{"as_of":"2026-08-08T16:57:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5ed2726cb366b2a3fe3bb6acd297512c74991d51bc1de2e676cfcad07a84c136","coverage":[{"denominator":34,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":34,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:50:51.076830Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T05:40:40.614250Z","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":0,"observed_at":"2026-08-05T02:28:24.338817Z","source":"arxiv_reference"}],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.04344","snapshot_observed_at":"2026-08-06T05:40:40.614250Z","title":"V.; Zhang, B.; Liu, J.; Li, S.; Zhang, L.; and Fan, X","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2508.01474","last_updated":"2025-08-02T19:50:58Z","snapshot_observed_at":"2026-08-08T14:09:19.164861Z","submitted_at":"2025-08-02T19:50:58Z","title":"HT-Transformer: Event Sequences Classification by Accumulating Prefix Information with History Tokens","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-06T05:40:40.614250Z"},"links":{"cited_paper":"/paper/2506.04344","citing_paper":"/paper/2508.01474"},"observation_digest":"sha256:efe9239b81faee6926bed620080e251fe0e41e5ecc65dddfc75d1fc0a30279de","observation_id":"56b8f86f-b531-47e5-9b96-810e811239b1","resolution":{"observed_at":"2026-08-06T05:40:40.614250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"cited_work":{"arxiv_id":"2506.04344","doi":"10.48550/arxiv.2506.04344","metadata_source":"arxiv_reference","pith_arxiv_id":"2506.04344","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"GEM: empowering LLM for both embedding generation and language understanding","venue":"ArXiv.org","work_id":"ddbe73a2-04e7-4266-8b26-e1cc5a11a962","year":2025},"citing_paper":{"arxiv_id":"2604.14403","last_updated":"2026-04-15T20:34:10Z","snapshot_observed_at":"2026-07-06T23:02:13.885476Z","submitted_at":"2026-04-15T20:34:10Z","title":"A Unified Model and Document Representation for On-Device Retrieval-Augmented Generation","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-05-10T11:54:09.047134Z"},"links":{"cited_paper":"/paper/2506.04344","citing_paper":"/paper/2604.14403"},"observation_digest":"sha256:cfc4a7613cd6d7443ebe03104e0051b130b669f3f66e1a92c2a230193d7ccc35","observation_id":"0437573e-5622-4973-baf6-20be6a77b38d","resolution":{"observed_at":"2026-05-10T11:55:20.131760Z","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"}}],"links":{"evidence":"/evidence","html":"/paper/2506.04344/citation-record","integrity":"/paper/2506.04344/integrity","json":"/paper/2506.04344/citation-record.json","paper":"/paper/2506.04344"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2005.11401","last_updated":"2021-04-12T15:42:18Z","snapshot_observed_at":"2026-08-07T05:44:30.677502Z","submitted_at":"2020-05-22T21:34:34Z","title":"Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2005.11401","snapshot_observed_at":"2026-08-07T10:50:50.446367Z","title":"Retrieval- Augmented Generation for Knowledge - Intensive NLP Tasks , April 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.446367Z"},"links":{"cited_paper":"/paper/2005.11401","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:a21493f176a40cdde0309539d7fdcc05472ba7126c1b8adacb631359c5d02a8a","observation_id":"89d5cddc-2109-4a92-8f86-f9af40507ce9","resolution":{"observed_at":"2026-08-07T10:50:50.446367Z","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":"2026-08-07T10:50:50.504529Z","title":"BERT : Pre-training of deep bidirectional transformers for language understanding","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.504529Z"},"links":{"citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:e45a67a81a7474e1b3795f8e46a4cd0189dd8c5de28ef5d7c15d4e250728de40","observation_id":"18c2ab01-402e-4006-acbc-11d60474751f","resolution":{"observed_at":"2026-08-07T10:50:50.504529Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.10005","last_updated":"2022-01-24T23:36:20Z","snapshot_observed_at":"2026-07-06T12:30:51.934079Z","submitted_at":"2022-01-24T23:36:20Z","title":"Text and Code Embeddings by Contrastive Pre-Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.10005","snapshot_observed_at":"2026-08-07T10:50:50.598694Z","title":"Text and code embeddings by contrastive