{"as_of":"2026-08-04T19:55:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:b7ce55a5bf61737106df1ffb2b7acf853d51b515ed6370fcbb6280ace14586d4","coverage":[{"denominator":14,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":14,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-02T11:20:25.848158Z","state":"measured"},{"denominator":14,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":14,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-04T06:34:03.388597+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.16073/citation-record","integrity":"/paper/2606.16073/integrity","json":"/paper/2606.16073/citation-record.json","paper":"/paper/2606.16073"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-02T11:20:25.111462Z","title":"At each iteration, the algorithm alternates between forward (on-policy) and backward (off-policy) updates","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:25.111462Z"},"links":{"citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:bb5b8e6abe3e64c140c4fff039511c4ed3d607a744a40858193e0a42b2286708","observation_id":"13b9b79e-2311-4450-a467-8f472b970d06","resolution":{"observed_at":"2026-08-02T11:20:25.111462Z","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":"2026-08-02T11:20:25.428397Z","title":"Environment↓Parameter→lr𝜌 𝛾 𝑁 max grad clip GMM9 (𝑑=40)10 −4 100 10−1 102 10−3 ManyWell (𝑑=40)10 −5 10−1 10−2 102 10−5 Digits (𝑑=196)10 −4 100 10−1 5×10 1 10−3 A.6","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:25.428397Z"},"links":{"citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:8b20344cc3686c643c7b3302048e483d0816d52fdf925978199f0a5b8f417d2a","observation_id":"030f3a7f-d22d-4464-b8d6-00031c359595","resolution":{"observed_at":"2026-08-02T11:20:25.428397Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.00671","last_updated":"2025-07-01T11:12:34Z","snapshot_observed_at":"2026-07-06T21:50:26.258056Z","submitted_at":"2025-07-01T11:12:34Z","title":"Harnessing the Power of Reinforcement Learning for Adaptive MCMC","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.00671","snapshot_observed_at":"2026-08-02T11:20:24.613981Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:24.613981Z"},"links":{"cited_paper":"/paper/2507.00671","citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:304c95ea3c3c634bac9f4b6c6bf584db835b58976d9a3bd25eb3d52965a428d2","observation_id":"f3c185a4-7663-4ea0-82a3-8a697854852a","resolution":{"observed_at":"2026-08-02T11:20:24.613981Z","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":"2026-08-02T11:20:25.541351Z","title":"LetH𝑘 be the RKHS associated with a positive definite kernel𝑘","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:25.541351Z"},"links":{"citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:868a569ef59d6ab21eb5f1a3b8b944be9855dc7706c0e7e821a0b819a2eb71e7","observation_id":"cab8a942-8e5b-4a56-b41b-9147efb99d3e","resolution":{"observed_at":"2026-08-02T11:20:25.541351Z","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":"2026-08-02T11:20:25.713140Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:25.713140Z"},"links":{"citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:425970a21445e6272ad3d4041b4525cd4e05a13866879b18cd8f9a403fa5a9bc","observation_id":"45f3a1d6-724a-48aa-b801-2f3ea5dafe67","resolution":{"observed_at":"2026-08-02T11:20:25.713140Z","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":"2026-08-02T11:20:25.848158Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:25.848158Z"},"links":{"citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:6257d9f6351d3a816fbfdd5523c28832f9f0aa8345dd72c5caf76ce16173d04c","observation_id":"6a3ae19d-aba5-43fd-b7dc-127494cb8734","resolution":{"observed_at":"2026-08-02T11:20:25.848158Z","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":"2026-08-02T11:20:25.279615Z","title":null,"venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":128,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:25.279615Z"},"links":{"citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:b15f38302fdfd481b571438a209d1508baa771fa581d796659286481b951becd","observation_id":"53bcfe29-f77f-48bb-b288-5751a7dc5207","resolution":{"observed_at":"2026-08-02T11:20:25.279615Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2510.22688","last_updated":"2026-06-20T16:57:31Z","snapshot_observed_at":"2026-08-04T08:04:20.528000Z","submitted_at":"2025-10-26T14:20:44Z","title":"Stopping Rules for Monte Carlo Methods: A Review","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2510.22688","snapshot_observed_at":"2026-08-02T11:20:24.699027Z","title":"and