{"as_of":"2026-08-23T13:30:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f8ce845d60c3dd4796dd0055936e3abc344b3f491191c118e799814796b19694","coverage":[{"denominator":37,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":37,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T10:32:14.077931Z","state":"measured"},{"denominator":37,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":37,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-23T06:30:58.430688+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.03739/citation-record","integrity":"/paper/2606.03739/integrity","json":"/paper/2606.03739/citation-record.json","paper":"/paper/2606.03739"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T10:32:14.077931Z","title":"Rate distortion theory: A mathematical basis for data compression.Prentice-Hall, 1971","venue":null,"work_id":null,"year":1971},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:dc7b07e7a0784fb7093b3f04fbc714e466a0874537e0a4d776fd1799ba59bc7d","observation_id":"ba90d938-1e8c-4cc0-a62a-1d0e7ff82618","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"What is the state of neural network pruning?Proceedings of Machine Learning and Systems, 2, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:cca2b6740007ac488066838eb0d9fcb61b846740674c3e00fd24ca1048a573c7","observation_id":"6cbcbf6d-0507-488c-b09c-dcbe0b6fefeb","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Weitere studien über das wärmegleichgewicht unter gasmolekülen.Sitzungs- berichte der Kaiserlichen Akademie der Wissenschaften, 66:275–370, 1872","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:9e4746baabba89a95e68f8ae37be803acfec456e2efbbd28b9582949199e32eb","observation_id":"54cea951-b0d9-4676-bd8d-7680af064a75","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2604.00025","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T02:56:28.850293Z","title":"Brevity constraints reverse performance hierarchies in language models","venue":null,"work_id":"6477fd7e-6f62-4ffd-9f70-04d60c5f25d6","year":2026},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:714332651526abe93197c2987898f3be4f2a78950f642408ed61d1c0e8f6ebf3","observation_id":"2ca56a52-2225-4d4d-8389-a073b4eca37d","resolution":{"observed_at":"2026-07-02T02:56:28.852639Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T10:32:14.077931Z","title":"Caveman: Concise output mode for claude code","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:d5f7cb9966d8846ba2d4f96c1bd2eb27a2bb71393c9f88b811e2dce1b249863d","observation_id":"f2ba5f50-219b-461d-9922-b643ba6b4f31","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Natural language autoencoders","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:718c96053bc9a7ebd249e30923150b4f6645c8514880eab539c7ae2e8296b759","observation_id":"15cb51ec-ba29-48f1-854a-f1d79a7774be","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2107.03374","last_updated":"2021-07-14T17:16:02Z","snapshot_observed_at":"2026-08-20T20:50:23.483838Z","submitted_at":"2021-07-07T17:41:24Z","title":"Evaluating Large Language Models Trained on Code","version":2},"cited_work":{"arxiv_id":"2107.03374","doi":"10.48550/arxiv.2107.03374","metadata_source":"pith","pith_arxiv_id":"2107.03374","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Evaluating Large Language Models Trained on Code","venue":"cs.LG","work_id":"042493e9-b26f-4b4e-bbde-382072ca9b08","year":2021},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"cited_paper":"/paper/2107.03374","citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:429c3d559b8daad9a22c05c1c098b5958363b2f9cde5be7c2bc03e7f7c471785","observation_id":"a6fa23ed-85ab-4036-974e-e4dcfc1d3a9b","resolution":{"observed_at":"2026-07-02T02:56:28.860464Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-01T08:08:23.404839+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-01T08:08:23.404839+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T10:32:14.077931Z","title":"Adapting language models to compress contexts.EMNLP, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:d5cb3010288a9c3782fc044b8cfa9b3b6d387a07851fd45357fcc4a665b88dde","observation_id":"ef50f987-8c0b-43c4-9f28-5d9a2e3fef63","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2110.14168","last_updated":"2021-11-18T00:23:45Z","snapshot_observed_at":"2026-08-14T02:43:01.480086Z","submitted_at":"2021-10-27T04:49:45Z","title":"Training