{"as_of":"2026-08-08T22:53:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:04e985522563d38180c4d43b4e5afca25acf1a36d73d0c64f1a80427421833d9","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":25,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":25,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":25,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":25,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T13:46:41.722624Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":1,"source":"arxiv_reference","source_observed_at":"2026-08-05T02:28:24.338817Z","state":"measured"}],"external_citation_measurements":[{"count":13,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2301.12652","last_updated":"2023-05-24T05:08:07Z","snapshot_observed_at":"2026-08-02T02:08:12.414817Z","submitted_at":"2023-01-30T04:18:09Z","title":"REPLUG: Retrieval-Augmented Black-Box Language Models","version":4},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-05-17T12:41:53.833754Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2301.12652"},"observation_digest":"sha256:5d581e9f4e1eca86734fdc88681f4092b8e4fb2d8124fd4915a6fedcd3fd0962","observation_id":"89d50f23-276d-488a-91ca-207866a5de5d","resolution":{"observed_at":"2026-05-17T12:41:54.157591Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2309.07597","last_updated":"2024-09-24T03:01:25Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-14T10:57:50Z","title":"C-Pack: Packed Resources For General Chinese Embeddings","version":5},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-05-13T13:24:32.084878Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2309.07597"},"observation_digest":"sha256:e60059b6aaa0ee93a18662b4131cd055d6d95d99fe86872c9656881a85725a93","observation_id":"021cd3df-8573-4f6f-93c6-9e12341bd929","resolution":{"observed_at":"2026-05-13T13:24:32.146825Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2401.15391","last_updated":"2024-01-27T11:41:48Z","snapshot_observed_at":"2026-08-02T18:59:01.488566Z","submitted_at":"2024-01-27T11:41:48Z","title":"MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-05-15T13:54:19.264893Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2401.15391"},"observation_digest":"sha256:657501852522f1b08b81ba10d36de3fc25d6eb56173092de75956e7d4f98ddaa","observation_id":"c308368e-0a39-437b-b143-773356fafe8a","resolution":{"observed_at":"2026-05-15T13:54:19.706602Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-08T13:46:41.722624Z","title":"Yixuan Tang and Yi Yang","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.07131","last_updated":"2025-04-01T12:39:12Z","snapshot_observed_at":"2026-08-08T13:40:45.330993Z","submitted_at":"2025-02-10T23:49:39Z","title":"TWICE: What Advantages Can Low-Resource Domain-Specific Embedding Model Bring? -- A Case Study on Korea Financial Texts","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-08T13:46:41.722624Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2502.07131"},"observation_digest":"sha256:522566b25ebec002aa2c546c7d1098556662318adeed6ca71c3a3f19e2f00828","observation_id":"b7d7b3c0-d56c-461e-bec8-09791e9b380f","resolution":{"observed_at":"2026-08-08T13:46:41.722624Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-08T12:25:12.330701Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2502.07555","last_updated":"2025-02-12T03:33:06Z","snapshot_observed_at":"2026-08-08T12:18:01.094635Z","submitted_at":"2025-02-11T13:48:10Z","title":"O1 Embedder: Let Retrievers Think Before Action","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-08T12:25:12.330701Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2502.07555"},"observation_digest":"sha256:61c8e4b4a7bfa949f7647562b99e7717ee195ff4e0f32cce72ec0879c2e5765f","observation_id":"4be6ae3b-8bde-47ae-8215-b5ce395b94f2","resolution":{"observed_at":"2026-08-08T12:25:12.330701Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-07T15:12:24.472276Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.17131","last_updated":"2025-05-22T01:59:54Z","snapshot_observed_at":"2026-08-07T23:47:01.265288Z","submitted_at":"2025-05-22T01:59:54Z","title":"Relative Bias: A Comparative Framework for Quantifying Bias in LLMs","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T15:12:24.472276Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2505.17131"},"observation_digest":"sha256:e8db421bafe6681ee07e80d447475dbf0ca69c6042568a82239f0edd4b01043f","observation_id":"118dff2d-0753-4dd6-9bc8-c24c37b20be7","resolution":{"observed_at":"2026-08-07T15:12:24.472276Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-07T13:45:15.017927Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2505.21128","last_updated":"2025-05-27T12:45:45Z","snapshot_observed_at":"2026-08-07T13:32:28.017857Z","submitted_at":"2025-05-27T12:45:45Z","title":"Named