{"as_of":"2026-08-09T15:09:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:ff73ddde52cdbc94bf2564f1ebfad956ac549955555c6d84c68e65ea792aa5ba","coverage":[{"denominator":52,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":52,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T08:28:53.958603Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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":"2026-06-27T16:36:54.699174Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-07-03T01:17:31.581995Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"cited_work":{"arxiv_id":"2510.20535","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2510.20535","snapshot_observed_at":"2026-07-30T02:04:24.799755Z","title":"Arc-encoder: learning compressed text representations for large language models","venue":null,"work_id":"e88bdf98-92c9-48e8-bc5a-dab4e83ed16d","year":2025},"citing_paper":{"arxiv_id":"2604.26483","last_updated":"2026-04-29T09:48:44Z","snapshot_observed_at":"2026-08-02T12:48:50.463577Z","submitted_at":"2026-04-29T09:48:44Z","title":"Efficient Listwise Reranking with Compressed Document Representations","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-05-07T10:44:37.955281Z"},"links":{"cited_paper":"/paper/2510.20535","citing_paper":"/paper/2604.26483"},"observation_digest":"sha256:fe311f005edac7ff9b8cd80e7db98d254b578d05be692077439917b96cd04301","observation_id":"24e5a228-b79f-40c8-8e5c-7594cab32019","resolution":{"observed_at":"2026-07-30T02:04:24.799755Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"cited_work":{"arxiv_id":"2510.20535","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2510.20535","snapshot_observed_at":"2026-07-30T02:04:24.799755Z","title":"Arc-encoder: learning compressed text representations for large language models","venue":null,"work_id":"e88bdf98-92c9-48e8-bc5a-dab4e83ed16d","year":2025},"citing_paper":{"arxiv_id":"2606.09659","last_updated":"2026-06-08T15:43:16Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2026-06-08T15:43:16Z","title":"End-to-End Context Compression at Scale","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-06-27T16:36:54.699174Z"},"links":{"cited_paper":"/paper/2510.20535","citing_paper":"/paper/2606.09659"},"observation_digest":"sha256:ae3976418e50e8364ab486f98918eb6ddede73de0c12ffd1c123b5c95c1280aa","observation_id":"3ce40eee-963f-45d8-a810-3d48fcd74522","resolution":{"observed_at":"2026-07-30T02:04:24.799755Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2510.20535/citation-record","integrity":"/paper/2510.20535/integrity","json":"/paper/2510.20535/citation-record.json","paper":"/paper/2510.20535"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T08:28:47.193225Z","title":"Beat the ai: Investigating adversarial human annotation for reading comprehension","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:47.193225Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:181b90ef2f3d09759f99e60561f5f6fce1a21b3daf926329c52e5cdf75321ae6","observation_id":"77afc9d7-327d-46af-8153-0ac2552393b7","resolution":{"observed_at":"2026-08-04T08:28:47.193225Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-04T08:28:47.326603Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:47.326603Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:031f65ad6dff3fbbb157415a44ab1c5f956b2778cc409094ea7b663b82475237","observation_id":"9af977eb-6ea8-4957-a1df-7f4942c3cbd6","resolution":{"observed_at":"2026-08-04T08:28:47.326603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.15595","last_updated":"2023-06-28T04:26:05Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-06-27T16:26:26Z","title":"Extending Context Window of Large Language Models via Positional Interpolation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.15595","snapshot_observed_at":"2026-08-04T08:28:47.439715Z","title":"Extending context window of large language models via positional interpolation, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:47.439715Z"},"links":{"cited_paper":"/paper/2306.15595","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:a38988280af572f1624ef540fdd5d85f946fade080f2c9772ae3425503b0695c","observation_id":"2b814d7e-ba47-4d6f-affe-1d049a9f8e45","resolution":{"observed_at":"2026-08-04T08:28:47.439715Z","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":"2026-08-04T08:28:47.592901Z","title":"D ialog S um: A real-life scenario dialogue summarization