pre-training","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.598694Z"},"links":{"cited_paper":"/paper/2201.10005","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:cfcd83400aecd94add897a821e2b45a1d49161be33273a185ab314a87d1fb1ef","observation_id":"385f74ba-f19f-4050-9853-7edde4a801fb","resolution":{"observed_at":"2026-08-07T10:50:50.598694Z","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":"2026-08-07T10:50:51.575414Z","title":"Fine-tuning llama for multi-stage text retrieval","venue":null,"work_id":"b9c5cdfe-aad9-41aa-b9f3-b5f8b5ee0d7f","year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.710789Z"},"links":{"citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:f1751e22707456c79f6fc80aae9c4d79446a0ec000c8859e2b7652def5a9c84c","observation_id":"1243b383-9268-4dfd-bf42-c37e8c9375b2","resolution":{"observed_at":"2026-08-07T10:50:51.579902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2212.03533","last_updated":"2024-02-22T06:21:51Z","snapshot_observed_at":"2026-07-06T14:27:46.217000Z","submitted_at":"2022-12-07T09:25:54Z","title":"Text Embeddings by Weakly-Supervised Contrastive Pre-training","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.03533","snapshot_observed_at":"2026-08-07T10:50:50.820299Z","title":"Text embeddings by weakly-supervised contrastive pre-training","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.820299Z"},"links":{"cited_paper":"/paper/2212.03533","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:ed507b27891bcfb68cdaa3a3fb0ba64a56bd6b11518ee6841adc2ed6a5a1acf3","observation_id":"b5852f53-e774-4fb2-a52e-972368de05d3","resolution":{"observed_at":"2026-08-07T10:50:50.820299Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08821","last_updated":"2022-05-18T12:29:49Z","snapshot_observed_at":"2026-07-06T11:01:05.577957Z","submitted_at":"2021-04-18T11:27:08Z","title":"SimCSE: Simple Contrastive Learning of Sentence Embeddings","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08821","snapshot_observed_at":"2026-08-07T10:50:50.889962Z","title":"SimCSE : Simple Contrastive Learning of Sentence Embeddings , May 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.889962Z"},"links":{"cited_paper":"/paper/2104.08821","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:36f609bc96c474dd29dfc33b35b22adb16ee18b97b967302f2235be382e0f9c4","observation_id":"89ee3036-7a6c-4bce-b747-77e10c0636a1","resolution":{"observed_at":"2026-08-07T10:50:50.889962Z","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":"2026-08-07T10:50:50.900593Z","title":"C-pack: Packaged resources to advance general chinese embedding, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.900593Z"},"links":{"citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:fe90b3d6064ccdd2af61400280b7ad3cc8900e665bb4dc62b5e71cd242abcf22","observation_id":"4ab25975-5191-4e8c-9bd4-41520f22bdd6","resolution":{"observed_at":"2026-08-07T10:50:50.900593Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.15449","last_updated":"2025-09-07T18:50:16Z","snapshot_observed_at":"2026-08-08T06:06:41.534202Z","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":"2026-08-07T10:50:50.906275Z","title":"Repetition Improves Language Model Embeddings , February 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.906275Z"},"links":{"cited_paper":"/paper/2402.15449","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:3c2f2f3e9166596f7388e6c1839febed19958dde7b3ac05ea3035f30eed11688","observation_id":"c5fc8218-d8a9-436b-aaa5-576f9ff075c9","resolution":{"observed_at":"2026-08-07T10:50:50.906275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.09906","last_updated":"2025-03-03T04:28:49Z","snapshot_observed_at":"2026-07-06T17:30:34.153488Z","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":"2026-08-07T10:50:50.912114Z","title":"Generative representational instruction tuning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.912114Z"},"links":{"cited_paper":"/paper/2402.09906","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:f79cbfd37c032cf1962f058b017924c66c612db6217cc43ea7dbdd034b9ae303","observation_id":"8851ed20-e284-457e-87ac-674e2561cf3d","resolution":{"observed_at":"2026-08-07T10:50:50.912114Z","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":"2026-08-08T03:53:14.177644Z","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":"2026-08-07T10:50:50.918489Z","title":"Llm2vec: Large language models are secretly powerful text