{"as_of":"2026-08-04T01:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:467991888b6dabd1031aac7c750a13f08b41a6fcdd88e3ba192ced60908b8435","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-05-12T02:27:22.169290Z","state":"measured"},{"denominator":16,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":16,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-03T06:30:56.289259+00:00","state":"measured"},{"denominator":4,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":4,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T23:26:15.804622Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-05-22T06:11:08.934061Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"cited_work":{"arxiv_id":"2605.09650","doi":null,"metadata_source":"pith","pith_arxiv_id":"2605.09650","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Workspace Optimization: How to Train Your Agent","venue":"cs.AI","work_id":"4861ee13-7796-4794-91af-b5b283d136d3","year":2026},"citing_paper":{"arxiv_id":"2605.22166","last_updated":"2026-05-27T04:34:36Z","snapshot_observed_at":"2026-07-06T23:32:30.578213Z","submitted_at":"2026-05-21T08:36:49Z","title":"Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-05-22T06:10:26.185447Z"},"links":{"cited_paper":"/paper/2605.09650","citing_paper":"/paper/2605.22166"},"observation_digest":"sha256:86526051527cbe43f62f7386492d391bdf57033be10d04d70c158b48868cb97d","observation_id":"a2c397b7-3b45-47de-8f08-d0b5296dc628","resolution":{"observed_at":"2026-05-22T06:11:08.937182Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.09650","snapshot_observed_at":"2026-08-01T23:26:15.804622Z","title":"Workspace optimization: How to train your agent, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.15439","last_updated":"2026-07-16T20:18:59Z","snapshot_observed_at":"2026-08-02T22:55:43.716593Z","submitted_at":"2026-07-16T20:18:59Z","title":"Do Coding Agents Need Executable World Models, Simplification, and Verification to Solve ARC-AGI-3?","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T23:26:15.804622Z"},"links":{"cited_paper":"/paper/2605.09650","citing_paper":"/paper/2607.15439"},"observation_digest":"sha256:d5458e753d92fdd84b8cde673fc957393f1fd6a84ab98292f6b41a9c8f659593","observation_id":"86e1f36b-7400-4623-a323-69be51d1c8e4","resolution":{"observed_at":"2026-08-01T23:26:15.804622Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.09650","snapshot_observed_at":"2026-08-01T09:39:45.987272Z","title":"Workspace optimization: How to train your agent.arXiv preprint arXiv:2605.09650, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.20709","last_updated":"2026-07-22T20:25:55Z","snapshot_observed_at":"2026-08-03T06:14:31.246388Z","submitted_at":"2026-07-22T20:25:55Z","title":"NVIDIA-labs OO Agents: Native Python Object-Oriented Agents","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-01T09:39:45.987272Z"},"links":{"cited_paper":"/paper/2605.09650","citing_paper":"/paper/2607.20709"},"observation_digest":"sha256:7b0a9959b994b2572bb0054c0b4adebfb21e50c842eb506183ea27bfcc38331f","observation_id":"8af171e6-247a-4db9-b1fd-3e35b521d615","resolution":{"observed_at":"2026-08-01T09:39:45.987272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.09650","snapshot_observed_at":"2026-07-31T12:16:33.719014Z","title":"arXiv preprint arXiv:2605.09650 , year=","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.28287","last_updated":"2026-07-30T14:34:41Z","snapshot_observed_at":"2026-08-03T00:08:51.056317Z","submitted_at":"2026-07-30T14:34:41Z","title":"Tycho: Active Abstraction with Programmatic World Models for ARC-AGI-3","version":1},"reference_index":85,"source":"arxiv_source","source_observed_at":"2026-07-31T12:16:33.719014Z"},"links":{"cited_paper":"/paper/2605.09650","citing_paper":"/paper/2607.28287"},"observation_digest":"sha256:a4ddad7cf15f166347cad6c7d97cb29c9e814da4e7466716dbc8c5418ca5634a","observation_id":"7afbaea1-5df8-4121-a4b3-36dcc3f62397","resolution":{"observed_at":"2026-07-31T12:16:33.719014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"links":{"evidence":"/evidence","html":"/paper/2605.09650/citation-record","integrity":"/paper/2605.09650/integrity","json":"/paper/2605.09650/citation-record.json","paper":"/paper/2605.09650"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2509.04439","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-09T00:45:49.078281Z","title":"Arcmemo: Abstract reasoning composition with lifelong llm memory","venue":null,"work_id":"46a4a381-6b80-47f2-b4b1-823a1e62bfac","year":2025},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:62ac77641b9fc8fc48a8f66cc5c598b317fb9aaba1dfb2bdcbcdef6efe7ecfba","observation_id":"987c6e61-000b-4df5-8ce1-4552204bb07e","resolution":{"observed_at":"2026-05-12T07:37:00.848871Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2603.28052","last_updated":"2026-03-30T05:33:50Z","snapshot_observed_at":"2026-07-06T22:51:00.579062Z","submitted_at":"2026-03-30T05:33:50Z","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","version":1},"cited_work":{"arxiv_id":"2603.28052","doi":"10.48550/arxiv.2603.28052","metadata_source":"pith","pith_arxiv_id":"2603.28052","snapshot_observed_at":"2026-07-11T00:27:50.071304Z","title":"Meta-Harness: End-to-End Optimization of Model Harnesses","venue":"cs.AI","work_id":"5be3c079-4ffa-458f-adcf-204b66f7af51","year":2026},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"cited_paper":"/paper/2603.28052","citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:f899848e2dcf83522641b3b0e475a2de3b32c014cef6037b75e836fa4c5973b7","observation_id":"d865b5cf-e4c5-432f-a49b-7f3524c2125d","resolution":{"observed_at":"2026-05-13T16:15:58.398964Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2509.25140","last_updated":"2026-03-16T20:49:28Z","snapshot_observed_at":"2026-08-02T12:08:17.149184Z","submitted_at":"2025-09-29T17:51:03Z","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","version":2},"cited_work":{"arxiv_id":"2509.25140","doi":"10.48550/arxiv.2509.25140","metadata_source":"pith","pith_arxiv_id":"2509.25140","snapshot_observed_at":"2026-07-10T12:15:01.137692Z","title":"ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory","venue":"cs.AI","work_id":"551218b8-a306-4c1e-8795-6232cc30192b","year":2025},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"cited_paper":"/paper/2509.25140","citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:5a7ff7b4366003383dd47b742c358c84905496a86a03b896c2386fe91903e556","observation_id":"7f5b59a8-7aad-4c15-b7b6-3df4cbd0439d","resolution":{"observed_at":"2026-05-15T05:42:50.464031Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-05-22T15:52:34.995342+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-22T15:52:34.995342+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.03442","last_updated":"2023-08-06T00:21:19Z","snapshot_observed_at":"2026-07-06T15:13:13.695535Z","submitted_at":"2023-04-07T01:55:19Z","title":"Generative Agents: Interactive Simulacra of Human Behavior","version":2},"cited_work":{"arxiv_id":"2304.03442","doi":"10.1001/jamapsychiatry.2022.0609","metadata_source":"pith","pith_arxiv_id":"2304.03442","snapshot_observed_at":"2026-07-11T11:50:26.030339Z","title":"Generative Agents: Interactive Simulacra of Human Behavior","venue":"cs.HC","work_id":"01f7ddaa-284a-441a-be87-921aad4dc54b","year":2023},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"cited_paper":"/paper/2304.03442","citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:4a7af18149f76b6be94e8eaaedbad23b6ef83c562e741d69915f1f997520e293","observation_id":"beec7f6b-ca40-4b15-8e27-370253ec5cef","resolution":{"observed_at":"2026-05-12T07:37:00.716210Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-05-24T05:54:33.103795+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-24T05:54:33.103795+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2306.12672","last_updated":"2023-06-23T06:05:31Z","snapshot_observed_at":"2026-07-06T15:45:24.674515Z","submitted_at":"2023-06-22T05:14:00Z","title":"From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thought","version":2},"cited_work":{"arxiv_id":"2306.12672","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2306.12672","snapshot_observed_at":"2026-07-02T08:16:47.564365Z","title":"K.; Goodman, N","venue":null,"work_id":"6c5737b4-17c2-4f98-8bee-b388145aef7b","year":2023},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"cited_paper":"/paper/2306.12672","citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:1e46a7027979a666a424b09c184a4fc52576cb53707bae9b06d4f0ade6cca28f","observation_id":"50905093-3897-40ee-ad4b-c493f28b4fd0","resolution":{"observed_at":"2026-05-12T07:37:00.591676Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2512.24601","last_updated":"2026-05-11T15:26:31Z","snapshot_observed_at":"2026-07-06T22:40:27.178487Z","submitted_at":"2025-12-31T03:43:41Z","title":"Recursive