dataset","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:47.592901Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:993f297f8567cd6e645e335402f100701ba354c4e9bdee1629ec00013362cb83","observation_id":"469d3baa-d8d4-427e-9626-2067404ba2cc","resolution":{"observed_at":"2026-08-04T08:28:47.592901Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.13792","last_updated":"2024-12-09T06:07:03Z","snapshot_observed_at":"2026-08-03T20:12:47.789392Z","submitted_at":"2024-05-22T16:15:17Z","title":"xRAG: Extreme Context Compression for Retrieval-augmented Generation with One Token","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2405.13792","snapshot_observed_at":"2026-08-04T08:28:47.733664Z","title":"xrag: Extreme context compression for retrieval-augmented generation with one token, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:47.733664Z"},"links":{"cited_paper":"/paper/2405.13792","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:19159b8fe500a9dea2f2b54f24c9b6f262b5fa635f508b3a4bf6430b2b2d9035","observation_id":"d64f800f-9fe5-4404-a8a6-585e87bd8265","resolution":{"observed_at":"2026-08-04T08:28:47.733664Z","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":"2026-08-04T08:28:47.850975Z","title":"W iki S um: Coherent summarization dataset for efficient human-evaluation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:47.850975Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:38654950168854c4abbf5dd9842a379ebf62cbc3e182243b70b2ab172a6e7572","observation_id":"05398555-4748-4828-8364-6fd1694f011c","resolution":{"observed_at":"2026-08-04T08:28:47.850975Z","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":"10.18653/v1/2021.eacl-main.33","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"P ara SCI : A large scientific paraphrase dataset for longer paraphrase generation","venue":null,"work_id":"d663fcc2-c12c-4744-9772-193f0fc207c9","year":2021},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:48.012158Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:3d81ae26154ebe8c7d8f0af0afaf5bbbcb9681afe4a62bb6dc1ae6d788a4ee39","observation_id":"ac79817e-1ccf-4cce-a649-cf79bbde74d0","resolution":{"observed_at":"2026-08-04T08:33:29.961291Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1903.00161","last_updated":"2019-04-16T21:22:39Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2019-03-01T05:32:01Z","title":"DROP: A Reading Comprehension Benchmark Requiring Discrete Reasoning Over Paragraphs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1903.00161","snapshot_observed_at":"2026-08-04T08:28:48.179058Z","title":"Drop: A reading comprehension benchmark requiring discrete reasoning over paragraphs, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:48.179058Z"},"links":{"cited_paper":"/paper/1903.00161","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:033814ee6a6ab271867f1502f21333f5edd8f15e4b2506e481a5e99ce9005fea","observation_id":"a2ed31a2-0c8c-4c52-ac70-e8015cca1e74","resolution":{"observed_at":"2026-08-04T08:28:48.179058Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.06266","last_updated":"2025-06-13T17:58:55Z","snapshot_observed_at":"2026-08-07T05:54:59.580995Z","submitted_at":"2025-06-06T17:48:23Z","title":"Cartridges: Lightweight and general-purpose long context representations via self-study","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.06266","snapshot_observed_at":"2026-08-04T08:28:48.311843Z","title":"Cartridges: Lightweight and general-purpose long context representations via self-study, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:48.311843Z"},"links":{"cited_paper":"/paper/2506.06266","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:6553c161b70c0ed31fc76cc11bdec443010dbba9781f1743111e6e7895c32a8f","observation_id":"67ca3628-e56b-434a-ab5b-079d6a26a120","resolution":{"observed_at":"2026-08-04T08:28:48.311843Z","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":"2026-08-04T08:28:48.415613Z","title":"In-context autoencoder for context compression in a large language model, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:48.415613Z"},"links":{"cited_paper":"/paper/2307.06945","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:f8aa30f210492e2fe2c0d4f28f2c3e2bda42c83bb2eb6369c6bbf7ba91b881da","observation_id":"47ab78b7-f250-43db-8f87-25e040e2277b","resolution":{"observed_at":"2026-08-04T08:28:48.415613Z","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":"2026-08-04T08:28:48.527275Z","title":"SAMS