{"as_of":"2026-08-14T11:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d122b59b19f1ecf123604a056db56140549ca3f431e305c16d8092d52376868b","coverage":[{"denominator":31,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":31,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-11T14:53:05.993724Z","state":"measured"},{"denominator":34,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":34,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-14T06:32:32.682623+00:00","state":"measured"},{"denominator":3,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":3,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T05:18:21.906109Z","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":"2026-05-18T13:01:23.426021Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.11556","snapshot_observed_at":"2026-08-07T05:18:21.906109Z","title":"Token prepending: A training-free approach for eliciting better sentence embeddings from llms.arXiv preprint arXiv:2412.11556,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.08354","last_updated":"2026-05-28T08:13:47Z","snapshot_observed_at":"2026-08-10T06:36:57.892160Z","submitted_at":"2025-06-10T02:11:42Z","title":"Position: Text Embeddings Should Capture Implicit Semantics, Not Just Surface Meaning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T05:18:21.906109Z"},"links":{"cited_paper":"/paper/2412.11556","citing_paper":"/paper/2506.08354"},"observation_digest":"sha256:a6dd349f8d4db6f80a62627d9ee8c592929eda7d93d8903bb979bb7089599237","observation_id":"b724c061-ebe8-466a-8f05-66db570e912c","resolution":{"observed_at":"2026-08-07T05:18:21.906109Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"cited_work":{"arxiv_id":"2412.11556","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2412.11556","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Token prepending: A training-free approach for eliciting better sentence embeddings from llms","venue":null,"work_id":"ebb26fbc-fc25-4830-bf06-e8d9c1fb8138","year":null},"citing_paper":{"arxiv_id":"2509.24621","last_updated":"2026-05-25T10:53:36Z","snapshot_observed_at":"2026-08-08T21:41:13.842209Z","submitted_at":"2025-09-29T11:28:42Z","title":"FreeRet: MLLMs as Training-Free Retrievers","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-18T13:00:31.952588Z"},"links":{"cited_paper":"/paper/2412.11556","citing_paper":"/paper/2509.24621"},"observation_digest":"sha256:b9c662fcf3898b15aaf3d1c1038cc3fe59a4c3c12c0c06e363268154333ffdbd","observation_id":"1a8f6853-ed34-488e-91bc-60165a83da4d","resolution":{"observed_at":"2026-05-18T13:01:23.429112Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.11556","snapshot_observed_at":"2026-08-04T13:51:44.359594Z","title":"Token prepending: A training-free approach for eliciting better sentence embeddings from llms","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2509.24621","last_updated":"2026-05-25T10:53:36Z","snapshot_observed_at":"2026-08-08T21:41:13.842209Z","submitted_at":"2025-09-29T11:28:42Z","title":"FreeRet: MLLMs as Training-Free Retrievers","version":3},"reference_index":2009,"source":"pdf_text","source_observed_at":"2026-08-04T13:51:44.359594Z"},"links":{"cited_paper":"/paper/2412.11556","citing_paper":"/paper/2509.24621"},"observation_digest":"sha256:1d588df86b033f2846b0327a955a7bebe770d07008719f044235eb4dc4cf1052","observation_id":"255c323b-f667-4d5a-9ada-2c6cf0d17b70","resolution":{"observed_at":"2026-08-04T13:51:44.359594Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2412.11556/citation-record","integrity":"/paper/2412.11556/integrity","json":"/paper/2412.11556/citation-record.json","paper":"/paper/2412.11556"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.253782Z","title":null,"venue":null,"work_id":"ba954117-9935-4291-b032-08035b53d51b","year":2024},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.990198Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:aca11cdd5d1835c47821128017e2c14ba6610a93ee189aa93cceeec191be6f02","observation_id":"108ed56d-534e-4a5b-a79b-cffcb8617ea3","resolution":{"observed_at":"2026-08-11T14:53:06.257920Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-08-13T17:20:44.002518Z","submitted_at":"2024-07-31T17:54:27Z","title":"The