{"as_of":"2026-08-21T09:02:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a881f347e3f137e97548270af8f88cae22a4a7a76caabb5c1d8abe5065c342e9","coverage":[{"denominator":61,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":61,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T14:26:49.899186Z","state":"measured"},{"denominator":61,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":61,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-21T06:32:19.484+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/2608.10402/citation-record","integrity":"/paper/2608.10402/integrity","json":"/paper/2608.10402/citation-record.json","paper":"/paper/2608.10402"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"2511.21631","last_updated":"2025-11-27T12:16:54Z","snapshot_observed_at":"2026-08-17T13:26:10.378579Z","submitted_at":"2025-11-26T17:59:08Z","title":"Qwen3-VL Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.21631","snapshot_observed_at":"2026-08-15T14:26:49.693059Z","title":"Qwen3-vl technical report.arXiv preprint arXiv:2511.21631, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.693059Z"},"links":{"cited_paper":"/paper/2511.21631","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:bc22bbe9c02486c3e53a0eb10a510a01454c45085480292d7f32f41051e736e3","observation_id":"82618e03-ec9b-4d8f-85ef-dc20e26b33cc","resolution":{"observed_at":"2026-08-15T14:26:49.693059Z","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":"2026-08-15T14:26:49.697514Z","title":"Concur: High-throughput agentic batch inference of llm via congestion-based concurrency control.arXiv preprint arXiv:2601.22705, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.697514Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:aefee87c75cbd542fed8b70320dffad59e008944bbbe9b92006c4cf8f110e065","observation_id":"a37e8fe2-00b4-40ae-8764-3407108ea365","resolution":{"observed_at":"2026-08-15T14:26:49.697514Z","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":"2026-08-15T14:26:49.700935Z","title":"Fast llm post-training via decoupled and fastest-of-n speculation.arXiv preprint arXiv:2511.16193, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.700935Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:c60062cabf6610ff80ed7409fc389b48128a7af2af81e8fbab013bd588990d33","observation_id":"e67f34b9-c3c0-49db-b151-0b8bdc79881e","resolution":{"observed_at":"2026-08-15T14:26:49.700935Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.19017","last_updated":"2025-07-25T07:11:49Z","snapshot_observed_at":"2026-08-19T06:36:45.292994Z","submitted_at":"2025-07-25T07:11:49Z","title":"MindSpeed RL: Distributed Dataflow for Scalable and Efficient RL Training on Ascend NPU Cluster","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.19017","snapshot_observed_at":"2026-08-15T14:26:49.704505Z","title":"Mindspeed rl: Distributed dataflow for scalable and efficient rl training on ascend npu cluster.arXiv preprint arXiv:2507.19017, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.704505Z"},"links":{"cited_paper":"/paper/2507.19017","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:002bbb9264b0a9c29bbbc58f3513210ae60d655749adef466a6d3dc8d0874c43","observation_id":"a8b5541e-3e30-436d-804b-0ed94e9d8c6e","resolution":{"observed_at":"2026-08-15T14:26:49.704505Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.940195Z","title":"AREAL: A large-scale asynchronous reinforcement learning system for language reasoning","venue":null,"work_id":"66ec6e13-d0d5-4f57-a9d8-283bf657369a","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.708179Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:4d7d728104afe46eea2cf2d461266b77478834b73617300a03937a28dc860d8b","observation_id":"1014d932-c40f-41b3-a3a5-eb2747449483","resolution":{"observed_at":"2026-08-15T14:26:50.944023Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.929406Z","title":"Cost-Efficient large language model serving for multi-turn conversations with CachedAtten- tion","venue":null,"work_id":"61d5d4d8-884a-4dcd-8a3d-f902b044d2b2","year":2024},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.711705Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:d44521ea3e455eb4be5ca77ab42888ce500a01224ed3041db4e7bf954f6f60eb","observation_id":"f9e5f4ac-b803-4671-93e0-9a1951833aeb","resolution":{"observed_at":"2026-08-15T14:26:50.933259Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.918402Z","title":"An empirical study on low gpu utilization of deep