encoders","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.918489Z"},"links":{"cited_paper":"/paper/2404.05961","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:1a08b247a4f6affe34faad6e70a89e1749f41edd6d93f1009402f319d92a00b4","observation_id":"9700de77-2f49-4fa5-948a-12517ac0b089","resolution":{"observed_at":"2026-08-07T10:50:50.918489Z","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":"2026-07-06T14:04:58.943383Z","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":"2026-08-07T10:50:50.922897Z","title":"MTEB : Massive text embedding benchmark","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.922897Z"},"links":{"cited_paper":"/paper/2210.07316","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:00d4e57001e95ffc30789c2e8c68d5b665fb8fc567d19fba64d0bba790f6761e","observation_id":"ab6a3e69-e4ea-4ebb-8e61-a26ff110038c","resolution":{"observed_at":"2026-08-07T10:50:50.922897Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.13663","last_updated":"2024-12-19T06:32:26Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-18T09:39:44Z","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.13663","snapshot_observed_at":"2026-08-07T10:50:50.928922Z","title":"Smarter, Better , Faster , Longer : A Modern Bidirectional Encoder for Fast , Memory Efficient , and Long Context Finetuning and Inference , December 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.928922Z"},"links":{"cited_paper":"/paper/2412.13663","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:28b02a5ac5c71da2e0d72ecf70c0690d9fcbe01dd6a86a71bddff243901fe8b6","observation_id":"7525c314-ae57-4354-8548-9a76959bc985","resolution":{"observed_at":"2026-08-07T10:50:50.928922Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2304.08467","last_updated":"2024-02-12T19:03:18Z","snapshot_observed_at":"2026-08-03T18:12:47.785090Z","submitted_at":"2023-04-17T17:47:37Z","title":"Learning to Compress Prompts with Gist Tokens","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.08467","snapshot_observed_at":"2026-08-07T10:50:50.934692Z","title":"Learning to Compress Prompts with Gist Tokens , February 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.934692Z"},"links":{"cited_paper":"/paper/2304.08467","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:b4570c630f664652d41c49299eec6709f74a27c5870b273fbc2421335df032e3","observation_id":"bb5dd380-cf9b-49e1-9c75-b7b0f5df5c91","resolution":{"observed_at":"2026-08-07T10:50:50.934692Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2406.12275","last_updated":"2025-03-03T09:05:52Z","snapshot_observed_at":"2026-07-06T18:32:44.452493Z","submitted_at":"2024-06-18T05:05:12Z","title":"VoCo-LLaMA: Towards Vision Compression with Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.12275","snapshot_observed_at":"2026-08-07T10:50:50.940626Z","title":"Voco-llama: Towards vision compression with large language models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.940626Z"},"links":{"cited_paper":"/paper/2406.12275","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:d73db9bd51d968d57591cc30d3ba9fa86687704cab4c58e95aafa226feeaf2ac","observation_id":"fa0c8107-91a4-4810-9bac-fc901fbcce76","resolution":{"observed_at":"2026-08-07T10:50:50.940626Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.10435","last_updated":"2023-05-21T10:12:02Z","snapshot_observed_at":"2026-07-06T15:28:53.270447Z","submitted_at":"2023-05-11T19:20:38Z","title":"Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directions","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.10435","snapshot_observed_at":"2026-08-07T10:50:50.947353Z","title":"Vasilakos, and Thippa Reddy Gadekallu","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.947353Z"},"links":{"cited_paper":"/paper/2305.10435","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:c1aa36529abf4d11ec225e9b0eb6e238a0aaeecce42671442ea206f0f6360f9f","observation_id":"66468508-7e84-4028-9783-158e188347a4","resolution":{"observed_at":"2026-08-07T10:50:50.947353Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.21783","last_updated":"2024-11-23T23:27:33Z","snapshot_observed_at":"2026-07-06T18:55:11.576666Z","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":"2026-08-07T10:50:50.956133Z","title":"The llama 3 herd of models","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.956133Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:684445456553480250cfbacf14bb9e042a460f224c5c05f85833c6f997af0647","observation_id":"b7a4681f-2b96-4002-8650-670a079aea7e","resolution":{"observed_at":"2026-08-07T10:50:50.956133Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.11805","last_updated":"2025-05-09T21:04:06Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-12-19T02:39:27Z","title":"Gemini: A Family of Highly Capable Multimodal Models","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.11805","snapshot_observed_at":"2026-08-07T10:50:50.961472Z","title":"Gemini: a family of highly capable multimodal models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.961472Z"},"links":{"cited_paper":"/paper/2312.11805","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:8e11a34df96bc827a8e397bad0a25b5ac4f2d132143ff1619e4370ff1a0782b0","observation_id":"bd1ef6d0-214c-455c-b700-308f01b879d5","resolution":{"observed_at":"2026-08-07T10:50:50.961472Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06825","last_updated":"2023-10-10T17:54:58Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-10-10T17:54:58Z","title":"Mistral 7B","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.06825","snapshot_observed_at":"2026-08-07T10:50:50.966606Z","title":"Mistral 7b","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.966606Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:466c8e836a46c7ccde8ec7c4995405d3da023c6cb95a964a64f635d696ba4355","observation_id":"4308d845-5dff-444b-827f-b9e21b5f35ae","resolution":{"observed_at":"2026-08-07T10:50:50.966606Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.19437","last_updated":"2025-02-18T17:26:38Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-27T04:03:16Z","title":"DeepSeek-V3 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.19437","snapshot_observed_at":"2026-08-07T10:50:50.972727Z","title":"Deepseek-v3 technical report","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.972727Z"},"links":{"cited_paper":"/paper/2412.19437","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:79f995af64f38b5c807a3e59f9c23fca83e121a18681e9108762df8c48d899f2","observation_id":"d5682ada-6695-4761-8aa0-5460b51e9b37","resolution":{"observed_at":"2026-08-07T10:50:50.972727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-07T10:50:50.978473Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.978473Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:233193c87d288ef7132ead3686acf218848454ba69fda2586107e32ee5037863","observation_id":"af21dc5a-92e3-42a7-a61c-631129e94067","resolution":{"observed_at":"2026-08-07T10:50:50.978473Z","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":"2026-08-07T10:50:50.983856Z","title":"u ttler, Mike Lewis, Wen-tau Yih, Tim Rockt \\","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.983856Z"},"links":{"citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:bf901864e1197f8c44d450580cb44c310756ae2bd5415b2c5b80c7f5eaeb21ac","observation_id":"9e6cca32-97f6-437e-8add-5ff566be37ac","resolution":{"observed_at":"2026-08-07T10:50:50.983856Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2006.04768","last_updated":"2020-06-14T08:15:54Z","snapshot_observed_at":"2026-07-06T09:27:03.809621Z","submitted_at":"2020-06-08T17:37:52Z","title":"Linformer: Self-Attention with Linear Complexity","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2006.04768","snapshot_observed_at":"2026-08-07T10:50:50.989466Z","title":"Li, Madian Khabsa, Han Fang, and Hao Ma","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.989466Z"},"links":{"cited_paper":"/paper/2006.04768","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:27c0fe41093d0c67f34873c4381c2711b7d71e8ea64587ec014780cbfe1dfec9","observation_id":"9f93a1f9-d31e-4f71-bd1d-9bb03d683953","resolution":{"observed_at":"2026-08-07T10:50:50.989466Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.01889","last_updated":"2023-11-27T06:38:47Z","snapshot_observed_at":"2026-08-07T09:22:20.831075Z","submitted_at":"2023-10-03T08:44:50Z","title":"Ring Attention with Blockwise Transformers for Near-Infinite Context","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.01889","snapshot_observed_at":"2026-08-07T10:50:50.996932Z","title":"Ring attention with blockwise transformers for near-infinite context, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:50.996932Z"},"links":{"cited_paper":"/paper/2310.01889","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:55956fad3f0e98d9bf396d4bc50c11c804af6ce7e05e91733a1529aa4e76347d","observation_id":"ccef10ec-d139-45f0-a606-c12549b212c5","resolution":{"observed_at":"2026-08-07T10:50:50.996932Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.17453","last_updated":"2024-04-07T00:56:53Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-09-29T17:59:56Z","title":"Efficient