um corpus: A human-annotated dialogue dataset for abstractive summarization","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:48.527275Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:fc6a949a7fc60254e306da9f3bdb7359fcaa65aca5cf2213b98c6837e055aa82","observation_id":"480576b9-0f08-4d63-8e47-ccab5bab20f0","resolution":{"observed_at":"2026-08-04T08:28:48.527275Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03193","last_updated":"2021-06-06T17:58:12Z","snapshot_observed_at":"2026-08-01T11:21:28.445632Z","submitted_at":"2021-06-06T17:58:12Z","title":"The FLORES-101 Evaluation Benchmark for Low-Resource and Multilingual Machine Translation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03193","snapshot_observed_at":"2026-08-04T08:28:48.642822Z","title":"The flores-101 evaluation benchmark for low-resource and multilingual machine translation, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:48.642822Z"},"links":{"cited_paper":"/paper/2106.03193","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:2e77e7fffb8352cd5898ce8bc4ee7f39823d5c708ccd69c91e04553dfb8cdee3","observation_id":"a273f037-b6cc-42d9-aff2-7ef0d5a82a20","resolution":{"observed_at":"2026-08-04T08:28:48.642822Z","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":"2026-08-04T08:28:48.745468Z","title":"The llama 3 herd of models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:48.745468Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:d842e752268d9450fe3d8ced0a0f3ad7ebfa32b339eb40abaa74cc49707d8630","observation_id":"585ead68-8566-4cd0-a220-6c88a63c35c0","resolution":{"observed_at":"2026-08-04T08:28:48.745468Z","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":"2026-08-04T08:28:48.880119Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:48.880119Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:141fa49d64bfee7f3e5164c19b83354720356565c79960829d95c2690d6395d7","observation_id":"e7d878b9-bccc-40a3-a65e-99dffa820486","resolution":{"observed_at":"2026-08-04T08:28:48.880119Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.07922","last_updated":"2024-08-19T05:46:56Z","snapshot_observed_at":"2026-07-06T16:06:30.884141Z","submitted_at":"2023-08-15T17:59:18Z","title":"RAVEN: In-Context Learning with Retrieval-Augmented Encoder-Decoder Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.07922","snapshot_observed_at":"2026-08-04T08:28:49.019731Z","title":"Raven: In-context learning with retrieval-augmented encoder-decoder language models, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:49.019731Z"},"links":{"cited_paper":"/paper/2308.07922","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:6ca7a0269d6a5623b814b768bb04752e93906930262d9ddaa0aea687b449565c","observation_id":"812d1cc3-8384-4280-a6b5-40eb112de0b3","resolution":{"observed_at":"2026-08-04T08:28:49.019731Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.03299","last_updated":"2022-11-16T16:38:18Z","snapshot_observed_at":"2026-08-05T00:57:17.859949Z","submitted_at":"2022-08-05T17:39:22Z","title":"Atlas: Few-shot Learning with Retrieval Augmented Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2208.03299","snapshot_observed_at":"2026-08-04T08:28:49.124274Z","title":"Atlas: Few-shot learning with retrieval augmented language models, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:49.124274Z"},"links":{"cited_paper":"/paper/2208.03299","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:ee2d82111b7c0b5ca3d514d8b82737f981baf97209eaa316341d19a96d84ebd7","observation_id":"4514d89f-5b4a-472b-aa8a-5a2651099980","resolution":{"observed_at":"2026-08-04T08:28:49.124274Z","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":"2026-08-04T08:28:49.240662Z","title":"Product Quantization for Nearest Neighbor Search","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:49.240662Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:da15d668b07f9b3e6a8ed59a08775ee7dbe207d304e78ea6f1c4f14c5edd1165","observation_id":"2fff8202-5c09-48be-8c33-758c80ae54ca","resolution":{"observed_at":"2026-08-04T08:28:49.240662Z","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":"2026-08-04T08:28:49.411439Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:49.411439Z"},"links":{"cited_paper":"/paper/2310.06825","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:cc82d7493e1d98ef4e53e62ac8731d1a168d1c05377949c148f3a8329af61c56","observation_id":"fea60645-34e3-4280-aee2-d58eec7f5e39","resolution":{"observed_at":"2026-08-04T08:28:49.411439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05736","last_updated":"2023-12-06T17:02:25Z","snapshot_observed_at":"2026-08-06T08:38:21.368130Z","submitted_at":"2023-10-09T14:10:21Z","title":"LLMLingua: Compressing Prompts for Accelerated Inference of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05736","snapshot_observed_at":"2026-08-04T08:28:49.536406Z","title":"Llmlingua: Compressing prompts for accelerated inference of large language models, 2023 b","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:49.536406Z"},"links":{"cited_paper":"/paper/2310.05736","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:28ad70ae6c8d7b8ad7caa8936a9a1d1042630f5e529b91ac828df4a219102c7b","observation_id":"9fd21ffa-571e-4863-abbb-a76960a04134","resolution":{"observed_at":"2026-08-04T08:28:49.536406Z","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":"2026-08-04T08:28:49.668756Z","title":"F reebase QA : A new factoid QA data set matching trivia-style question-answer pairs with F reebase","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:49.668756Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:f39bb640bef198b295cf3924e74888e159a34d54d0a4ffc42499f9ef53cec844","observation_id":"0e984759-51b5-4418-a3da-3c0416c535c5","resolution":{"observed_at":"2026-08-04T08:28:49.668756Z","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":"2026-08-04T08:28:49.806892Z","title":null,"venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:49.806892Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:26fa19a847838cad8cebb8b9f76777b75194b2b98e0f47c507a619c55b010579","observation_id":"93a82ff8-22ee-4d9b-98a3-9d04acb3af22","resolution":{"observed_at":"2026-08-04T08:28:49.806892Z","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":"2026-08-04T08:28:50.003727Z","title":"T rivia QA : A large scale distantly supervised challenge dataset for reading comprehension","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:50.003727Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:b5462ef028d95b3e576ec8057e3b9effc81bd2a1e7b2bf1b0a9bee5d18d9bcbf","observation_id":"78a3125f-1577-4957-9af3-0f6e5ea0db1c","resolution":{"observed_at":"2026-08-04T08:28:50.003727Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.13063","last_updated":"2025-06-22T15:07:37Z","snapshot_observed_at":"2026-08-07T18:07:45.625452Z","submitted_at":"2025-02-18T17:08:45Z","title":"Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.13063","snapshot_observed_at":"2026-08-04T08:28:50.138327Z","title":"Cramming 1568 tokens into a single vector and back again: Exploring the limits of embedding space capacity, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:50.138327Z"},"links":{"cited_paper":"/paper/2502.13063","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:a977973b636cdaf66c051a6fb96056f9126ed7e02986358593b8e11998607747","observation_id":"47f6454c-b8a3-4a83-85b0-e449cf2e31ca","resolution":{"observed_at":"2026-08-04T08:28:50.138327Z","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":"2026-08-04T08:28:50.308857Z","title":"Toutanova, Llion Jones, Ming-Wei Chang, Andrew Dai, Jakob Uszkoreit, Quoc Le, and Slav Petrov","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:50.308857Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:d92397272fcd4bf919016c266db7e84b2cbe3530023a8cdb4dacbecf41a09343","observation_id":"63c3ba3d-e916-4fb3-b0fe-be1d5e4e6823","resolution":{"observed_at":"2026-08-04T08:28:50.308857Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17428","last_updated":"2025-02-25T00:35:18Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","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":"2026-08-04T08:28:50.468192Z","title":"Nv-embed: Improved techniques for training llms as generalist embedding models, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:50.468192Z"},"links":{"cited_paper":"/paper/2405.17428","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:c2b06584283ea12484b71b0cbf63dd52f311c843efc739a8125bb95b9d531caf","observation_id":"3fbca933-978e-4541-a384-7c4c7eacbb72","resolution":{"observed_at":"2026-08-04T08:28:50.468192Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-04T08:28:50.606035Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:50.606035Z"},"links":{"cited_paper":"/paper/2005.11401","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:3b9721c59e56f198f2faea4b3078def7059c59cb4c8ea79290055888faaa7ea1","observation_id":"282f5508-4dd0-4e46-8c34-5b6848b9109f","resolution":{"observed_at":"2026-08-04T08:28:50.606035Z","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":"2026-08-04T08:28:50.721418Z","title":"Shifting