Entity Swapping for Metadata Anonymization in a Text Corpus","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T13:45:15.017927Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2505.21128"},"observation_digest":"sha256:673db131c69173638e3f51637c945425f1af463ca33d8c3f437a5ebdcfbb3103","observation_id":"24ddb460-6ef5-42f0-9db7-db5421ad3661","resolution":{"observed_at":"2026-08-07T13:45:15.017927Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-07T04:09:33.302508Z","title":"One embedder, any task: Instruction-finetuned text embeddings.arXiv preprint arXiv:2212.09741, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.17277","last_updated":"2025-06-13T07:44:53Z","snapshot_observed_at":"2026-08-08T06:02:29.925753Z","submitted_at":"2025-06-13T07:44:53Z","title":"Chunk Twice, Embed Once: A Systematic Study of Segmentation and Representation Trade-offs in Chemistry-Aware Retrieval-Augmented Generation","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T04:09:33.302508Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2506.17277"},"observation_digest":"sha256:66b7f240efb1d6b983c3b407b71af8c2fac1f8287f5e677a194a65e40c7dfe7c","observation_id":"6c5b92c1-e38f-47bf-8f80-221fcf8972c8","resolution":{"observed_at":"2026-08-07T04:09:33.302508Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-06T19:11:19.699224Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.06405","last_updated":"2025-07-08T21:15:12Z","snapshot_observed_at":"2026-08-06T19:03:19.862902Z","submitted_at":"2025-07-08T21:15:12Z","title":"SImpHAR: Advancing impedance-based human activity recognition using 3D simulation and text-to-motion models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-06T19:11:19.699224Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2507.06405"},"observation_digest":"sha256:becd48f0b300b159c7611072b23e6d464bd555c80f9f8a63161b74cc0df0b7e8","observation_id":"6883a59a-de35-4ced-bf0e-1fa5ed415976","resolution":{"observed_at":"2026-08-06T19:11:19.699224Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-06T17:15:44.323907Z","title":"One embedder, any task: Instruction-finetuned text embeddings,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.11310","last_updated":"2025-07-15T13:42:32Z","snapshot_observed_at":"2026-08-06T17:08:40.759428Z","submitted_at":"2025-07-15T13:42:32Z","title":"LRCTI: A Large Language Model-Based Framework for Multi-Step Evidence Retrieval and Reasoning in Cyber Threat Intelligence Credibility Verification","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-06T17:15:44.323907Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2507.11310"},"observation_digest":"sha256:778bd3c80128c89b9651e6f736b51eb4eca15a152d4fdbc5b9478708f9d6f04f","observation_id":"74d000c0-5df8-4577-8d25-d1b78cad69f4","resolution":{"observed_at":"2026-08-06T17:15:44.323907Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T19:49:52.058216Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2508.11779","last_updated":"2025-08-15T19:05:57Z","snapshot_observed_at":"2026-08-08T17:09:38.233329Z","submitted_at":"2025-08-15T19:05:57Z","title":"A Multi-Task Evaluation of LLMs' Processing of Academic Text Input","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-05T19:49:52.058216Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2508.11779"},"observation_digest":"sha256:4b30c96ad3708a0b095a0070e9cbd35612a2dbc5246e5179d2fe1f425e10d3d5","observation_id":"a5b7a1f0-1b5a-4b6f-b200-0b67fb4a2009","resolution":{"observed_at":"2026-08-05T19:49:52.058216Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2509.20354","last_updated":"2025-11-01T23:38:27Z","snapshot_observed_at":"2026-08-01T16:32:32.583858Z","submitted_at":"2025-09-24T17:56:51Z","title":"EmbeddingGemma: Powerful and Lightweight Text Representations","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-05-15T12:07:20.946370Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2509.20354"},"observation_digest":"sha256:849fb7dc5e6e9f428e7d519baf422a9dfd992b124c268bd2345aa4329c75cdd5","observation_id":"787527fc-2be2-4f24-8251-c165c00fdbe8","resolution":{"observed_at":"2026-05-15T12:07:21.077467Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-03T23:28:00.724571Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2511.05913","last_updated":"2026-05-31T08:50:30Z","snapshot_observed_at":"2026-08-08T16:07:43.266021Z","submitted_at":"2025-11-08T08:18:44Z","title":"NILC: Discovering New Intents with LLM-assisted