Llama 3 Herd of Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.21783","snapshot_observed_at":"2026-08-11T14:53:05.917628Z","title":"arXiv preprint arXiv:2407.21783","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.917628Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:6ab5c8d2bbf915cd928a54eb8cd64a1301d70aeea7c1705c14c1307a1223cd8b","observation_id":"efcb2972-75fc-4a61-8ab9-f4f24c324847","resolution":{"observed_at":"2026-08-11T14:53:05.917628Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.312953Z","title":null,"venue":null,"work_id":"4711b4ed-faee-4de8-af1a-fe80fb370088","year":2019},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.921097Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:229ec2c7a560c65a48459fe7d1551f1d5c972d5bc06e32da83817dcf07dbb22e","observation_id":"4989ea08-aa33-4dd0-bdad-99ca2c21efd4","resolution":{"observed_at":"2026-08-11T14:53:06.316743Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17428","last_updated":"2025-02-25T00:35:18Z","snapshot_observed_at":"2026-08-14T08:11:36.232487Z","submitted_at":"2024-05-27T17:59:45Z","title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.17428","snapshot_observed_at":"2026-08-11T14:53:05.935530Z","title":"CoRR, abs/2405.17428","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.935530Z"},"links":{"cited_paper":"/paper/2405.17428","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:d93b10241a4261d80488e47e504257a05f9bf6b8e669fd1fe3d7cb5e9a5168e5","observation_id":"40c01b9e-e723-4523-b7d8-0fb927a882cf","resolution":{"observed_at":"2026-08-11T14:53:05.935530Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.18458","last_updated":"2024-07-22T09:35:08Z","snapshot_observed_at":"2026-08-13T04:08:05.464184Z","submitted_at":"2024-02-28T16:35:52Z","title":"Meta-Task Prompting Elicits Embeddings from Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.18458","snapshot_observed_at":"2026-08-11T14:53:05.939461Z","title":"arXiv preprint arXiv:2402.18458","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.939461Z"},"links":{"cited_paper":"/paper/2402.18458","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:c8e3aa76334188fdf41a77200e06a8f289da22d1770d069f6966f003142ef82d","observation_id":"7758a319-e8c4-4002-ab26-a09df6f5922b","resolution":{"observed_at":"2026-08-11T14:53:05.939461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.12871","last_updated":"2024-12-31T07:56:13Z","snapshot_observed_at":"2026-08-13T10:07:33.623064Z","submitted_at":"2023-09-22T13:52:42Z","title":"AnglE-optimized Text Embeddings","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.12871","snapshot_observed_at":"2026-08-11T14:53:05.943734Z","title":"arXiv preprint arXiv:2309.12871","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.943734Z"},"links":{"cited_paper":"/paper/2309.12871","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:6a903cc034b9c3182f139458c9af413cb55dcb07bdd30946921cffbffcac210a","observation_id":"0fc4cf6c-2208-4cb9-a08e-a228e0a7aca1","resolution":{"observed_at":"2026-08-11T14:53:05.943734Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.01509","last_updated":"2024-06-09T13:07:50Z","snapshot_observed_at":"2026-08-13T04:04:39.831807Z","submitted_at":"2024-03-03T13:14:47Z","title":"Fantastic Semantics and Where to Find Them: Investigating Which Layers of Generative LLMs Reflect Lexical Semantics","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.01509","snapshot_observed_at":"2026-08-11T14:53:05.947792Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.947792Z"},"links":{"cited_paper":"/paper/2403.01509","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:b2b2eb13be2f828477bab55244314061be00a3eec1c77e3eaca1d1e8af21bcdd","observation_id":"64afa96f-68a7-4d35-8637-7117b79dd4e5","resolution":{"observed_at":"2026-08-11T14:53:05.947792Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.290191Z","title":"In Proceedings of the Ninth International Conference on Language Resources and Evaluation, LREC 2014 , pages 