Verifiers to Solve Math Word Problems","version":2},"cited_work":{"arxiv_id":"2110.14168","doi":"10.1002/j.1545-","metadata_source":"pith","pith_arxiv_id":"2110.14168","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Training Verifiers to Solve Math Word Problems","venue":"cs.LG","work_id":"acab1aa8-b4d6-40e0-a3ee-25341701dca2","year":2021},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"cited_paper":"/paper/2110.14168","citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:f0dad21ecb7486bcab23a353617286e49c3acf1f79231e99069fbf50811f03ee","observation_id":"10658a7a-a1ba-4338-8ae0-16c8e596cf88","resolution":{"observed_at":"2026-07-02T02:56:28.845055Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T10:32:14.077931Z","title":"Wiley-Interscience, 2nd edition, 2006","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:7a5c9a25123f097a5091b0e0281bdd4c369a80bc7c23464c1ab98e3ceb812288","observation_id":"d4df089e-7989-4750-9811-bec9e9acf6fe","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Llm.int8(): 8-bit matrix multiplication for transformers at scale.Advances in Neural Information Processing Systems, 35, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:d65002017ba69ecd4fa0848023b75b171eff5ea136e78276014b9e3ed2723401","observation_id":"a9425b18-7802-4899-90c8-ba2e6975fdae","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Gptq: Accurate post-training quantization for generative pre-trained transformers.ICLR, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:128f68e69cb168ceefb46b452ed33970cda5c2d7418734591acf773b2b67e1f2","observation_id":"f0f2afd1-fb44-4bbc-b489-9c415bc62091","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Model tells you what to discard: Adaptive kv cache compression for llms.ICLR, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:496247c457b09ac0c07fb56b31be8eb640a23b1c6996fa692b454bf3e1cc2959","observation_id":"6320c858-035a-4b32-93e0-28f5500cbe87","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"In-contextautoencoder for context compression in a large language model.ICLR, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:3fa57121ff06bcc6b10a37993d2d7b2bb9c2d538b000c24b36ed8b7dd240b643","observation_id":"cd6a8bd6-ff06-44d6-ac4c-bab5c5546d50","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"llama.cpp: Llm inference in c/c++.https: //github.com/ggml-org/llama.cpp, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:216286ea7e159d23e30243ec418b27179589bfd864e6c05f5c9269929d65dba9","observation_id":"0501f133-3c1e-4df2-8bf4-ff28f3a8efa7","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Learning both weights and connections for efficient neural networks","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:c5382720269a62880c223853017b9dfc440789a94437f72a6104428225b16347","observation_id":"140d79f6-bd67-49af-9448-9c38a4e6d533","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Measuring massive multitask language understanding.ICLR, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:39a22356e921b3729d46478641b54cadecc3b8e3821f6e249c5812bd4aec139c","observation_id":"d7f47425-3b64-4319-8d0c-82412a10aac9","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1503.02531","last_updated":"2015-03-09T15:44:49Z","snapshot_observed_at":"2026-08-16T18:00:58.008096Z","submitted_at":"2015-03-09T15:44:49Z","title":"Distilling the Knowledge in a Neural Network","version":1},"cited_work":{"arxiv_id":"1503.02531","doi":"10.1109/cvpr52733.2024.01515","metadata_source":"pith","pith_arxiv_id":"1503.02531","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Distilling the Knowledge in a Neural Network","venue":"stat.ML","work_id":"d927ab1f-17b8-4002-9d09-c3d55764fbad","year":2015},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"cited_paper":"/paper/1503.02531","citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:2d5bd8a3438699e04bbb9eab898a2e31a674bff9302762bded370de5457464e1","observation_id":"9bb9c75b-6374-4ee4-968f-01c0ae76771c","resolution":{"observed_at":"2026-07-02T02:56:28.841101Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T10:32:14.077931Z","title":"Training compute-optimal large language models.Advances in Neural Information