Language Models","version":3},"cited_work":{"arxiv_id":"2512.24601","doi":"10.48550/arxiv.2512.24601","metadata_source":"pith","pith_arxiv_id":"2512.24601","snapshot_observed_at":"2026-07-10T16:57:24.578170Z","title":"Recursive Language Models","venue":"cs.AI","work_id":"695de9e6-4374-4788-916e-33e8c0667aae","year":2025},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"cited_paper":"/paper/2512.24601","citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:83e8cfd7de5de47850fef474dae15ed0ef67af12a31aa638bd82a451ccf490e7","observation_id":"7d196f65-9e07-4758-9f74-8720fe83f0b9","resolution":{"observed_at":"2026-05-12T07:37:00.196237Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"2a9d46d7-b2dd-475c-b63d-040f085bd7d6","year":null},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:81784b43fca3fe7c277defe61ee7d89c50702f72ee1ee332571d9aa73c90d8fe","observation_id":"8ccb78dd-f76c-4420-9827-3ed8d3e572b9","resolution":{"observed_at":"2026-05-12T22:41:56.470606Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"1603096c-c881-4b41-be71-43a24b8bc6bc","year":null},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:6831f1161a9f7b8d2869bf695be8e5c02900355eac971b707a71835094e5efaf","observation_id":"61488062-b0ab-45e5-bb6a-1815dc2972c5","resolution":{"observed_at":"2026-05-12T22:41:56.473662Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"The delta is feedback rather than a hard gate, so the role can keep iterating within the round budget","venue":null,"work_id":"e2b9bcb6-762b-4b78-8f71-9b7ffdfd1850","year":null},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:8f11cf0e684d3c41a51c71f645299317bfcb217e5cff85ee3f3d3f9dabe620ee","observation_id":"cb106ca8-7ed7-48ea-8a12-96209a62dafa","resolution":{"observed_at":"2026-05-12T22:41:56.478196Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"0843115f-c11d-40a2-ab98-37b862763612","year":null},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:491350ebef560a151bdd778402cd59eb7d5d895834ebd840ff36dfbfcb02e979","observation_id":"74e10418-ca9a-4ef3-9d49-e5914628d286","resolution":{"observed_at":"2026-05-12T22:41:56.481417Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":null,"venue":null,"work_id":"259583c5-d732-40b2-9ba5-175c58783357","year":null},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:ff9c869a4c72e99f99c54aea8829bbc718b9ab71e3be805030fabc08f18f1f00","observation_id":"71b3e34f-54e8-41bf-958e-a82c2a4da19a","resolution":{"observed_at":"2026-05-12T22:41:56.484737Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"ACTION:entity","venue":null,"work_id":"8fcbbd08-39e5-4d90-ab23-834cf74d15f1","year":2026},"citing_paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-05-12T02:27:22.169290Z"},"links":{"citing_paper":"/paper/2605.09650"},"observation_digest":"sha256:f5526977d33f33b2d00b3d8850ef11a25db52befd613ac3386f2a48aa08f3aa3","observation_id":"f26b6939-2893-403f-bc4b-81592443140f","resolution":{"observed_at":"2026-05-12T22:41:56.488605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-03T06:30:56.289259+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2605.09650","last_updated":"2026-05-10T16:52:10Z","latest_version":1,"primary_category":"cs.AI","snapshot_observed_at":"2026-08-02T04:49:54.300688Z","submitted_at":"2026-05-10T16:52:10Z","title":"Workspace Optimization: How to Train Your Agent"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":4,"parse_uncertain":0,"unresolved":4,"verified_exact":2,"verified_fuzzy":2},"total_outbound_references":12},"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":"2026-08-03T06:30:56.289259+00:00","source":"crossref"},{"observed_at":"2026-08-03T06:30:50.922721+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 4 inbound Pith citation observations for arXiv:2605.09650."}