Streaming Language Models with Attention Sinks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.17453","snapshot_observed_at":"2026-08-07T10:50:51.002644Z","title":"Efficient streaming language models with attention sinks, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.002644Z"},"links":{"cited_paper":"/paper/2309.17453","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:bc55dfa411edb126f47e14fe459e8881e458395242c0ccf6b343228649561a9f","observation_id":"60657e88-35fb-4aaf-9f6d-3a1bd6e1f174","resolution":{"observed_at":"2026-08-07T10:50:51.002644Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.12094","last_updated":"2025-06-02T11:46:43Z","snapshot_observed_at":"2026-08-02T16:34:35.677937Z","submitted_at":"2024-12-16T18:58:57Z","title":"SepLLM: Accelerate Large Language Models by Compressing One Segment into One Separator","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.12094","snapshot_observed_at":"2026-08-07T10:50:51.014693Z","title":"SepLLM : Accelerate Large Language Models by Compressing One Segment into One Separator , December 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.014693Z"},"links":{"cited_paper":"/paper/2412.12094","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:63d6b7ff0e1c28b7f8c817e6e4978834122394d8e6ab555b54c49284a101bd6e","observation_id":"a5f70ddc-f502-4087-85e2-06912880a329","resolution":{"observed_at":"2026-08-07T10:50:51.014693Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14788","last_updated":"2023-11-04T04:09:43Z","snapshot_observed_at":"2026-08-02T20:54:41.815973Z","submitted_at":"2023-05-24T06:42:44Z","title":"Adapting Language Models to Compress Contexts","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14788","snapshot_observed_at":"2026-08-07T10:50:51.020934Z","title":"Adapting Language Models to Compress Contexts , November 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.020934Z"},"links":{"cited_paper":"/paper/2305.14788","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:6ed30d2b13e7de1a466f12e36385c8894daa08885a0ba046f4e0f451b49b1c4e","observation_id":"35fc2f72-3aad-4cad-8785-1757348e5969","resolution":{"observed_at":"2026-08-07T10:50:51.020934Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.17483","last_updated":"2024-12-23T11:24:04Z","snapshot_observed_at":"2026-07-06T20:12:04.557004Z","submitted_at":"2024-12-23T11:24:04Z","title":"A Silver Bullet or a Compromise for Full Attention? A Comprehensive Study of Gist Token-based Context Compression","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.17483","snapshot_observed_at":"2026-08-07T10:50:51.027924Z","title":"A Silver Bullet or a Compromise for Full Attention ? A Comprehensive Study of Gist Token -based Context Compression , December 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.027924Z"},"links":{"cited_paper":"/paper/2412.17483","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:1b2626b76e61c00a952c0563c5bd4cd13466c7168be03fcf07213d85603753bf","observation_id":"35aed587-e364-4f0c-984e-314615014de2","resolution":{"observed_at":"2026-08-07T10:50:51.027924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.06945","last_updated":"2024-05-08T18:16:09Z","snapshot_observed_at":"2026-08-02T18:04:23.903413Z","submitted_at":"2023-07-13T17:59:21Z","title":"In-context Autoencoder for Context Compression in a Large Language Model","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.06945","snapshot_observed_at":"2026-08-07T10:50:51.035722Z","title":"In-context autoencoder for context compression in a large language model","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.035722Z"},"links":{"cited_paper":"/paper/2307.06945","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:3567f848379cc4728904317e2158973de9875d0705a996d192766dd6248595fd","observation_id":"39adb28a-0505-4479-885e-bb0e6b76633d","resolution":{"observed_at":"2026-08-07T10:50:51.035722Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.08763","last_updated":"2024-09-04T16:13:18Z","snapshot_observed_at":"2026-07-06T17:44:09.081164Z","submitted_at":"2024-03-13T17:58:57Z","title":"Simple and Scalable Strategies to Continually Pre-train Large Language Models","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.08763","snapshot_observed_at":"2026-08-07T10:50:51.041868Z","title":"Richter, Quentin Anthony, Timothée Lesort, Eugene Belilovsky, and Irina