learn- ing jobs","venue":null,"work_id":"4023bd60-7a10-4994-9d17-635a7c9c5380","year":2024},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.715206Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:070aa773b6ea9d0c2530712d45a808fd5ad295b68dc02a3ab62431bfc9c4e8de","observation_id":"b7ee8ca3-fbf3-4b11-a1f5-4904ed5c6dba","resolution":{"observed_at":"2026-08-15T14:26:50.922155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2404.19737","last_updated":"2024-04-30T17:33:57Z","snapshot_observed_at":"2026-08-16T23:36:44.216328Z","submitted_at":"2024-04-30T17:33:57Z","title":"Better & Faster Large Language Models via Multi-token Prediction","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2404.19737","snapshot_observed_at":"2026-08-15T14:26:49.718231Z","title":"Better & faster large language models via multi-token prediction.arXiv preprint arXiv:2404.19737, 2024","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.718231Z"},"links":{"cited_paper":"/paper/2404.19737","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:15df611d0346b098893a0f1592ed17a36c746d5b61752e42c6324c0bc233ffac","observation_id":"64a2742a-af11-4671-8b65-3abe89dba088","resolution":{"observed_at":"2026-08-15T14:26:49.718231Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.908312Z","title":"Elasticflow: An elastic server- less training platform for distributed deep learning","venue":null,"work_id":"60a312e1-c6a0-4a71-8ad9-0876969bd7dd","year":2023},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.721542Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:34a4ac85d67a035e4674f0bd52939778b26a888358fe9a6fdf38906a10ac55e6","observation_id":"d08eb4d2-3e28-4c8e-a01b-4d1e8f17dbba","resolution":{"observed_at":"2026-08-15T14:26:50.911709Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2507.01663","last_updated":"2025-07-02T12:45:34Z","snapshot_observed_at":"2026-08-13T08:22:12.599337Z","submitted_at":"2025-07-02T12:45:34Z","title":"AsyncFlow: An Asynchronous Streaming RL Framework for Efficient LLM Post-Training","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.01663","snapshot_observed_at":"2026-08-15T14:26:49.724333Z","title":"Asyncflow: An asynchronous streaming rl framework for efficient llm post-training.arXiv preprint arXiv:2507.01663, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.724333Z"},"links":{"cited_paper":"/paper/2507.01663","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:eeb8d47f155598ef27324dedb87223b80846ca7f3fb0dfc9aa89c6ed8011603b","observation_id":"7bc8be89-b6cb-45ef-a78c-efe4d2c526b1","resolution":{"observed_at":"2026-08-15T14:26:49.724333Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.897814Z","title":"OpenRLHF: A ray-based easy-to-use, scal- able and high-performance RLHF framework","venue":null,"work_id":"ff937006-acf8-4a6c-accf-202638a1cb1e","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.728233Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:fc0b874a3920d52104b4e5ce3cde1952375158f162086aa591592f108fa2be0b","observation_id":"f7add97b-798b-4869-bf0e-3f8d1dbbc92c","resolution":{"observed_at":"2026-08-15T14:26:50.901581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.880660Z","title":"Gpipe: Efficient training of giant neural networks us- ing pipeline parallelism","venue":null,"work_id":"f47aa412-3269-4433-9274-d3fa11a5a0b3","year":2019},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.734628Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:0fd0c8ebcaae7ac5b8e1215ee4079d8fa18fcbfd73b5cd666e1647cff3e2d97d","observation_id":"7f4d7fc5-bdbb-48ba-ade2-1c8e8caf6eeb","resolution":{"observed_at":"2026-08-15T14:26:50.884290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.870423Z","title":"Elastic resource sharing for distributed deep learning","venue":null,"work_id":"5a374caa-86d8-4b0e-8306-df7219636e4a","year":2021},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.737811Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:f2d12413eedf480f83063653c22bd5c1fd4dda06d508366d0bbd82a9d2373342","observation_id":"a0b23b16-743e-47f9-ba03-65e301e64888","resolution":{"observed_at":"2026-08-15T14:26:50.873982Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T14:26:49.740802Z","title":"Efficient memory man- agement for large language model serving with