{"as_of":"2026-08-08T03:33:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3a55ef3ab4162189b4558c73df85797cdf2c03e0d982e67407fd118206bd84cf","coverage":[{"denominator":20,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":20,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-06T19:42:02.778812Z","state":"measured"},{"denominator":21,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":21,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-07-01T08:17:10.481202Z","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":"2026-07-01T08:25:33.443431Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"cited_work":{"arxiv_id":"2507.04889","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2507.04889","snapshot_observed_at":"2026-07-01T08:25:33.443431Z","title":null,"venue":null,"work_id":"6ea174bd-7e6d-4fbc-ac7f-56e3dbaf6f47","year":2025},"citing_paper":{"arxiv_id":"2606.07539","last_updated":"2026-04-29T17:39:36Z","snapshot_observed_at":"2026-08-02T12:30:34.186010Z","submitted_at":"2026-04-29T17:39:36Z","title":"Prompt Governance? On Governing Technologies Governed by Natural Language","version":1},"reference_index":220,"source":"pdf_text","source_observed_at":"2026-07-01T08:17:10.481202Z"},"links":{"cited_paper":"/paper/2507.04889","citing_paper":"/paper/2606.07539"},"observation_digest":"sha256:a9323e25f42480c2ebcbb036e07eee5bcc72c73bf5f902d1594ed37354ca7ae4","observation_id":"21dc31cb-63d4-4e91-ab82-79ac74b6af8a","resolution":{"observed_at":"2026-07-01T08:25:33.445168Z","resolver_source":"arxiv_id","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2507.04889/citation-record","integrity":"/paper/2507.04889/integrity","json":"/paper/2507.04889/citation-record.json","paper":"/paper/2507.04889"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2406.06385","last_updated":"2024-09-03T16:36:06Z","snapshot_observed_at":"2026-08-03T17:41:51.570643Z","submitted_at":"2024-06-10T15:44:22Z","title":"Low-Rank Quantization-Aware Training for LLMs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.06385","snapshot_observed_at":"2026-08-06T19:42:00.899573Z","title":"Low-Rank Quantization- Aware Training for LLMs","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:00.899573Z"},"links":{"cited_paper":"/paper/2406.06385","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:11f0e168b37930075a08803d15601bbcd36258ae027cdfe63c7c7fcad8181e27","observation_id":"95c57692-4605-4118-8f34-aaaddd32e8b6","resolution":{"observed_at":"2026-08-06T19:42:00.899573Z","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":"2026-08-06T19:42:01.265854Z","title":"The Llama 3 Herd of Models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.265854Z"},"links":{"cited_paper":"/paper/2407.21783","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:dd34a98b7ea030d855c8dc6e3bc434f3fcc79cc1542ae7edd82240ae4c842436","observation_id":"9fee9a89-6bc7-4aef-a5ac-882a88bba002","resolution":{"observed_at":"2026-08-06T19:42:01.265854Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2403.14608","last_updated":"2024-09-16T02:54:50Z","snapshot_observed_at":"2026-08-04T09:07:42.158421Z","submitted_at":"2024-03-21T17:55:50Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","version":7},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2403.14608","snapshot_observed_at":"2026-08-06T19:42:01.398780Z","title":"Parameter-Efficient Fine-Tuning for Large Models: A Comprehensive Survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.398780Z"},"links":{"cited_paper":"/paper/2403.14608","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:38848d56f265343006dcc807db533742c4fb02e33c05e448ed5e20576f90e7e9","observation_id":"c900cb8f-bf9c-487d-ac78-c3ada66d128d","resolution":{"observed_at":"2026-08-06T19:42:01.398780Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.14454","last_updated":"2024-12-19T02:09:59Z","snapshot_observed_at":"2026-07-06T20:09:42.677491Z","submitted_at":"2024-12-19T02:09:59Z","title":"Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.14454","snapshot_observed_at":"2026-08-06T19:42:01.551848Z","title":"Are Longer Prompts Always Better? Prompt Selection in Large Language Models