ai efficiency from model-centric to data-centric compression, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:50.721418Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:e004d3ac671f1d1bc3b0f1b3b8d4fd3788fbae57bc39248c6a2b4b8d66ffab9f","observation_id":"75e6aed7-41dd-4c9d-aa77-3f89fe383757","resolution":{"observed_at":"2026-08-04T08:28:50.721418Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1711.05101","last_updated":"2019-01-04T21:01:49Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2017-11-14T14:24:06Z","title":"Decoupled Weight Decay Regularization","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1711.05101","snapshot_observed_at":"2026-08-04T08:28:50.825031Z","title":"Decoupled weight decay regularization, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:50.825031Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:fa54c20d13bd42ae0fba66f921b2d6877544619015b153b80a56583362f8a95e","observation_id":"81a86141-a389-4d1c-8270-50e89069b665","resolution":{"observed_at":"2026-08-04T08:28:50.825031Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2501.16075","last_updated":"2025-01-27T14:26:27Z","snapshot_observed_at":"2026-07-06T20:26:46.276053Z","submitted_at":"2025-01-27T14:26:27Z","title":"PISCO: Pretty Simple Compression for Retrieval-Augmented Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2501.16075","snapshot_observed_at":"2026-08-04T08:28:50.987062Z","title":"Pisco: Pretty simple compression for retrieval-augmented generation, 2025 a","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:50.987062Z"},"links":{"cited_paper":"/paper/2501.16075","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:6dee1d89250292e748a9b2190d967438e4aa5cf4e7f32ccf6d1d3c77f5f690e1","observation_id":"37043d6e-f6d1-40a7-a6bc-c05d4d732e8d","resolution":{"observed_at":"2026-08-04T08:28:50.987062Z","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":"2026-08-04T08:28:51.072557Z","title":"Oscar: Online soft compression and reranking, 2025 b","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:51.072557Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:69ca5801ebc993b5278962871398b9c66e68307fbf4d68300e48eed4ecef10f8","observation_id":"ab620ee9-c45c-42f5-8b55-0a48a001287a","resolution":{"observed_at":"2026-08-04T08:28:51.072557Z","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":"2026-08-04T08:28:51.206578Z","title":"Learning to compress prompts with gist tokens, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:51.206578Z"},"links":{"cited_paper":"/paper/2304.08467","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:ed593788a3f745cafccbb1afef024dca808a7159673e2f4ee41bd7ddd0c4be34","observation_id":"815c4e34-fc9e-4245-a950-d35d87cedc9e","resolution":{"observed_at":"2026-08-04T08:28:51.206578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.09268","last_updated":"2018-10-31T14:46:47Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2016-11-28T18:14:11Z","title":"MS MARCO: A Human Generated MAchine Reading COmprehension Dataset","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1611.09268","snapshot_observed_at":"2026-08-04T08:28:51.328933Z","title":"MS MARCO: A human generated machine reading comprehension dataset","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:51.328933Z"},"links":{"cited_paper":"/paper/1611.09268","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:d7ff62fd404951d43865095557a7aafb81ca7ec8f743f55ca6450da94d0b97b8","observation_id":"e80f9306-3e5a-4923-b92c-127a2c897a57","resolution":{"observed_at":"2026-08-04T08:28:51.328933Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.12968","last_updated":"2024-08-12T04:48:11Z","snapshot_observed_at":"2026-08-08T18:14:49.192773Z","submitted_at":"2024-03-19T17:59:56Z","title":"LLMLingua-2: Data Distillation for Efficient and Faithful Task-Agnostic Prompt Compression","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.12968","snapshot_observed_at":"2026-08-04T08:28:51.479132Z","title":"Vicky Zhao, Lili Qiu, and Dongmei