page- dattention","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.740802Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:c648504d379f9e1bd8aa821cd5ae3cab871d872637929bb54c427d8386467185","observation_id":"a127731c-6ccd-4b83-9fe7-4f108fa2508e","resolution":{"observed_at":"2026-08-15T14:26:49.740802Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2511.02230","last_updated":"2026-05-25T23:34:23Z","snapshot_observed_at":"2026-08-20T02:29:27.571369Z","submitted_at":"2025-11-04T03:43:05Z","title":"Continuum: Efficient and Robust Multi-Turn LLM Agent Scheduling with KV Cache Time-to-Live","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.02230","snapshot_observed_at":"2026-08-15T14:26:49.744036Z","title":"Con- tinuum: Efficient and robust multi-turn llm agent scheduling with kv cache time-to-live.arXiv preprint arXiv:2511.02230, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.744036Z"},"links":{"cited_paper":"/paper/2511.02230","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:d49103725854c011f7b6a72bb194f8c65ea98ace11d5a775fbe392207570a693","observation_id":"9795f78c-8429-4813-983d-7b4c611d7077","resolution":{"observed_at":"2026-08-15T14:26:49.744036Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.853755Z","title":"Chimera: efficiently training large-scale neural networks with bidirectional pipelines","venue":null,"work_id":"01450bae-385c-46c3-a12c-17e3dec91700","year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.747429Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:6e9c31d28b37c8a005805dfe90f163f2dbefa60ae04b6ddcecd5c57445b611e6","observation_id":"cd8d188a-83ad-402e-abc1-9bd1375b2af0","resolution":{"observed_at":"2026-08-15T14:26:50.857508Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T14:26:49.753999Z","title":"Agentbench: Evaluating LLMs as agents","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.753999Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:d667d6d8543458b48bc35d9734cfde64ca009c9d69078867d56721c7c8a11bbd","observation_id":"b8330ebb-a3bd-4d2c-baae-dffef575bc18","resolution":{"observed_at":"2026-08-15T14:26:49.753999Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.826283Z","title":"Visualagent- bench: Towards large multimodal models as visual foun- dation agents","venue":null,"work_id":"74616b75-c28e-488c-8a73-1799e3698d16","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.756994Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:fa1880a5649b79088ef07cd80ea9ea767d1d2d2148313e6045ef3a188d4c2335","observation_id":"64555e3f-ef62-45fd-abea-d08ddec23249","resolution":{"observed_at":"2026-08-15T14:26:50.830043Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.815055Z","title":"Devanur, Gregory R","venue":null,"work_id":"b9b6a63c-2eac-4281-be3c-eb41d210972c","year":2019},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.760407Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:e7219a92e85b5a1b7781233112e9532cf665b4368aacb0102de848c2bf33c68a","observation_id":"1af656f2-25a5-4ceb-a0e1-8017fc5eccf9","resolution":{"observed_at":"2026-08-15T14:26:50.818730Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T14:26:49.763461Z","title":"Efficient large-scale language model training on gpu clusters using megatron-lm","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.763461Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:2fe9f0c431512e93186b06b7861a3893d6e54f04393188e51af6492416d5de79","observation_id":"3c909a80-9959-4b17-88db-236fd036fd39","resolution":{"observed_at":"2026-08-15T14:26:49.763461Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.797037Z","title":"Suffixdecoding: Extreme speculative decod- ing for emerging AI applications","venue":null,"work_id":"7f321878-0ffd-4466-ba80-e37c2262829f","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.767044Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:526c2a92720ee7117e1d1091088ee084a156ca901d6e094535fb059a763253aa","observation_id":"a0f7d344-c816-407f-8eef-4c942a486574","resolution":{"observed_at":"2026-08-15T14:26:50.800449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.787702Z","title":"Ganger, and Eric P","venue":null,"work_id":"53cdb24d-00a4-4956-8d14-fd1c136e6bbc","year":2021},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.770249Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:6440e6d40ec046a36c8b0b9748e058ffdf061e4c9f8408daf3688ac64fc2799c","observation_id":"9fe08512-db9c-41ca-aaf7-fbbd12e29f30","resolution":{"observed_at":"2026-08-15T14:26:50.790945Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2511.14617","last_updated":"2026-04-03T12:47:37Z","snapshot_observed_at":"2026-08-20T12:38:06.758101Z","submitted_at":"2025-11-18T16:12:21Z","title":"Seer: Online Context Learning for Fast Synchronous LLM Reinforcement Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2511.14617","snapshot_observed_at":"2026-08-15T14:26:49.773529Z","title":"Seer: Online con- text learning for fast synchronous llm reinforcement learning.arXiv preprint arXiv:2511.14617, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.773529Z"},"links":{"cited_paper":"/paper/2511.14617","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:32b7c689b5a8514876eefd9abee0beee99d0101be4be609dd602c935a1d2984c","observation_id":"a9f0904e-13d8-45f5-8f86-8d37bcd4faf8","resolution":{"observed_at":"2026-08-15T14:26:49.773529Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.15115","last_updated":"2025-01-03T02:18:21Z","snapshot_observed_at":"2026-08-17T18:50:07.059564Z","submitted_at":"2024-12-19T17:56:09Z","title":"Qwen2.5 Technical Report","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2412.15115","snapshot_observed_at":"2026-08-15T14:26:49.777123Z","title":"Qwen2.5 technical report.arXiv preprint arXiv:2412.15115, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.777123Z"},"links":{"cited_paper":"/paper/2412.15115","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:ca7a75be5d3e398b386e2b8dee99b9e8dc1f654e019d62820c38648b06522588","observation_id":"6d1a760b-1e27-4f13-bd4a-b93df838e698","resolution":{"observed_at":"2026-08-15T14:26:49.777123Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.776235Z","title":"Qwen3.5: Towards native multimodal agents","venue":null,"work_id":"358016ed-b339-412f-b523-e6a0bf900d21","year":2026},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.780368Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:f2bbe51622443f262468b7302050a40894645d20f34398eff7703151ba6fc9fc","observation_id":"861a0e83-9f51-4b29-8fcf-85b9b74ac108","resolution":{"observed_at":"2026-08-15T14:26:50.780185Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.765577Z","title":"Transcending cost-quality tradeoff in agent serving via session-awareness","venue":null,"work_id":"04cbe6e9-ef52-40fb-a59f-12adda62047a","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.783669Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:d73e7fffac5e2212d91ad31f2a313f30f4da620e1e2237a58c9a0930a780c029","observation_id":"53d8c996-065c-4da7-8db5-6129a75ddc4c","resolution":{"observed_at":"2026-08-15T14:26:50.769290Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1707.06347","last_updated":"2017-08-28T09:20:06Z","snapshot_observed_at":"2026-08-20T07:04:06.309989Z","submitted_at":"2017-07-20T02:32:33Z","title":"Proximal Policy Optimization Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1707.06347","snapshot_observed_at":"2026-08-15T14:26:49.787186Z","title":"Proximal policy optimiza- tion algorithms.arXiv preprint arXiv:1707.06347, 2017","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.787186Z"},"links":{"cited_paper":"/paper/1707.06347","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:f246a5f23b5e6ca56d320bcc1c683a93ddb5570aeefb7a4beb428696e0496cea","observation_id":"c38ba17c-23f2-4a81-8932-c16c12b0a77f","resolution":{"observed_at":"2026-08-15T14:26:49.787186Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.03300","last_updated":"2024-04-27T15:25:53Z","snapshot_observed_at":"2026-08-06T14:58:42.911363Z","submitted_at":"2024-02-05T18:55:32Z","title":"DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.03300","snapshot_observed_at":"2026-08-15T14:26:49.790558Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.790558Z"},"links":{"cited_paper":"/paper/2402.03300","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:65f2b492d6617eb9a5781725c8f2caff7df746b65f9453997b84a105e07499e1","observation_id":"1ac890ec-f01b-4a80-b899-49042c7a7e45","resolution":{"observed_at":"2026-08-15T14:26:49.790558Z","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":"2026-08-15T14:26:49.794254Z","title":"Laminar: A scalable asynchronous rl post-training framework.arXiv preprint arXiv:2510.12633, 2025","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.794254Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:70cf906ce96775d1fa44d779487e4594709a8cdd70b75e0f1669597b67ff61a2","observation_id":"5f74ee9c-a882-4b13-8c00-8421c6d93ca1","resolution":{"observed_at":"2026-08-15T14:26:49.794254Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.753233Z","title":"Hybridflow: A flexible and efficient rlhf