for Recommendation Systems","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.551848Z"},"links":{"cited_paper":"/paper/2412.14454","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:7ea18e8ba2f9fdbcfef885969b97e662d17e5ef02892aa022b10d7a6dd98086f","observation_id":"073b46af-19c6-4efd-b97c-a8f5e8cf3719","resolution":{"observed_at":"2026-08-06T19:42:01.551848Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2104.08786","last_updated":"2022-03-03T12:10:58Z","snapshot_observed_at":"2026-07-06T11:01:05.577957Z","submitted_at":"2021-04-18T09:29:16Z","title":"Fantastically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2104.08786","snapshot_observed_at":"2026-08-06T19:42:01.929370Z","title":"Fantas- tically Ordered Prompts and Where to Find Them: Overcoming Few-Shot Prompt Order Sensitivity","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.929370Z"},"links":{"cited_paper":"/paper/2104.08786","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:b1b6dd02f4d23563bf2020cc57f35cb459ce9bd948664e7a4ad175d86142d671","observation_id":"36376b3a-063f-4a71-a1a2-87009f16dc0b","resolution":{"observed_at":"2026-08-06T19:42:01.929370Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08747","last_updated":"2025-01-05T04:09:00Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2023-08-17T02:53:23Z","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-tuning","version":5},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.08747","snapshot_observed_at":"2026-08-06T19:42:02.024680Z","title":"An Empirical Study of Catastrophic Forgetting in Large Language Models During Continual Fine-Tuning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:02.024680Z"},"links":{"cited_paper":"/paper/2308.08747","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:56150865cb1d5a2ed21179448ef26b11010186b36bb361cc0e5dc6044f3355b2","observation_id":"a469524d-016a-4e72-9611-2a7be1fb31cf","resolution":{"observed_at":"2026-08-06T19:42:02.024680Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2202.12837","last_updated":"2022-10-20T14:04:10Z","snapshot_observed_at":"2026-08-01T15:23:39.998892Z","submitted_at":"2022-02-25T17:25:19Z","title":"Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2202.12837","snapshot_observed_at":"2026-08-06T19:42:02.154504Z","title":"Rethinking the Role of Demonstrations: What Makes in-Context Learning Work?","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:02.154504Z"},"links":{"cited_paper":"/paper/2202.12837","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:bb58978edf74112e03a89dcffc98e2476fe397ff9d4806feb9c94b9376d9c98a","observation_id":"69e2730f-bc46-4a05-9023-03ba0a6846b2","resolution":{"observed_at":"2026-08-06T19:42:02.154504Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2405.17202","last_updated":"2024-10-31T03:26:21Z","snapshot_observed_at":"2026-08-07T08:42:03.046490Z","submitted_at":"2024-05-27T14:24:47Z","title":"Efficient multi-prompt evaluation of LLMs","version":3},"cited_work":{"arxiv_id":"2405.17202","doi":"10.48550/arxiv.2405.17202","metadata_source":"pith","pith_arxiv_id":"2405.17202","snapshot_observed_at":"2026-08-07T06:16:28.064256Z","title":"Efficient multi-prompt evaluation of LLMs","venue":"cs.CL","work_id":"200a41ee-9e24-40e8-9c77-f3a15ee905cb","year":2024},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:02.266252Z"},"links":{"cited_paper":"/paper/2405.17202","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:c7fb01a239888f1f96271f914a2f0e136bb63bace7ec6e7351edfedd84a7c003","observation_id":"8417e108-98b4-4b51-be67-6c537a14c9f7","resolution":{"observed_at":"2026-08-06T19:42:03.030966Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.04356","last_updated":"2022-12-06T18:46:04Z","snapshot_observed_at":"2026-07-06T14:28:21.844826Z","submitted_at":"2022-12-06T18:46:04Z","title":"Robust Speech Recognition via Large-Scale Weak Supervision","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.04356","snapshot_observed_at":"2026-08-06T19:42:02.363973Z","title":"Robust Speech Recognition via Large-Scale Weak