216–223","venue":null,"work_id":"13bc1180-373a-4edd-8bca-ae7d6f69c212","year":2014},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.951953Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:695804f368bd141911297f35e5ee77ad006f9e99823bf4a5d7e4dd4cdc336837","observation_id":"540d13bb-0eae-430f-9666-8e04dd8daa98","resolution":{"observed_at":"2026-08-11T14:53:06.294130Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09906","last_updated":"2025-03-03T04:28:49Z","snapshot_observed_at":"2026-08-13T04:18:23.781512Z","submitted_at":"2024-02-15T12:12:19Z","title":"Generative Representational Instruction Tuning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.09906","snapshot_observed_at":"2026-08-11T14:53:05.955495Z","title":"CoRR, abs/2402.09906","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.955495Z"},"links":{"cited_paper":"/paper/2402.09906","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:ed610bbc9b0c35cc2b805c3057abb6b151d2a940c47b1db98f24b23ebfa35b44","observation_id":"62d74e90-e4b5-4092-ace0-fc3dfcaad84c","resolution":{"observed_at":"2026-08-11T14:53:05.955495Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2210.07316","last_updated":"2023-03-19T13:37:01Z","snapshot_observed_at":"2026-08-14T05:00:07.792972Z","submitted_at":"2022-10-13T19:42:08Z","title":"MTEB: Massive Text Embedding Benchmark","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2210.07316","snapshot_observed_at":"2026-08-11T14:53:05.959574Z","title":"arXiv preprint arXiv:2210.07316","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.959574Z"},"links":{"cited_paper":"/paper/2210.07316","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:c3c14e6f24694bb428aa2c7300ee2a7a1d14b10e4246c0c18dd2bf0c39f89c76","observation_id":"3e7ef034-ef87-4e85-88e6-17d2f871fe21","resolution":{"observed_at":"2026-08-11T14:53:05.959574Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.278065Z","title":"In Proceedings of the 2013 conference on empiri- cal methods in natural language processing , pages 1631–1642","venue":null,"work_id":"a3fb3358-abd8-4529-874f-ac90ecebfa1f","year":2013},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.963481Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:dc218cf185ab15232b21c36e3718f6ccea7869fadece89083cc8dc95e0d0e8b2","observation_id":"b7d8345a-23cf-4941-a151-cb1036ec8e1a","resolution":{"observed_at":"2026-08-11T14:53:06.282271Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15449","last_updated":"2025-09-07T18:50:16Z","snapshot_observed_at":"2026-08-13T04:11:58.141409Z","submitted_at":"2024-02-23T17:25:10Z","title":"Repetition Improves Language Model Embeddings","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.15449","snapshot_observed_at":"2026-08-11T14:53:05.967185Z","title":"arXiv preprint arXiv:2402.15449","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.967185Z"},"links":{"cited_paper":"/paper/2402.15449","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:23be0ac2705c7bbdeac6087e0b54778a2d911b7c7a6535c07aba35e391229dc1","observation_id":"4f665b67-7b9d-4602-9ae0-3b424173a7cc","resolution":{"observed_at":"2026-08-11T14:53:05.967185Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.265989Z","title":"In Findings of the Association for Com- putational Linguistics: ACL 2023 , pages 1102–1121","venue":null,"work_id":"3916c03b-e38c-4750-90c6-2e1334e4b387","year":2023},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.971151Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:5434ae896e5fc1f6a9165d34aea481658862192347161795f7b8a95629053368","observation_id":"fafe3187-d9b1-452d-a196-2de4d501bd2d","resolution":{"observed_at":"2026-08-11T14:53:06.270139Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.00118","last_updated":"2024-10-02T15:22:49Z","snapshot_observed_at":"2026-08-02T16:20:09.773989Z","submitted_at":"2024-07-31T19:13:07Z","title":"Gemma 2: Improving Open Language Models at a Practical Size","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2408.00118","snapshot_observed_at":"2026-08-11T14:53:05.974806Z","title":"arXiv preprint