framework","venue":null,"work_id":"367c3026-7ad9-417a-8abd-5a17d1b86177","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.797585Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:5dd10f289b98730ca1f038c9260dc2f049b86f44a769429e81e4e9c1094510f1","observation_id":"94624e24-24ed-4d71-bdfe-b2df374b4163","resolution":{"observed_at":"2026-08-15T14:26:50.757694Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.739716Z","title":"ALFWorld: Aligning Text and Embodied Environments for Interactive Learning","venue":null,"work_id":"3254240e-a05d-4aee-81e4-f263255cf252","year":2021},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.800904Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:57fee7bebdd4d5964773e55e7cce9400742456e05d9000555373dad341aa0f5e","observation_id":"ffb682cc-fc5b-4c85-ba09-3d0a18a31f57","resolution":{"observed_at":"2026-08-15T14:26:50.744090Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.727061Z","title":"Learning to summarize with human feedback","venue":null,"work_id":"0f88848c-4b8a-4ab8-ab74-ea659e4cb6e3","year":2020},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.804312Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:b4789d696f23de7f7ff1ba41ec4f5b07a03b033cf6f354479071fde695d7db2b","observation_id":"5362262e-2030-46a4-9b86-aba806c480f9","resolution":{"observed_at":"2026-08-15T14:26:50.731406Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2505.19897","last_updated":"2026-04-20T16:29:04Z","snapshot_observed_at":"2026-08-18T01:10:23.346857Z","submitted_at":"2025-05-26T12:27:27Z","title":"ScienceBoard: Evaluating Multimodal Autonomous Agents in Realistic Scientific Workflows","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.19897","snapshot_observed_at":"2026-08-15T14:26:49.807840Z","title":"Scienceboard: Evaluating multimodal au- tonomous agents in realistic scientific workflows.arXiv preprint arXiv:2505.19897, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.807840Z"},"links":{"cited_paper":"/paper/2505.19897","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:dabc27461f22dbea69a3f7a72533ed93b511c2007d05d07a998c9f1ca2ef3fc7","observation_id":"ffe025e8-6546-4c1c-b595-d37f1e8e413d","resolution":{"observed_at":"2026-08-15T14:26:49.807840Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.713050Z","title":"dist_checkpointing package","venue":null,"work_id":"0d7b6c4f-61e7-4968-b59f-9ddd1f66024a","year":2026},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.811669Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:921e8e19e466e06e033d44d877b94aa366f2edb9a89e1b1de691910ce27de941","observation_id":"9027aa32-a355-45a5-8d19-83cbf2209523","resolution":{"observed_at":"2026-08-15T14:26:50.717469Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T14:26:49.815281Z","title":"Efficient llm serving for agentic workflows: A data systems per- spective.arXiv preprint arXiv:2603.16104, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.815281Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:5f34b94bd0ec34893f94d53cb68fef368cdb2061cc8c1866fff0faf880c439ac","observation_id":"e97b0279-a541-49bb-8d0a-ab5cc3144b80","resolution":{"observed_at":"2026-08-15T14:26:49.815281Z","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":"2026-08-15T14:26:49.818561Z","title":"ByteCheckpoint: A unified checkpointing system for large foundation model development","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.818561Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:f532e37f1d874265d97ea7c6e80642f59ba9786ff63375822a90f70c66e10f57","observation_id":"d3f8c0e2-a7c7-422a-b4db-813ce342a289","resolution":{"observed_at":"2026-08-15T14:26:49.818561Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.22950","last_updated":"2025-06-28T16:52:29Z","snapshot_observed_at":"2026-08-16T18:40:53.708179Z","submitted_at":"2025-06-28T16:52:29Z","title":"Infinite Sampling: Efficient and Stable Grouped RL Training for Large Language Models","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.22950","snapshot_observed_at":"2026-08-15T14:26:49.821867Z","title":"Infinite sampling: Ef- ficient and stable grouped rl training for large language models.arXiv preprint arXiv:2506.22950, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.821867Z"},"links":{"cited_paper":"/paper/2506.22950","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:855a7aaa4ea7aeea0232faf7310fdf5e959184e1edc35bf512180d3212663fe0","observation_id":"5e194027-7fbd-4cf7-816b-ace09f840c68","resolution":{"observed_at":"2026-08-15T14:26:49.821867Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.691263Z","title":"AntMan: Dynamic scaling on GPU clus- ters for deep learning","venue":null,"work_id":"519606a9-6cfe-4a8a-a33c-5be39d3870ce","year":2020},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.825690Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:0edef916770687504bf93c1828a16c35e65b3a76976f6a620535009027286e4f","observation_id":"fc4aea15-8dc9-442b-b4b3-c4ddd4697940","resolution":{"observed_at":"2026-08-15T14:26:50.695454Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.678258Z","title":"OSWorld: Benchmarking multimodal agents for open-ended tasks in real com- puter environments","venue":null,"work_id":"5a87c45b-22dc-46d9-9e6f-00945277be1b","year":2024},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.829112Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:d64e904e093f35e7f170f6da1508105853ae3e9384d99ccb76a23e00730a559e","observation_id":"e015e9d5-e1b4-4a04-a0d7-e9bbce5dfebc","resolution":{"observed_at":"2026-08-15T14:26:50.682580Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.665746Z","title":"SGLang HiCache: Fast Hierarchical KV Caching with Your Favorite Storage Backends - LMSYS Blog — lmsys.org","venue":null,"work_id":"ce3feb8a-135e-46e3-8a27-4e168b97cd10","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.832579Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:2df45f1749e1dbac4631291ba3ee8b24aac887f3fae0442753f23d5db10576a2","observation_id":"93117da0-00b7-4397-9739-f06f95b1711f","resolution":{"observed_at":"2026-08-15T14:26:50.670009Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.652449Z","title":"AndroidLab: Training and systematic benchmarking of android autonomous agents","venue":null,"work_id":"b55317d0-7cb9-4284-bad1-e24479023e9c","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.835791Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:aee514e34d092bab69e8d93ca52c08fe9a947fc4686c264b973e71cf33b5aa32","observation_id":"3747fd94-750a-4ed2-ae38-8d126c5224ec","resolution":{"observed_at":"2026-08-15T14:26:50.657848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.640351Z","title":"Webshop: Towards scalable real-world web interaction with grounded language agents","venue":null,"work_id":"bb92de41-fe80-45d4-b71c-bc86d447c029","year":2022},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.839138Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:adb89a730b33facd33ba6b9e2eb983bda21a5efc37f9a87e0ebdff97da09120c","observation_id":"107ab895-44ea-43d7-98e8-b3bca806d12c","resolution":{"observed_at":"2026-08-15T14:26:50.644853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.628110Z","title":"Orca: A distributed serving system for Transformer-Based generative mod- els","venue":null,"work_id":"94ed9cf1-1c1f-4f4b-a9ab-8f71188297ea","year":2022},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.842641Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:0c6f662dd60aba10dcfc8928b6cb842a29aa023e706ad55cf7a11f5a5299dade","observation_id":"65fcf7fe-bfcc-4e0d-a664-627b964e77df","resolution":{"observed_at":"2026-08-15T14:26:50.632337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T14:26:49.846014Z","title":"Agentrl: Scaling agentic reinforcement learning with a multi-turn, multi-task framework.arXiv preprint arXiv:2510.04206, 2025","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.846014Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:83464c6056254abb1dd848b82e011e98b0fa92c85bfa26e8621bd0509f0b10fd","observation_id":"f0dd54f8-471a-4a31-977c-461f7e5375de","resolution":{"observed_at":"2026-08-15T14:26:49.846014Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.615727Z","title":"Disttrain: Addressing model and data heterogeneity with disaggregated training for multimodal large lan- guage models","venue":null,"work_id":"cc714538-8556-476b-adce-d85f1690a944","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.849409Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:76d10b5f09878af5384474156bfb105dcb2982838a786dd8aa54c14d4b53fd3e","observation_id":"1e195668-74eb-4322-b738-7028388ef865","resolution":{"observed_at":"2026-08-15T14:26:50.619844Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2304.11277","last_updated":"2023-09-12T16:28:00Z","snapshot_observed_at":"2026-08-01T19:01:47.393546Z","submitted_at":"2023-04-21T23:52:27Z","title":"PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2304.11277","snapshot_observed_at":"2026-08-15T14:26:49.852698Z","title":"Py- torch