Zhang","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:51.479132Z"},"links":{"cited_paper":"/paper/2403.12968","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:533a948b5a04cc3f97f5c56940343bd740fc150df19ae8f60237a850c2128c52","observation_id":"d6b81bd0-a923-4fa5-9354-92f5e1a34ea4","resolution":{"observed_at":"2026-08-04T08:28:51.479132Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.02252","last_updated":"2021-05-27T15:20:59Z","snapshot_observed_at":"2026-08-07T22:58:49.396675Z","submitted_at":"2020-09-04T15:32:19Z","title":"KILT: a Benchmark for Knowledge Intensive Language Tasks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.02252","snapshot_observed_at":"2026-08-04T08:28:51.584949Z","title":"Kilt: a benchmark for knowledge intensive language tasks, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:51.584949Z"},"links":{"cited_paper":"/paper/2009.02252","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:a12daaeafdfc7673f8fa89b44d14661ea448ba0f32561a018ed44077592a3da9","observation_id":"5105116b-8f9a-40e4-b370-78d7fa947479","resolution":{"observed_at":"2026-08-04T08:28:51.584949Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1911.05507","last_updated":"2019-11-13T14:36:01Z","snapshot_observed_at":"2026-08-09T11:59:51.650526Z","submitted_at":"2019-11-13T14:36:01Z","title":"Compressive Transformers for Long-Range Sequence Modelling","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1911.05507","snapshot_observed_at":"2026-08-04T08:28:51.749218Z","title":"Compressive transformers for long-range sequence modelling","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:51.749218Z"},"links":{"cited_paper":"/paper/1911.05507","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:396f23c5094ad02f91baae5c2ec9ac0d2f118c9f742549869607b1fc04549813","observation_id":"a47257d8-5a90-4870-aead-a7dd9d5bb1fd","resolution":{"observed_at":"2026-08-04T08:28:51.749218Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1606.05250","last_updated":"2016-10-11T02:42:36Z","snapshot_observed_at":"2026-08-08T11:05:45.903773Z","submitted_at":"2016-06-16T16:36:00Z","title":"SQuAD: 100,000+ Questions for Machine Comprehension of Text","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1606.05250","snapshot_observed_at":"2026-08-04T08:28:51.911951Z","title":"Squad: 100,000+ questions for machine comprehension of text, 2016","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:51.911951Z"},"links":{"cited_paper":"/paper/1606.05250","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:be2711eb2dfcbf9318e4c6be698ee12df38caf3633ab236aa73ab1cd3df4cb85","observation_id":"12ea5903-b5a8-46f7-af95-f04daa3be81c","resolution":{"observed_at":"2026-08-04T08:28:51.911951Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2305.14196","last_updated":"2023-12-17T17:05:09Z","snapshot_observed_at":"2026-08-03T17:17:47.899275Z","submitted_at":"2023-05-23T16:15:31Z","title":"ZeroSCROLLS: A Zero-Shot Benchmark for Long Text Understanding","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2305.14196","snapshot_observed_at":"2026-08-04T08:28:52.073439Z","title":"Zeroscrolls: A zero-shot benchmark for long text understanding, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:52.073439Z"},"links":{"cited_paper":"/paper/2305.14196","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:163fa1e7dd933ba8bded8671873252afd48256559b8bfae478498b3cac7ebcca","observation_id":"c392bb0b-749e-42f0-9d93-74d738c55ac2","resolution":{"observed_at":"2026-08-04T08:28:52.073439Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2204.06092","last_updated":"2023-01-22T14:25:40Z","snapshot_observed_at":"2026-07-06T12:59:46.149474Z","submitted_at":"2022-04-12T21:58:44Z","title":"ASQA: Factoid Questions Meet Long-Form Answers","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2204.06092","snapshot_observed_at":"2026-08-04T08:28:52.215969Z","title":"Asqa: Factoid questions meet long-form answers, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:52.215969Z"},"links":{"cited_paper":"/paper/2204.06092","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:8da5ff573a842ba40231822c320b16c5271493b6b1d8ac2481637a0f0f624a2e","observation_id":"626d3f5b-3edf-4104-a651-2aa5bd4bef49","resolution":{"observed_at":"2026-08-04T08:28:52.215969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.02656","last_updated":"2025-03-04T14:17:00Z","snapshot_observed_at":"2026-08-09T02:11:02.203384Z","submitted_at":"2025-03-04T14:17:00Z","title":"Adapting Decoder-Based