arXiv:2408.00118","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.974806Z"},"links":{"cited_paper":"/paper/2408.00118","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:6816edb37e981905ce57d4b39345eb6efabd0ad4a558c498496bfbca97479a64","observation_id":"77d8d5f5-340f-45de-a660-fb2aeb91634b","resolution":{"observed_at":"2026-08-11T14:53:05.974806Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.09288","last_updated":"2023-07-19T17:08:59Z","snapshot_observed_at":"2026-08-07T12:56:43.323460Z","submitted_at":"2023-07-18T14:31:57Z","title":"Llama 2: Open Foundation and Fine-Tuned Chat Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.09288","snapshot_observed_at":"2026-08-11T14:53:05.978674Z","title":"arXiv preprint arXiv:2307.09288","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.978674Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:82287783cf133a80481ddbf996d328c49dc9e06dd31d8b2b84963cb0ed889aa6","observation_id":"67bd6a3b-6023-499d-9885-1c0dacd754e1","resolution":{"observed_at":"2026-08-11T14:53:05.978674Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.10671","last_updated":"2024-09-10T13:25:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-07-15T12:35:42Z","title":"Qwen2 Technical Report","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.10671","snapshot_observed_at":"2026-08-11T14:53:05.982600Z","title":"arXiv preprint arXiv:2407.10671","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.982600Z"},"links":{"cited_paper":"/paper/2407.10671","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:990b5d2dbb2ddc3efa7245004ad5745666963b4e861b26dbd1a1cff1f3f333ce","observation_id":"c987c767-1e0f-4b53-b7d9-ace33d12b5e1","resolution":{"observed_at":"2026-08-11T14:53:05.982600Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.03921","last_updated":"2024-05-15T13:34:14Z","snapshot_observed_at":"2026-08-13T00:37:16.922741Z","submitted_at":"2024-04-05T07:07:15Z","title":"Simple Techniques for Enhancing Sentence Embeddings in Generative Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.03921","snapshot_observed_at":"2026-08-11T14:53:05.986519Z","title":"arXiv preprint arXiv:2404.03921","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.986519Z"},"links":{"cited_paper":"/paper/2404.03921","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:28e17638d24b514b68fae0ff833e1aacb40bf53a53d13a04cadddc2a790b0dd7","observation_id":"690fb787-8cbe-455d-95d4-5252b8001553","resolution":{"observed_at":"2026-08-11T14:53:05.986519Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.241523Z","title":"The representative word for sentence <PST> ’[TEXT]’ is:","venue":null,"work_id":"fe460660-91eb-444f-bd4b-7ea78ff3661e","year":2023},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.993724Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:e69cac4581bd93d2cdbd99b0705ecf93fb0646cff7a7d15d7e91c511daeb5c2a","observation_id":"8d0fe18a-0312-428f-9941-e91045cc824e","resolution":{"observed_at":"2026-08-11T14:53:06.245512Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.342310Z","title":"In Proceedings of the 6th International Workshop on Semantic Evalua- tion, SemEval@NAACL-HLT 2012, pages 385–393","venue":null,"work_id":"79a820ca-4a0b-4951-b1bc-45f3d7c0f9e7","year":2012},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.892712Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:95b15cf79919a0df062a997a241f18f91eec1da096daba63c9e57d0026d466fd","observation_id":"71d7c8b5-7ee0-4092-af7e-e0f6007e54ed","resolution":{"observed_at":"2026-08-11T14:53:06.345641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.332782Z","title":"In Proceed- ings of the Second Joint Conference on Lexical and Computational Semantics, *SEM 2013 , pages 32–43","venue":null,"work_id":"19588bde-0a32-40db-8368-6ca6894e7210","year":2013},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.896381Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:68497e43dd1ee1e96ee5cf1687572d9aca7dc033ceb5a1596c5eaf1600433d62","observation_id":"e8e9d304-a31b-44d4-948d-2c62b752d486","resolution":{"observed_at":"2026-08-11T14:53:06.336084Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.361493Z","title":"In Proceedings of the 8th International Workshop on Semantic Evaluation, SemEval@COLING 2014, pages 