fsdp: Experiences on scaling fully sharded data parallel.arXiv preprint arXiv:2304.11277, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.852698Z"},"links":{"cited_paper":"/paper/2304.11277","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:9cff678b5a2140ccff51b23126aeecfe1a08c06fc6782d4f0321f8b5fe97a5ea","observation_id":"ebef55f3-8373-4db4-bffa-12f0022db6d0","resolution":{"observed_at":"2026-08-15T14:26:49.852698Z","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":"2026-08-15T14:26:49.856480Z","title":"Gonzalez, Clark Bar- rett, and Ying Sheng","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.856480Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:1bdebd4c326edd5abe7af3c4185861bf27928b8f7750bbbb58400633b264ac39","observation_id":"cfbca248-5fad-47f7-bab6-7098562b483a","resolution":{"observed_at":"2026-08-15T14:26:49.856480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.594847Z","title":"Dist- Serve: Disaggregating prefill and decoding for goodput- optimized large language model serving","venue":null,"work_id":"4ef1a7c9-91aa-46f9-9753-d75bb566f096","year":2024},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.859873Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:075da49abf36cdf37e93cd05b88de12281119d70b6bc992147d9b919308ddb3d","observation_id":"b40f9a31-5406-48c1-9023-2c03fc277f36","resolution":{"observed_at":"2026-08-15T14:26:50.599746Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2504.15930","last_updated":"2025-04-22T14:19:06Z","snapshot_observed_at":"2026-08-20T01:49:19.844891Z","submitted_at":"2025-04-22T14:19:06Z","title":"StreamRL: Scalable, Heterogeneous, and Elastic RL for LLMs with Disaggregated Stream Generation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.15930","snapshot_observed_at":"2026-08-15T14:26:49.863185Z","title":"Streamrl: Scalable, het- erogeneous, and elastic rl for llms with disaggregated stream generation.arXiv preprint arXiv:2504.15930, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.863185Z"},"links":{"cited_paper":"/paper/2504.15930","citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:32cdd0b36c4a39642131d82bc7ac3cab7ad2928cb677752f5a4caa40d6ece6a5","observation_id":"5d24dedc-1a5d-462b-aecb-c1dfdfb56e90","resolution":{"observed_at":"2026-08-15T14:26:49.863185Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.582323Z","title":"Optimizing RLHF training for large language models with stage fusion","venue":null,"work_id":"9b426395-9acd-4cf0-bf5b-de61c4c06f20","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.866922Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:ef5a00c51e8cd97254b8700e9c7f3f038db0007a7468fd86e37292324074edc4","observation_id":"b8f8ec3c-5e0c-472d-ab32-fc7833d0c145","resolution":{"observed_at":"2026-08-15T14:26:50.586588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.568983Z","title":"Webarena: A realistic web environment for building autonomous agents","venue":null,"work_id":"774a7513-42bf-40c9-a5d8-9dee6bafbf1b","year":2023},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.870297Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:68deda3b002ae842d699ac27c657d15440f3731036729d130af9dbcddf97b2d1","observation_id":"cced223d-ff58-4350-9685-1c550aa04213","resolution":{"observed_at":"2026-08-15T14:26:50.573456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T14:26:49.873925Z","title":"April: Active partial rollouts in rein- forcement learning to tame long-tail generation.arXiv preprint arXiv:2509.18521, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.873925Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:8438bd70dbafa5a1c4bbc6d6dd4545d2554f3a0b53a50c5f6f3ddb300954c1ce","observation_id":"f48ab19c-4ba3-4971-969e-1cb6f8234957","resolution":{"observed_at":"2026-08-15T14:26:49.873925Z","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":"2026-08-15T14:26:49.877327Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.877327Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:b6f3cb4faa06748a3dcf6b7d361c0c573c2361f10798f71b00a176c4d30df30c","observation_id":"0623726d-579b-472e-b113-fb7895237561","resolution":{"observed_at":"2026-08-15T14:26:49.877327Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.537980Z","title":"slime: An llm post-training framework for rl 16 