Kawai, R","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":2011,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:24.699027Z"},"links":{"cited_paper":"/paper/2510.22688","citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:a4745d4d3491322d7edfdc2f0992dbe56f856e611c28f331bfc83bc4d2388d7e","observation_id":"d4bcbea4-5b6f-479e-8adf-17fa3a2f7188","resolution":{"observed_at":"2026-08-02T11:20:24.699027Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.01541","last_updated":"2025-06-02T11:07:27Z","snapshot_observed_at":"2026-07-06T21:34:53.033109Z","submitted_at":"2025-06-02T11:07:27Z","title":"Adaptive Destruction Processes for Diffusion Samplers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.01541","snapshot_observed_at":"2026-08-02T11:20:24.399466Z","title":"Adaptive destruction processes for diffusion samplers","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:24.399466Z"},"links":{"cited_paper":"/paper/2506.01541","citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:5b1a76201aa3c9d4faf780c607ef0f1630b05d56e60c7196c9e2b14166157240","observation_id":"25cfdfbd-2c3b-4389-8dcb-c52b414ecb69","resolution":{"observed_at":"2026-08-02T11:20:24.399466Z","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":"2026-08-02T11:20:24.843688Z","title":"Experimental details A.1","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:24.843688Z"},"links":{"citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:1d6bdd20023a8ad31b377a01c5bb0a4d160283fb0141897a06940727635b7efa","observation_id":"494902e1-d5aa-48d2-9349-0e8a3af8ce5d","resolution":{"observed_at":"2026-08-02T11:20:24.843688Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1410.8516","last_updated":"2015-04-10T12:27:56Z","snapshot_observed_at":"2026-07-06T03:59:05.142685Z","submitted_at":"2014-10-30T19:44:20Z","title":"NICE: Non-linear Independent Components Estimation","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1410.8516","snapshot_observed_at":"2026-08-02T11:20:24.263466Z","title":"NICE: Non-linear independent components estimation.arXiv preprint arXiv:1410.8516,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:24.263466Z"},"links":{"cited_paper":"/paper/1410.8516","citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:ae3885ef19cdb18d74d31baacc005a1cfa2c48867aefe146769454b907c8ac65","observation_id":"8b219690-cf30-4f74-85a7-9432e6222773","resolution":{"observed_at":"2026-08-02T11:20:24.263466Z","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":"2026-08-02T11:20:24.992555Z","title":"The target distribution is a continuous density over R196, obtained by training an invertible flow on 14×14 MNIST images","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:24.992555Z"},"links":{"citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:a14e07d144c9849de5ba20bfe134e4ffeb4ccf1cbc6e95f15a84f760afd69019","observation_id":"7e291451-742e-494b-8744-9a81b6fbebd7","resolution":{"observed_at":"2026-08-02T11:20:24.992555Z","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":"2026-08-02T11:20:24.512414Z","title":"Learning shortest paths with generative flow networks","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:24.512414Z"},"links":{"citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:a4d895c410a207b3f4e38203a7954ed85cfba15f931ec5bbb9bb98f06f723964","observation_id":"eea278b8-dbd6-4fe2-a455-c959caf82de3","resolution":{"observed_at":"2026-08-02T11:20:24.512414Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2307.01422","last_updated":"2023-07-04T01:28:02Z","snapshot_observed_at":"2026-07-06T15:49:58.951341Z","submitted_at":"2023-07-04T01:28:02Z","title":"Generative Flow Networks: a Markov Chain Perspective","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.01422","snapshot_observed_at":"2026-08-02T11:20:24.186587Z","title":"and Bengio, Y","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels","version":2},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-02T11:20:24.186587Z"},"links":{"cited_paper":"/paper/2307.01422","citing_paper":"/paper/2606.16073"},"observation_digest":"sha256:97303ffe748b88b5d66237d047f0ca7d48be0d85119ef5d8e9daa20d0dc76efc","observation_id":"b339838f-5448-41a2-b546-3ce924689008","resolution":{"observed_at":"2026-08-02T11:20:24.186587Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.16073","last_updated":"2026-07-17T08:20:07Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-02T11:20:23.020830Z","submitted_at":"2026-06-15T00:18:21Z","title":"Stop the Sampler! Classifier-Based Adaptive Stopping for Sampling Kernels"},"reference_resolution":{"displayed":14,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":14,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":14},"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":"2026-08-04T06:34:03.388597+00:00","source":"crossref"},{"observed_at":"2026-08-04T06:33:57.428241+00:00","source":"retraction_watch"}],"thesis":"As of 4 August 2026, this Paper Citation Record lists 14 of 14 outbound references and 0 inbound Pith citation observations for arXiv:2606.16073."}