Rish","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.041868Z"},"links":{"cited_paper":"/paper/2403.08763","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:ea83bb5d31437b28f89a237c25543d5885eff86b55469912d06d6687748ccaa7","observation_id":"2a349dfa-8ce7-4ec9-9dcc-80c8a642da10","resolution":{"observed_at":"2026-08-07T10:50:51.041868Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2004.04906","last_updated":"2020-09-30T21:27:13Z","snapshot_observed_at":"2026-07-06T09:11:26.109763Z","submitted_at":"2020-04-10T04:53:17Z","title":"Dense Passage Retrieval for Open-Domain Question Answering","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2004.04906","snapshot_observed_at":"2026-08-07T10:50:51.049808Z","title":"Dense Passage Retrieval for Open - Domain Question Answering , September 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.049808Z"},"links":{"cited_paper":"/paper/2004.04906","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:951863be7a57c0fc58a55afdc486b099a15714384b10af5b246b63b511216996","observation_id":"a4065ce3-fe3c-4bac-b82d-d8b8dcc93864","resolution":{"observed_at":"2026-08-07T10:50:51.049808Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2103.00020","last_updated":"2021-02-26T19:04:58Z","snapshot_observed_at":"2026-07-06T10:45:03.059688Z","submitted_at":"2021-02-26T19:04:58Z","title":"Learning Transferable Visual Models From Natural Language Supervision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2103.00020","snapshot_observed_at":"2026-08-07T10:50:51.057601Z","title":"Learning Transferable Visual Models From Natural Language Supervision , February 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.057601Z"},"links":{"cited_paper":"/paper/2103.00020","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:ef17248f0be8858dd92f1d53a05017dca4ebbc007d7c9d0f7a0b836a666c0848","observation_id":"1b73f1a8-f33d-4d48-b8e1-7e3cd0727a6a","resolution":{"observed_at":"2026-08-07T10:50:51.057601Z","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":"2026-08-07T10:50:51.536585Z","title":"Aligning ai with shared human values","venue":null,"work_id":"579c117a-c5f5-4156-9fc8-128e588be975","year":2021},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.065352Z"},"links":{"citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:ef2ea0ce5de10322eb22a51b1720b25e4964700652fd28ec41d9775a37974947","observation_id":"1cc475ff-34c6-427c-bfe6-37fa697217e8","resolution":{"observed_at":"2026-08-07T10:50:51.542254Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:50:51.515479Z","title":"Measuring massive multitask language understanding","venue":null,"work_id":"65757e99-08d5-4e6b-91b9-4368f7615492","year":2021},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.070727Z"},"links":{"citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:0a21dc1ddd215280f9051a6cb2839ed51a42ffc72835f6e63c1a1f6ff96bb83e","observation_id":"f000a97b-4201-4e5f-930a-c52f567bd2a3","resolution":{"observed_at":"2026-08-07T10:50:51.524730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"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":"2406.14833","last_updated":"2024-06-27T08:11:01Z","snapshot_observed_at":"2026-08-06T04:10:07.196405Z","submitted_at":"2024-06-21T02:28:37Z","title":"Efficient Continual Pre-training by Mitigating the Stability Gap","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.14833","snapshot_observed_at":"2026-08-07T10:50:51.076830Z","title":"Efficient continual pre-training by mitigating the stability gap, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-07T10:50:51.076830Z"},"links":{"cited_paper":"/paper/2406.14833","citing_paper":"/paper/2506.04344"},"observation_digest":"sha256:5b5177ec6f3a40f965d495da67011243cf16c47fdac5f128592f70ef9d23824f","observation_id":"340dc06a-e7c4-4e88-9387-69b785d2b744","resolution":{"observed_at":"2026-08-07T10:50:51.076830Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.04344","last_updated":"2025-06-04T18:02:07Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-08T14:08:49.352570Z","submitted_at":"2025-06-04T18:02:07Z","title":"GEM: Empowering LLM for both Embedding Generation and Language Understanding"},"reference_resolution":{"displayed":34,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":31,"verified_exact":0,"verified_fuzzy":3},"total_outbound_references":34},"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 34 of 34 outbound references and 2 inbound Pith citation observations for arXiv:2506.04344."}