Clustering","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T23:28:00.724571Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2511.05913"},"observation_digest":"sha256:d61211c6763a23e4d7fbbf8cf313ddebb9b99e3c884aea0a5b3cbe3212b26e43","observation_id":"df305b97-9e87-4018-88b7-d4934d595b10","resolution":{"observed_at":"2026-08-03T23:28:00.724571Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2511.15424","last_updated":"2026-04-07T16:13:27Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-11-19T13:22:08Z","title":"LLM-MemCluster: Empowering Large Language Models with Dynamic Memory for Text Clustering","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-17T20:45:26.815527Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2511.15424"},"observation_digest":"sha256:e21bbd46ebc768e0e127acf6ce80ee2d76d48f3bcfd88260490336d8bcc4a62d","observation_id":"ea6fb512-17a2-40bc-86f3-0ff008c05638","resolution":{"observed_at":"2026-05-17T20:50:15.141225Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2601.13188","last_updated":"2026-05-31T23:24:12Z","snapshot_observed_at":"2026-08-06T06:37:02.963853Z","submitted_at":"2026-01-19T16:11:19Z","title":"Large Language Lovers: Lived Experiences of Negotiating Agency and Platform Control in AI Companionship","version":2},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-05-16T13:30:47.813209Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2601.13188"},"observation_digest":"sha256:3de3e22300d6335824b69b04623bdb58f1f525020e4c4ff84f5b0cc624ebd91d","observation_id":"fc6bdb11-6a4b-4c79-bdf6-d13877eae3ea","resolution":{"observed_at":"2026-05-16T13:30:58.513226Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-03T09:40:07.837316Z","title":"Smith, Luke Zettlemoyer, and Tao Yu","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2601.13188","last_updated":"2026-05-31T23:24:12Z","snapshot_observed_at":"2026-08-06T06:37:02.963853Z","submitted_at":"2026-01-19T16:11:19Z","title":"Large Language Lovers: Lived Experiences of Negotiating Agency and Platform Control in AI Companionship","version":3},"reference_index":102,"source":"pdf_text","source_observed_at":"2026-08-03T09:40:07.837316Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2601.13188"},"observation_digest":"sha256:c5d3163e7b9e072c07929d9be82e0b56a5c192b018aa0e1db52e6506725e2223","observation_id":"7a6b7eea-d2fc-4515-847a-c4fa31445992","resolution":{"observed_at":"2026-08-03T09:40:07.837316Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2602.23620","last_updated":"2026-04-27T03:42:57Z","snapshot_observed_at":"2026-08-05T23:25:43.959344Z","submitted_at":"2026-02-27T02:53:17Z","title":"Synthetic Data Powers Product Retrieval for Long-tail Knowledge-Intensive Queries in E-commerce Search","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-15T19:27:17.802597Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2602.23620"},"observation_digest":"sha256:64973d8c35b5dcc1393461d73e0dbea3a0f77d85c5eb6ae531f0855768f2635b","observation_id":"08e6c655-7b2b-46e9-8164-082a1dc5a466","resolution":{"observed_at":"2026-05-15T19:30:16.762903Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2605.02950","last_updated":"2026-06-06T17:04:15Z","snapshot_observed_at":"2026-07-06T23:15:55.848885Z","submitted_at":"2026-05-01T17:46:26Z","title":"Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-05-09T19:45:15.249619Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2605.02950"},"observation_digest":"sha256:86683b502437260229edd566e72799a2a4ad68d1da13d83da8261523e34ffd25","observation_id":"6298dd4f-6a92-4f41-bab0-51d7e5f4345c","resolution":{"observed_at":"2026-05-09T19:45:54.225868Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2605.02950","last_updated":"2026-06-06T17:04:15Z","snapshot_observed_at":"2026-07-06T23:15:55.848885Z","submitted_at":"2026-05-01T17:46:26Z","title":"Kernel Affine Hull Machines as Compute-Efficient Encoders for Frozen Semantic Spaces","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-07-01T07:38:00.290159Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2605.02950"},"observation_digest":"sha256:fae26bcc0a47c49ad1dda4326a532f9181095ac31669708a0df0d8a85553596c","observation_id":"1f59ffe2-f240-4a34-bbb4-a131c7908d7f","resolution":{"observed_at":"2026-07-01T07:45:28.692511Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2605.04018","last_updated":"2026-05-05T17:42:50Z","snapshot_observed_at":"2026-07-06T23:16:49.553583Z","submitted_at":"2026-05-05T17:42:50Z","title":"Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-07T16:06:51.876295Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2605.04018"},"observation_digest":"sha256:24e1c294d6f1b73528e58bc3f7745be4e91fdc1faf0db098bcf870a8ea89b54a","observation_id":"c708ca3f-4839-4b44-b7e3-6706e49cb946","resolution":{"observed_at":"2026-05-11T23:51:40.850194Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2605.15542","last_updated":"2026-05-15T02:27:41Z","snapshot_observed_at":"2026-08-01T22:59:27.797060Z","submitted_at":"2026-05-15T02:27:41Z","title":"DRS-GUI: Dynamic Region Search for Training-Free GUI Grounding","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-05-19T14:24:48.938948Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2605.15542"},"observation_digest":"sha256:4bc84b296a0043d1f2051a4397cb827650808f994656e93698e008481d6195aa","observation_id":"52cb277b-32cc-4692-95db-4a57f42b8982","resolution":{"observed_at":"2026-05-19T14:27:24.239271Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2606.22769","last_updated":"2026-06-22T02:15:28Z","snapshot_observed_at":"2026-08-02T11:50:00.793732Z","submitted_at":"2026-06-22T02:15:28Z","title":"Noise is Signal: Density-Based Outliers as Leading Indicators of Occupational Emergence in Labor Market Text","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-26T09:33:55.989475Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2606.22769"},"observation_digest":"sha256:833ea8e2ba29b05047da02a80eaa58681e56adc239e96732941c78b02be703fb","observation_id":"cc6842f2-9120-4f26-a3dc-ad32d743e387","resolution":{"observed_at":"2026-07-04T09:49:44.120242Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":"2212.09741","doi":"10.48550/arxiv.2212.09741","metadata_source":"arxiv_reference","pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"One embedder, any task: Instruction-finetuned text embeddings","venue":"arXiv (Cornell University)","work_id":"03a885b1-d6e5-49db-86e9-a41843d605ed","year":2022},"citing_paper":{"arxiv_id":"2606.24094","last_updated":"2026-06-23T03:20:09Z","snapshot_observed_at":"2026-08-06T22:07:11.614337Z","submitted_at":"2026-06-23T03:20:09Z","title":"Universal Guideline-Driven Image Clustering via a Hybrid LLM Agent","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-06-26T01:19:19.253076Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2606.24094"},"observation_digest":"sha256:a4159414d7578d4621810c6b7ca4a3f58aa2f8729b9146ac5635cd9b982bdd74","observation_id":"c4c2818f-952b-4b1f-b24e-714f86d29ffb","resolution":{"observed_at":"2026-07-04T15:49:57.652139Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"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"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-01T14:17:29.504094Z","title":"arXiv preprint arXiv:2212.09741 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.18825","last_updated":"2026-07-21T08:01:17Z","snapshot_observed_at":"2026-08-08T11:57:56.292573Z","submitted_at":"2026-07-21T08:01:17Z","title":"AILQA: Evaluating AI-Driven Legal Question Answering Systems for the Indian Legal System","version":1},"reference_index":79,"source":"arxiv_source","source_observed_at":"2026-08-01T14:17:29.504094Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2607.18825"},"observation_digest":"sha256:04ca294d817ea3b42720f0c3df9400eae02039f554c6b8711d18f7205b55de75","observation_id":"e3c87036-8e23-43a0-b70f-fd4adaf349ad","resolution":{"observed_at":"2026-08-01T14:17:29.504094Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.09741","snapshot_observed_at":"2026-08-01T02:23:46.019790Z","title":"One embedder, any task: Instruction-finetuned text embeddings.arXiv preprint arXiv:2212.09741, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2607.25471","last_updated":"2026-07-28T09:03:38Z","snapshot_observed_at":"2026-08-08T15:30:57.511627Z","submitted_at":"2026-07-28T09:03:38Z","title":"TRWH: A Text-Driven Random Walk Heterogeneous GNN for Semantic-Aware Sparse Recommendation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T02:23:46.019790Z"},"links":{"cited_paper":"/paper/2212.09741","citing_paper":"/paper/2607.25471"},"observation_digest":"sha256:5d29ac2580ff430d80c08ab8af6dcb9956e1813d4f1faffc4aa40e23e7dfdec3","observation_id":"0f9e1693-c7b3-451d-bf0c-b1f733313019","resolution":{"observed_at":"2026-08-01T02:23:46.019790Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2212.09741/citation-record","integrity":"/paper/2212.09741/integrity","json":"/paper/2212.09741/citation-record.json","paper":"/paper/2212.09741"},"outbound":[],"paper":{"arxiv_id":"2212.09741","last_updated":"2023-05-30T15:22:50Z","latest_version":3,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-04T08:37:37.119739Z","submitted_at":"2022-12-19T18:57:05Z","title":"One Embedder, Any Task: Instruction-Finetuned Text Embeddings"},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 0 of 0 outbound references and 25 inbound Pith citation observations for arXiv:2212.09741."}