81–91","venue":null,"work_id":"3805556c-e35d-4134-bcbe-b019ff97dcef","year":2014},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2014,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.884739Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:4bce679ce338f5b0d071584c39353859900cf628e6471fc3618afaad0dba6073","observation_id":"7de734b9-e67d-4251-903a-08a550f460a4","resolution":{"observed_at":"2026-08-11T14:53:06.364693Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.370823Z","title":"In Proceedings of the 9th International Work- shop on Semantic Evaluation, SemEval@NAACL- HLT 2015, pages 252–263","venue":null,"work_id":"e9116f6e-827d-43b3-a6d8-57dc57615990","year":2015},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.880126Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:f9a48a2a10643928c50d48dbbed9c631d8df4132a91634f2218690873f366c16","observation_id":"e4d5623f-ee44-4e7b-a43b-535780dac4e1","resolution":{"observed_at":"2026-08-11T14:53:06.374074Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.352129Z","title":"In Proceedings of the 10th International Workshop on Semantic Evaluation, SemEval@NAACL-HLT 2016, pages 497–511","venue":null,"work_id":"fbf40148-f178-4ed1-8b0a-daf04dd85798","year":2016},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.888584Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:bf2aadd281de292f3a927ff8cf6a0daefa17865826538de1f1328dcb24c03b18","observation_id":"4e9f45d5-a87a-48e3-9689-0c92f5614879","resolution":{"observed_at":"2026-08-11T14:53:06.355275Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1708.00055","last_updated":"2017-07-31T20:12:06Z","snapshot_observed_at":"2026-08-04T03:50:51.013049Z","submitted_at":"2017-07-31T20:12:06Z","title":"SemEval-2017 Task 1: Semantic Textual Similarity - Multilingual and Cross-lingual Focused Evaluation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.00055","snapshot_observed_at":"2026-08-11T14:53:05.907487Z","title":"CoRR, abs/1708.00055","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.907487Z"},"links":{"cited_paper":"/paper/1708.00055","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:842775f5af35d7c89edbdccefcea49572ced50c73493547bb05bd0808796bd6a","observation_id":"5e3cf048-dc15-4c8f-8ad3-1b4beb8b8923","resolution":{"observed_at":"2026-08-11T14:53:05.907487Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.323240Z","title":"In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, pages 4171–4186","venue":null,"work_id":"729b3de2-26ae-4515-adb4-906aac18752d","year":2019},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.914495Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:9dd5e3487b070a4a5d3dadb674e9198f354e3ee4f665858d7f76e8c59d278f19","observation_id":"16ddd876-1993-4469-9f85-06a84649374f","resolution":{"observed_at":"2026-08-11T14:53:06.326899Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2005.14165","last_updated":"2020-07-22T19:47:17Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2020-05-28T17:29:03Z","title":"Language Models are Few-Shot Learners","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.14165","snapshot_observed_at":"2026-08-11T14:53:05.903623Z","title":"arXiv preprint ArXiv:2005.14165","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.903623Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:62220f342e5d6d5a1467e6a9feb6fbb49e386359b2f0f8bbd092964f3e33b8ff","observation_id":"4bc6f53d-b46a-433b-8d40-9a6fb43ce96d","resolution":{"observed_at":"2026-08-11T14:53:05.903623Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-11T14:53:06.301392Z","title":"In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing , pages 6894–6910","venue":null,"work_id":"440b5089-29b2-464d-b03a-186b5bfab8fc","year":2021},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.924102Z"},"links":{"citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:4824b912410e706b8cb6942c9790b21309fc2b8cf49ee2fce351ae52bde57266","observation_id":"8d57fae1-cb7f-4915-87e4-3ab781e86955","resolution":{"observed_at":"2026-08-11T14:53:06.305665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.07066","last_updated":"2025-02-04T23:34:30Z","snapshot_observed_at":"2026-08-14T10:25:08.147953Z","submitted_at":"2024-04-10T14:56:40Z","title":"Exploring