Language Models for Diverse Encoder Downstream Tasks","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.02656","snapshot_observed_at":"2026-08-04T08:28:52.292856Z","title":"Adapting decoder-based language models for diverse encoder downstream tasks, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:52.292856Z"},"links":{"cited_paper":"/paper/2503.02656","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:a7d579036a276714cd01f7043ae8fdfce3cfa0c7354fa653e1ee279ea358e4d2","observation_id":"d0e00654-8943-4713-b191-4b2155dbc290","resolution":{"observed_at":"2026-08-04T08:28:52.292856Z","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":"2026-08-04T08:28:52.371154Z","title":"Gmsa: Enhancing context compression via group merging and layer semantic alignment, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:52.371154Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:724cd254b47b5eb3e93c3cdc4100088f2eb8dda30088caf8740016ff80b258c3","observation_id":"f2ec37d3-6603-4905-ac57-39e11fe0d8f8","resolution":{"observed_at":"2026-08-04T08:28:52.371154Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2009.06732","last_updated":"2022-03-14T10:35:35Z","snapshot_observed_at":"2026-08-05T21:57:04.021766Z","submitted_at":"2020-09-14T20:38:14Z","title":"Efficient Transformers: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2009.06732","snapshot_observed_at":"2026-08-04T08:28:52.455570Z","title":"Efficient transformers: A survey, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:52.455570Z"},"links":{"cited_paper":"/paper/2009.06732","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:4b5e9af7601c36d5a7acec218535f6c2ad1edf676bc4003cfd0e470b0f45643c","observation_id":"65c88820-912f-4ddd-9b9e-4559d0d1bf43","resolution":{"observed_at":"2026-08-04T08:28:52.455570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.19786","last_updated":"2025-03-25T15:52:34Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2025-03-25T15:52:34Z","title":"Gemma 3 Technical Report","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2503.19786","snapshot_observed_at":"2026-08-04T08:28:52.614851Z","title":"Gemma 3 technical report, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:52.614851Z"},"links":{"cited_paper":"/paper/2503.19786","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:468c544c49203e384a0de034e17eca7cf5064bad87d6c9f1798c8f56a40735e4","observation_id":"cc122789-2c81-4677-9937-6b65b5ae0616","resolution":{"observed_at":"2026-08-04T08:28:52.614851Z","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":"2026-08-04T08:28:52.775526Z","title":"Llama‑2‑7B‑32K‑Instruct — and fine‑tuning for Llama‑2 models with Together API","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:52.775526Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:fdf690d079c8675e0e4f9eb273f5fc645178791f678439c9e950933342468b95","observation_id":"f3bfec3d-c494-4413-bfc3-f4ce17ff5dfa","resolution":{"observed_at":"2026-08-04T08:28:52.775526Z","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":"2026-08-04T08:28:52.903835Z","title":"Llama 2: Open foundation and fine-tuned chat models, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:52.903835Z"},"links":{"cited_paper":"/paper/2307.09288","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:3c1935e472a0dcfa727b5162c1e72ca1011c2c9598bad8f3e1db450342f3028f","observation_id":"e5ad97da-d50a-453a-89d1-dac6a2566838","resolution":{"observed_at":"2026-08-04T08:28:52.903835Z","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":"2026-08-04T08:28:53.069755Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:53.069755Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:3430ebdbf609bd449aadf61eada7748754a4e7127aceda117c3fa5d517ac0a2a","observation_id":"f9102c28-8507-4826-bf39-f4ac7ac18b18","resolution":{"observed_at":"2026-08-04T08:28:53.069755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1809.09600","last_updated":"2018-09-25T17:28:20Z","snapshot_observed_at":"2026-08-09T10:11:58.541007Z","submitted_at":"2018-09-25T17:28:20Z","title":"HotpotQA: A Dataset for Diverse, Explainable Multi-hop Question Answering","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1809.09600","snapshot_observed_at":"2026-08-04T08:28:53.163411Z","title":"Cohen, Ruslan Salakhutdinov, and Christopher