Processing Systems, 35, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:76471af569c8e6ff23a0dbfe0dbf56abe44c03e140da180c9112bf659f686f6e","observation_id":"0c258a8f-b340-4938-8a24-64d34bbde838","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Information theory and statistical mechanics.Physical Review, 106(4):620–630, 1957","venue":null,"work_id":null,"year":1957},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:6e1986465aaa3636fa43bce406c8e46b939aa9d510a26655d74b35e4656d6587","observation_id":"98de3cc5-a73e-481b-89e5-c1964fa9d8e1","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Llmlingua: Compressing prompts for accelerated inference of large language models.EMNLP, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:f234ea15c7822649dc177beb9381e23f0cb8cbfb37563e165ba0f921d1d63dfa","observation_id":"d4515042-db72-446b-8927-f2f23962af92","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Swe-bench: Can language models resolve real-world github issues?ICLR, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:b616dcfcbb9fe58bd87f92015c28d41a0ed166f5edf6037e768f64a60bc51638","observation_id":"b439e51a-6f1d-49cc-b970-5b1725f69971","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Pearson, 2nd edition, 2009","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:458691a7adfba8a9bd245929a28fb1f0cde90897af9414d556d8374675f59ce1","observation_id":"2226e3c2-6906-4618-af89-231c8ae7b7e2","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2001.08361","last_updated":"2020-01-23T03:59:20Z","snapshot_observed_at":"2026-08-13T17:41:53.092611Z","submitted_at":"2020-01-23T03:59:20Z","title":"Scaling Laws for Neural Language Models","version":1},"cited_work":{"arxiv_id":"2001.08361","doi":"10.1145/3616855.3635845","metadata_source":"pith","pith_arxiv_id":"2001.08361","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Scaling Laws for Neural Language Models","venue":"cs.LG","work_id":"b7dd8749-9c45-4977-ab9b-64478dce1ae8","year":2020},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"cited_paper":"/paper/2001.08361","citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:8817ce1895f48062bf9487e9d40b7f56b7df67fd43b3d497b9e77c00d5674528","observation_id":"64ab233d-d116-4cf3-b850-28999a28f415","resolution":{"observed_at":"2026-07-02T02:56:28.856276Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T10:32:14.077931Z","title":"Llm wiki: A second brain for llm agents","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:456f85d131ebdc80658fbbbe93d75ab13b9d51352b1267444fd09498df57a1f6","observation_id":"4e07787a-e3dd-40f3-bbcc-7ff40545632f","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Retrieval-augmented generation for knowledge-intensive nlp tasks.Advances in Neural Information Processing Systems, 33, 2020","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:8b557a3836073982651a2b524aacc7e74048ee4150cad7fff7cdf9319a71c7f5","observation_id":"6c09fc64-d7ba-45e6-923d-d6b9a68c1da7","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.06201","last_updated":"2023-10-09T23:03:24Z","snapshot_observed_at":"2026-08-16T14:53:38.585468Z","submitted_at":"2023-10-09T23:03:24Z","title":"Compressing Context to Enhance Inference Efficiency of Large Language Models","version":1},"cited_work":{"arxiv_id":"2310.06201","doi":"10.48550/arxiv.2310.06201","metadata_source":"arxiv_reference","pith_arxiv_id":"2310.06201","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Aixin Liu, Bei Feng, Bin Wang, Bingxuan Wang, Bo Liu, Chenggang Zhao, Chengqi Dengr, Chong Ruan, Damai Dai, Daya Guo, et al","venue":"arXiv (Cornell University)","work_id":"56a7a614-da51-43ee-bf59-0a5e05d2609b","year":2023},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"cited_paper":"/paper/2310.06201","citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:83163f3a4d1c736bc633f51e84e7a1703a0f1aa979ca066a82f8005a903c4638","observation_id":"104866a3-739d-4f92-af58-6962970e8449","resolution":{"observed_at":"2026-07-02T02:56:28.848812Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2503.00000","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-10T01:16:41.254373Z","title":"Guptaet al., arXiv e-prints (2025),Update with ac- tual MCIF reference., 