scaling","venue":null,"work_id":"908a6db2-3206-4786-b2fd-f12be50f9388","year":2025},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.880904Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:0ae3d0512f65da8da6f575b7c717ede236d668296b2375a6d74618137f51f452","observation_id":"e9d3c500-3dfb-4703-acc1-78e6a31f4664","resolution":{"observed_at":"2026-08-15T14:26:50.541665Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.526129Z","title":null,"venue":null,"work_id":"bab4a63d-1e56-49d0-bce5-38a9df8d833b","year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.884468Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:405c7311dcaa882072019670f10b1e4e9968d6addc136fc02488211da8138f6e","observation_id":"334d27d8-f95e-48a6-8a89-b3d4ada1463f","resolution":{"observed_at":"2026-08-15T14:26:50.529828Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.514441Z","title":"Let k be the number of batches such that their arrival time a j+k−1≤T, capped by the maximum memory capacity","venue":null,"work_id":"04ae7838-b8be-4e32-87c5-b6bed1e9779f","year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.888423Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:7bd872646b294cb20c028f10bb50ec23735c3dcaea18acda24f442a0cc8418ac","observation_id":"063689cd-de3e-4edd-9239-d6bf33e47d5b","resolution":{"observed_at":"2026-08-15T14:26:50.518241Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.503211Z","title":"The clock updates: T←T+t swap +k·tre f","venue":null,"work_id":"a9af3bcc-d18d-44f0-b851-327f30c10e20","year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.891957Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:4fdcd14f0d31ea2e6e7bf71d0cd3e2404e480431f9dcee0f9a86bce1a46126fd","observation_id":"99e22228-0dc9-4c17-bb0e-ce676300afcf","resolution":{"observed_at":"2026-08-15T14:26:50.506789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.491571Z","title":"The clock updates: T←T+t swap +k·(tact_f +tact_b)","venue":null,"work_id":"e3ec7238-61a1-46c0-ad5e-6eb680500610","year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.895488Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:f1670b3f6e61cedc8eb3e98ea87a49e1e30867025c531bfb645f42e7195a60e2","observation_id":"a13e2b58-cff4-48a8-b09d-4e63c5ec7a77","resolution":{"observed_at":"2026-08-15T14:26:50.495722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T14:26:50.478124Z","title":"Ccol evaluates to the final clock timeT","venue":null,"work_id":"ef177b9e-d0b6-4b88-a043-ab7377fca8b1","year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.899186Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:d16804502c41a3cbe2d8346d7489b90340fb17c81df49a59d080c092d995aa0a","observation_id":"e0d42c79-d469-45f7-84c7-38e0ab28d0b4","resolution":{"observed_at":"2026-08-15T14:26:50.483590Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-21T06:32:19.484+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+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":"2026-08-15T14:26:49.750519Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.750519Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:48a25998f4931064e8a3a14c4238b32f749a64edab2415e6c28da143b88673e9","observation_id":"8b0c4894-8464-4b64-932a-1a0bfb8670b7","resolution":{"observed_at":"2026-08-15T14:26:49.750519Z","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":"2026-08-15T14:26:49.731420Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling","version":1},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-15T14:26:49.731420Z"},"links":{"citing_paper":"/paper/2608.10402"},"observation_digest":"sha256:eba7a9cedefa233410b77969cab38e94d4561fd6d0547ce53833631a605d9a19","observation_id":"0fa814af-09eb-4619-8ccc-0596c3391f22","resolution":{"observed_at":"2026-08-15T14:26:49.731420Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2608.10402","last_updated":"2026-08-11T02:49:33Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-20T11:51:22.600442Z","submitted_at":"2026-08-11T02:49:33Z","title":"TideRL: Boosting Agentic RL Goodput with Readiness-Aware Scheduling"},"reference_resolution":{"displayed":61,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":28,"verified_exact":0,"verified_fuzzy":33},"total_outbound_references":61},"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":"2026-08-21T06:32:19.484+00:00","source":"crossref"},{"observed_at":"2026-08-21T06:32:16.066871+00:00","source":"retraction_watch"}],"thesis":"As of 21 August 2026, this Paper Citation Record lists 61 of 61 outbound references and 0 inbound Pith citation observations for arXiv:2608.10402."}