D","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:53.163411Z"},"links":{"cited_paper":"/paper/1809.09600","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:195c59c8cf9e90012494e00ee93f29b201504bfa2862c18fe0fe94368d6e389b","observation_id":"e1557152-3ae7-46f0-850a-4cbbd1f3642e","resolution":{"observed_at":"2026-08-04T08:28:53.163411Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.16617","last_updated":"2024-06-11T18:54:13Z","snapshot_observed_at":"2026-08-06T05:28:31.850302Z","submitted_at":"2024-02-26T14:47:35Z","title":"Long-Context Language Modeling with Parallel Context Encoding","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.16617","snapshot_observed_at":"2026-08-04T08:28:53.296578Z","title":"Long-context language modeling with parallel context encoding, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:53.296578Z"},"links":{"cited_paper":"/paper/2402.16617","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:e9d1c74ba4a76b2658de2238dfbff875228d37400dee77fd9019fa83bea55ce7","observation_id":"da34a77e-bc4a-4689-a26b-e27d97d63bf8","resolution":{"observed_at":"2026-08-04T08:28:53.296578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.06225","last_updated":"2025-04-08T17:13:41Z","snapshot_observed_at":"2026-08-07T16:07:26.344981Z","submitted_at":"2025-04-08T17:13:41Z","title":"Encoder-Decoder Gemma: Improving the Quality-Efficiency Trade-Off via Adaptation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.06225","snapshot_observed_at":"2026-08-04T08:28:53.456115Z","title":"Encoder-decoder gemma: Improving the quality-efficiency trade-off via adaptation, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:53.456115Z"},"links":{"cited_paper":"/paper/2504.06225","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:3252a51b4254eabe38421a7f8505451f48ee5e86dbcae69b4f8736be34c77f7b","observation_id":"7974651e-7f1f-4afa-a85c-dd1f6d2f6c15","resolution":{"observed_at":"2026-08-04T08:28:53.456115Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2301.13848","last_updated":"2023-01-31T18:46:19Z","snapshot_observed_at":"2026-08-05T10:16:18.497606Z","submitted_at":"2023-01-31T18:46:19Z","title":"Benchmarking Large Language Models for News Summarization","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2301.13848","snapshot_observed_at":"2026-08-04T08:28:53.553412Z","title":"Hashimoto","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:53.553412Z"},"links":{"cited_paper":"/paper/2301.13848","citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:040a7cdcb0de79362c5c247563e87a7b34f88f4cfd27e2551fcbefe9bddb4e2f","observation_id":"caf3d5de-563d-4141-97a5-a8b1b6dd7733","resolution":{"observed_at":"2026-08-04T08:28:53.553412Z","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":"2026-08-04T08:28:53.669440Z","title":"@esa (Ref","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:53.669440Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:958713c73ef381f215f35766ef82b3da5707b5ae928c3242db1245cefb0a955f","observation_id":"c6e2a893-b68a-4249-a67a-c511c4e9918c","resolution":{"observed_at":"2026-08-04T08:28:53.669440Z","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":"2026-08-04T08:28:53.849455Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:53.849455Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:4ad1010e2cf14c6d80781f3d7db5347260cd8beb824f184cd313bc6f464b21b6","observation_id":"c9e9f6b1-cda7-4bf7-bfdb-c3392be21b9c","resolution":{"observed_at":"2026-08-04T08:28:53.849455Z","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":"2026-08-04T08:28:53.958603Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-04T08:28:53.958603Z"},"links":{"citing_paper":"/paper/2510.20535"},"observation_digest":"sha256:712c5d495244eceb47ffcdf22c956e7f4ea799c95faf639ba6a77d95730cab72","observation_id":"95593cf6-c6b0-4669-a43f-e59832a1f247","resolution":{"observed_at":"2026-08-04T08:28:53.958603Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2510.20535","last_updated":"2026-07-29T08:07:09Z","latest_version":2,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-08T02:58:34.657399Z","submitted_at":"2025-10-23T13:20:57Z","title":"ARC-Encoder: learning compressed text representations for large language models"},"reference_resolution":{"displayed":52,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":51,"verified_exact":1,"verified_fuzzy":0},"total_outbound_references":52},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 52 of 52 outbound references and 2 inbound Pith citation observations for arXiv:2510.20535."}