2503.00000","venue":null,"work_id":"ad17618e-94d6-43d4-baf4-78d99556bd6d","year":2025},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:85608ef75d1307b9bb0938d86594ce3480504af78b764185be73d42f01271a53","observation_id":"d5b61f73-ebb9-493f-8032-b8274111630d","resolution":{"observed_at":"2026-07-02T02:56:28.864244Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-23T06:30:58.430688+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T10:32:14.077931Z","title":"Mempalace: Local-first ai memory system.https://github.com/ MemPalace/mempalace, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:538cf18f3a4045c9abaa99d1ffe4d1ca32a8a7afca3aee84012d36847d54daa7","observation_id":"f8e486a5-2627-4927-ad4d-b3597254c785","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Learning to compress prompts with gist tokens","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:dd7bc08cfea49f035b40caf791ae5c443efaba4f1155d6c878d6fe840899ba64","observation_id":"26bd2f02-7b90-4219-bdb4-ad71b732138b","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Ollama: Get up and running with large language models locally","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:f9deb8aed2297218fc5557acdc813e54b1b90aede382257716eca88458e8a19a","observation_id":"32cc8e33-aae7-42f9-a1ed-6bcda7fcdd27","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Graphify: Codebase knowledge graph via tree-sitter.https://github.com/ lucasrosati/claude-code-memory-setup, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:89ef2d52ce2be22ace1ec6dbf8fb0f3aa7ed910b211b55b1ebbbb82c619f9a8b","observation_id":"b6fbf396-ca02-4897-a662-94d0dc561d32","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Stop wasting tokens: A 71.5×cheaper claude code workflow","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:b9b4d871cb10c4bf334b04a715cefa4c6fe2d8dd05c1add437e0c7440f171aeb","observation_id":"f48db7e7-1ebe-4f70-a55c-c991f3d481ec","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"A mathematical theory of communication.The Bell System Technical Journal, 27(3):379–423, 1948","venue":null,"work_id":null,"year":1948},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:b0f858bd60f4853af224fdc9dbfb773c59921642b33f4e15844199f4cdfda930","observation_id":"414013c9-b3e6-4ecb-9643-db94834dec7f","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"Attention is all you need.Advances in Neural Information Processing Systems, 30, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:6d9438aa1cc395bcfd0d9a67c61e92c3386b73eae9bb77bd28cbfe18bb758618","observation_id":"4596c037-4855-44fa-a9b1-af887e77e10f","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"React: Synergizing reasoning and acting in language models.ICLR, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:7834390077d35f961360fe5c1c7f3a0ba1d613c40349e629415c643fda9a5ea7","observation_id":"abb0952a-ad73-4825-860a-6ee9e60dc60e","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","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":"2026-06-28T10:32:14.077931Z","title":"H2o: Heavy-hitter oracle for efficient generative inference of large language models.Advances in Neural Information Processing Systems, 36, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-28T10:32:14.077931Z"},"links":{"citing_paper":"/paper/2606.03739"},"observation_digest":"sha256:a4a407d2857ee82d88fe7fa8c6197018948e4faaa92754e176305e3c849d73b1","observation_id":"54652f56-9813-49f5-9b68-2607974a6584","resolution":{"observed_at":"2026-06-28T10:32:14.077931Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.03739","last_updated":"2026-06-02T14:55:02Z","latest_version":1,"primary_category":"cs.CL","snapshot_observed_at":"2026-08-19T17:58:25.956248Z","submitted_at":"2026-06-02T14:55:02Z","title":"Entropy Gate: Entropy Quenching for Near-Lossless Token Compression in LLM Pipelines"},"reference_resolution":{"displayed":37,"state_counts":{"malformed_identifier":0,"metadata_mismatch":2,"parse_uncertain":0,"unresolved":30,"verified_exact":5,"verified_fuzzy":0},"total_outbound_references":37},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-23T06:30:58.430688+00:00","source":"crossref"},{"observed_at":"2026-08-23T06:30:53.778098+00:00","source":"retraction_watch"}],"thesis":"As of 23 August 2026, this Paper Citation Record lists 37 of 37 outbound references and 0 inbound Pith citation observations for arXiv:2606.03739."}