44","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"V., and Gulin, A","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:7cb0c19941d381522a13261406056089a98e10032ba7c91d2b147a5eb604e2ec","observation_id":"08474b17-4f2e-4b4f-9ad4-2451d8a53b39","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"X., Dong, D., Wu, H., and Wang, H","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:d9a410a45a073be74a421d7054dc121353d672daa9ef0af6dc11e657682421e7","observation_id":"3a8d4cde-7ab5-44b6-8569-737de2ea6f9a","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"and Gurevych, I","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:a03a401660a92768db42b34893ea2c50e4953818908e6b4b83ab8302d41c1438","observation_id":"82480748-26dd-4e20-863b-1610f973a72f","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"and Prokhorenkova, L","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:eaee6a9805ea631b85caa91dcb155d5f4bd9e708566920a0390f76dbed84670d","observation_id":"314706de-6f00-45bc-ad37-03606a14b6bc","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Scalable zero-shot entity linking with dense entity retrieval","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:e87069f532f29cc854169dc551f0ec3143162e4120e5c6553ff78fc195b20d49","observation_id":"e33bf550-2f81-475e-929b-3ec4c2edcc53","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"A bi-metric framework for efficient nearest neighbor search","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:e99eaab01a3188cbc986f46b79a285f027aa7999ed23ee62642b2eb30da37b93","observation_id":"7ccb6adb-8037-41fa-a001-12f777b520eb","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Efficient nearest neighbor search for cross-encoder models using matrix factorization","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:27c4fca25abddc1871ef207bf6065af4f6b0b21fdb7907f5c9fc507b337c7cf1","observation_id":"e84363ba-aec1-4ea8-b5e8-8ae231534742","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Efficient k-NN search with cross-encoders using adaptive multi-round CUR decomposition","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:a356866362c673189eefff4b476845f083931ed764bfc2f01632ddc7fe635842","observation_id":"11e7da50-216e-4e2d-aa5a-0cb0fd0b7f6f","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Adaptive retrieval and scalable indexing for k-NN search with cross-encoders","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:f24663849c9cc7af9f807bed0b39130bd91908cab9b1126b034b87e7f13dd287","observation_id":"c23f88ad-a3cb-499a-b94e-389571fd9791","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"Modelling domain relationships for transfer learning on retrieval-based question answering systems in e-commerce","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:99b6ec562d587bebc7a8430b903ac70ef34f436440a4338721bf18ba065ca328","observation_id":"09e10b07-367b-48fe-a452-62a1b90dbe04","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-07-12T01:57:08.818406Z","title":"and Stratos, K","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-07-12T01:57:08.818406Z"},"links":{"citing_paper":"/paper/2607.03515"},"observation_digest":"sha256:8b53abbd7e2115b2a737d6d86cc6bccdb6be0098aa70c5e63c3657b44dcb8635","observation_id":"b1419c6e-f266-4088-b611-e6140967681c","resolution":{"observed_at":"2026-07-12T01:57:08.818406Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.03515","last_updated":"2026-07-03T17:41:37Z","latest_version":1,"primary_category":"cs.IR","snapshot_observed_at":"2026-08-04T00:05:19.554486Z","submitted_at":"2026-07-03T17:41:37Z","title":"Relevance-Based Embeddings: Lightweight Candidate Retrieval via Heavy-Ranker Calls"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":37,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":37},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2607.03515."}