Supervision","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:02.363973Z"},"links":{"cited_paper":"/paper/2212.04356","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:ca09fc1fc839df577114f01a7075c5d72fac51633be8b1b693fb646cceba8854","observation_id":"7ae0f467-f322-4e49-9d98-7ef88b704a61","resolution":{"observed_at":"2026-08-06T19:42:02.363973Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.13663","last_updated":"2024-12-19T06:32:26Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","submitted_at":"2024-12-18T09:39:44Z","title":"Smarter, Better, Faster, Longer: A Modern Bidirectional Encoder for Fast, Memory Efficient, and Long Context Finetuning and Inference","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.13663","snapshot_observed_at":"2026-08-06T19:42:02.475877Z","title":"Smarter, Better, Faster, Longer: A Modern BidirectionalEncoderforFast, MemoryEfficient, andLongContextFinetuningandInference","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:02.475877Z"},"links":{"cited_paper":"/paper/2412.13663","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:04c5d4d70bec266ab2380b294c08e75b1547b224dfdcaaebcd354286544c589b","observation_id":"995f63ee-7523-4efb-96d6-a74b3eba5be9","resolution":{"observed_at":"2026-08-06T19:42:02.475877Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2407.03978","last_updated":"2024-10-31T08:11:04Z","snapshot_observed_at":"2026-07-06T18:41:35.995594Z","submitted_at":"2024-07-04T14:50:45Z","title":"Benchmarking Complex Instruction-Following with Multiple Constraints Composition","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2407.03978","snapshot_observed_at":"2026-08-06T19:42:02.568438Z","title":"Benchmarking Complex Instruction-Following with Multiple Constraints Composition","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:02.568438Z"},"links":{"cited_paper":"/paper/2407.03978","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:841cdc3f41b95ec0ef6b5522cc6213d353a8f6d96804f29999d4d1b6b7c38bcd","observation_id":"97dde9ae-c4f5-4963-9e88-17599217f8c8","resolution":{"observed_at":"2026-08-06T19:42:02.568438Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2312.12148","last_updated":"2023-12-19T13:31:24Z","snapshot_observed_at":"2026-07-06T17:05:19.007669Z","submitted_at":"2023-12-19T13:31:24Z","title":"Parameter-Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2312.12148","snapshot_observed_at":"2026-08-06T19:42:02.683151Z","title":"Parameter- Efficient Fine-Tuning Methods for Pretrained Language Models: A Critical Review and Assessment","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:02.683151Z"},"links":{"cited_paper":"/paper/2312.12148","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:5cad97c77116d0550c0661befd30d15371cf4ed85978b0229fe5b973082e957b","observation_id":"23f6ae84-93c2-48c6-bc61-4786f43fd5f9","resolution":{"observed_at":"2026-08-06T19:42:02.683151Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.09690","last_updated":"2021-06-10T18:20:59Z","snapshot_observed_at":"2026-08-04T17:24:45.675795Z","submitted_at":"2021-02-19T00:23:59Z","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2102.09690","snapshot_observed_at":"2026-08-06T19:42:02.778812Z","title":"Calibrate Before Use: Improving Few-Shot Performance of Language Models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:02.778812Z"},"links":{"cited_paper":"/paper/2102.09690","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:7ba1d209fab9c801877f8e7fb18340e19ce7ecfba8d7b980dd42b5a4c34cf6ca","observation_id":"d87a4944-d290-4699-bcfd-913853402e8d","resolution":{"observed_at":"2026-08-06T19:42:02.778812Z","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":"2026-08-06T19:42:01.855677Z","title":"Decoupled Weight Decay Regularization","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.855677Z"},"links":{"cited_paper":"/paper/1711.05101","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:50e179a3660b26096ac72aae96ae9e2dd9b5de374a3155b923dd6daf1e9aaf6a","observation_id":"633e7da5-cf2d-42fb-ad50-d9cae5d1cfd0","resolution":{"observed_at":"2026-08-06T19:42:01.855677Z","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":"2026-08-06T19:42:01.080533Z","title":"Language Models Are Few-Shot