Concept Depth: How Large Language Models Acquire Knowledge and Concept at Different Layers?","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.07066","snapshot_observed_at":"2026-08-11T14:53:05.931474Z","title":"In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, EMNLP 2022, pages 8826–8837","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.931474Z"},"links":{"cited_paper":"/paper/2404.07066","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:638c9c6a25ad10521851e5bbcad5c11175a50c19925d1abfca7361b000bb1bbb","observation_id":"587812f3-9419-4d4f-a230-7593322c6bcb","resolution":{"observed_at":"2026-08-11T14:53:05.931474Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.16645","last_updated":"2023-07-31T13:26:03Z","snapshot_observed_at":"2026-08-13T10:44:09.820718Z","submitted_at":"2023-07-31T13:26:03Z","title":"Scaling Sentence Embeddings with Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.16645","snapshot_observed_at":"2026-08-11T14:53:05.927197Z","title":"arXiv preprint arXiv:2307.16645","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.927197Z"},"links":{"cited_paper":"/paper/2307.16645","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:6ebb29ea507137962a8c62c67f8d124e271ee741737d208b1d61a50d3fb55945","observation_id":"1c45e951-6ada-45e9-9556-78831fd5d4b1","resolution":{"observed_at":"2026-08-11T14:53:05.927197Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2404.05961","last_updated":"2024-08-21T22:46:05Z","snapshot_observed_at":"2026-08-13T00:34:33.528585Z","submitted_at":"2024-04-09T02:51:05Z","title":"LLM2Vec: Large Language Models Are Secretly Powerful Text Encoders","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.05961","snapshot_observed_at":"2026-08-11T14:53:05.899934Z","title":"arXiv preprint arXiv:2404.05961","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.899934Z"},"links":{"cited_paper":"/paper/2404.05961","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:f5b6fad3e44a524a99584ecc10d45d6e8eedef0e33d99e2145408578b1d45fc7","observation_id":"5bde0649-a4d5-4a59-b05e-7530f3345833","resolution":{"observed_at":"2026-08-11T14:53:05.899934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.12831","last_updated":"2025-05-19T08:19:27Z","snapshot_observed_at":"2026-08-07T15:43:24.075247Z","submitted_at":"2025-05-19T08:19:27Z","title":"Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering","version":1},"cited_work":{"arxiv_id":"2505.12831","doi":null,"metadata_source":"pith","pith_arxiv_id":"2505.12831","snapshot_observed_at":"2026-08-11T14:53:06.190428Z","title":"Contrastive Prompting Enhances Sentence Embeddings in LLMs through Inference-Time Steering","venue":"cs.CL","work_id":"44d97195-8e92-424a-a252-ff3e64943c6e","year":2025},"citing_paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-11T14:53:05.910963Z"},"links":{"cited_paper":"/paper/2505.12831","citing_paper":"/paper/2412.11556"},"observation_digest":"sha256:acf9a808fd9ec282710900ff3817a24fb005f98abc99cdc4c3f40dca1eafb95a","observation_id":"583693af-66e4-4723-9206-1fad1f4e1218","resolution":{"observed_at":"2026-08-11T14:53:06.196207Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-14T06:32:32.682623+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2412.11556","last_updated":"2025-07-03T06:24:49Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-12T07:13:44.612878Z","submitted_at":"2024-12-16T08:42:00Z","title":"Token Prepending: A Training-Free Approach for Eliciting Better Sentence Embeddings from LLMs"},"reference_resolution":{"displayed":31,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":19,"verified_exact":0,"verified_fuzzy":11},"total_outbound_references":31},"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":"2026-08-14T06:32:32.682623+00:00","source":"crossref"},{"observed_at":"2026-08-14T06:32:18.44784+00:00","source":"retraction_watch"}],"thesis":"As of 14 August 2026, this Paper Citation Record lists 31 of 31 outbound references and 3 inbound Pith citation observations for arXiv:2412.11556."}