Learners","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.080533Z"},"links":{"cited_paper":"/paper/2005.14165","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:c7e5b12407526dcc6ec589d93c3f673e06ad03a35104f4e1d9ba62b2aac33ec3","observation_id":"c70cfd6a-5409-43d3-9a29-d860807c5f7c","resolution":{"observed_at":"2026-08-06T19:42:01.080533Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2106.09685","last_updated":"2021-10-16T18:40:34Z","snapshot_observed_at":"2026-08-07T07:43:16.294957Z","submitted_at":"2021-06-17T17:37:18Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.09685","snapshot_observed_at":"2026-08-06T19:42:01.487042Z","title":"LoRA: Low-Rank Adaptation of Large Language Models","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.487042Z"},"links":{"cited_paper":"/paper/2106.09685","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:55f07d40e79947d16a613f2328c58b609b1cdabb688eb511f72c7fe761b101ee","observation_id":"538a01a4-9ce6-404a-b3e9-8498d320a442","resolution":{"observed_at":"2026-08-06T19:42:01.487042Z","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":"2026-08-06T19:42:01.180762Z","title":"LLM.Int8(): 8-Bit Matrix Multiplication for Transformers at Scale","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.180762Z"},"links":{"citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:619aebc323bc22bdeea745893a12205f90dc290f3b8b7828f29e5b8d63c29ca8","observation_id":"cbe224bd-eba5-4b79-980d-f1448be9ce6d","resolution":{"observed_at":"2026-08-06T19:42:01.180762Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2308.03281","last_updated":"2023-08-07T03:52:59Z","snapshot_observed_at":"2026-08-04T23:10:23.964516Z","submitted_at":"2023-08-07T03:52:59Z","title":"Towards General Text Embeddings with Multi-stage Contrastive Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2308.03281","snapshot_observed_at":"2026-08-06T19:42:01.752008Z","title":"Towards General Text Embeddings with Multi-Stage Contrastive Learning","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.752008Z"},"links":{"cited_paper":"/paper/2308.03281","citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:b6de40236cce4004dae04aa26d4cf10d1dc9c05c3fcc1f5fb38e8804c68ad0db","observation_id":"dbbaf3a8-13bf-4de0-8558-39ac713cebb7","resolution":{"observed_at":"2026-08-06T19:42:01.752008Z","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":"10.1073/pnas.2319625121","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:42:03.414604Z","title":"Quantization Avoids Saddle Points in Distributed Optimization","venue":null,"work_id":"81e4bb05-f5ac-465f-a859-2e27cbecf2ac","year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:00.799139Z"},"links":{"citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:5911db1d9fd20316b4cf82578397d676b0e51f2ab15fef2bd83486fab551ae73","observation_id":"7db66d8c-8b3e-40a0-a89d-83266853d2cc","resolution":{"observed_at":"2026-08-06T19:42:03.474538Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":"10.48550/arxiv.2501.18883","metadata_source":"doi_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-06T19:42:03.205526Z","title":"Predictive Prompt Analysis","venue":null,"work_id":"e744f495-c284-4aab-935f-cd39ff4ca217","year":null},"citing_paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-06T19:42:01.646267Z"},"links":{"citing_paper":"/paper/2507.04889"},"observation_digest":"sha256:d66b309b360f5da2d0c6a001acbe245b7c3434639e25f07e786a9276a01a0a10","observation_id":"7596ce54-f459-4ad0-bf55-96897282b28d","resolution":{"observed_at":"2026-08-06T19:42:03.280211Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.04889","last_updated":"2025-07-07T11:23:20Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T08:41:40.870535Z","submitted_at":"2025-07-07T11:23:20Z","title":"Fine-tuning on simulated data outperforms prompting for agent tone of voice"},"reference_resolution":{"displayed":20,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":17,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":20},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 20 of 20 outbound references and 1 inbound Pith citation observation for arXiv:2507.04889."}