{"as_of":"2026-08-09T01:04:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:3806eb2b006dfbc61ef27f2f7e1822d56ad008995f9e90f59703181f02030d30","coverage":[{"denominator":30,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":30,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-04T10:09:48.298843Z","state":"measured"},{"denominator":30,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":30,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+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/2510.11711/citation-record","integrity":"/paper/2510.11711/integrity","json":"/paper/2510.11711/citation-record.json","paper":"/paper/2510.11711"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-04T10:09:44.991726Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:44.991726Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:9b81db95e4b651a1d5b6a743eb20556cd58b6dbabc58bb90fd2695f96cbd60bc","observation_id":"cac2bb8f-47e5-4294-b4fb-dac952d1f0d6","resolution":{"observed_at":"2026-08-04T10:09:44.991726Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.02141","last_updated":"2020-10-05T16:40:38Z","snapshot_observed_at":"2026-08-08T10:21:35.674654Z","submitted_at":"2020-10-05T16:40:38Z","title":"AdaLead: A simple and robust adaptive greedy search algorithm for sequence design","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2010.02141","snapshot_observed_at":"2026-08-04T10:09:45.652844Z","title":null,"venue":null,"work_id":null,"year":1987},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:45.652844Z"},"links":{"cited_paper":"/paper/2010.02141","citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:5bf819841320a48b7d404fe0e8d338b0eb02d9ee918ec28603a6b21d20f5574a","observation_id":"f69419c0-a320-4316-8307-0ab868695047","resolution":{"observed_at":"2026-08-04T10:09:45.652844Z","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":"2026-08-04T10:09:47.801346Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.801346Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:cc0ee217b42dcdb43e124aba7db3b348180cc9b035333e8c4aa7c58429625c8e","observation_id":"e761ffc6-3029-4e47-8f9a-5992ceb434f2","resolution":{"observed_at":"2026-08-04T10:09:47.801346Z","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":"2026-08-04T10:09:45.447921Z","title":"Loula, J., LeBrun, B., Du, L., Lipkin, B., Pasti, C., Grand, G., Liu, T., Emara, Y., Freedman, M., Eis- ner, J., Cotterell, R., Mansinghka, V., Lew, A","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:45.447921Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:a9f665235327c8ce8b6bb1dabfb5a0ab5b7cf11258851025f9e3790055492f1a","observation_id":"5a8d99db-e306-4989-bb8b-0157b37a985b","resolution":{"observed_at":"2026-08-04T10:09:45.447921Z","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":"2026-08-04T10:09:46.556254Z","title":"(2023) (further developed in Zhang et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:46.556254Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:fdf74b75cca4dfc396e8063d5bde824c518506ba28c31933a4c3a60317813b5c","observation_id":"4402c683-ef1f-4083-9f98-422b4c4236a0","resolution":{"observed_at":"2026-08-04T10:09:46.556254Z","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":"2026-08-04T10:09:46.727078Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:46.727078Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:a18f3cdb2d3004d49c78642f273bee719b947f3237dd996a5604df51c2da0b01","observation_id":"19cf8d06-491d-4908-8f89-544471dfa0d7","resolution":{"observed_at":"2026-08-04T10:09:46.727078Z","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":"2026-08-04T10:09:46.868730Z","title":"By setting the latent variables asx n =y tn , we can see that the diffusion models belong to the family of hierarchical latent variable models","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:46.868730Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:00859e8797b22664f1748974052c1b436df27e3eed780d2d072c0dfc33bc2eed","observation_id":"9334235e-343d-4d14-b0b1-486e39310a55","resolution":{"observed_at":"2026-08-04T10:09:46.868730Z","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":"2026-08-04T10:09:46.950762Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:46.950762Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:f47bf6f9898004259fb327c1fb0e470070d7a452871eb2ec69daf9c76b5f7543","observation_id":"3dd19927-977b-4e48-9f45-25c676ec2ea5","resolution":{"observed_at":"2026-08-04T10:09:46.950762Z","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":"2026-08-04T10:09:47.106490Z","title":"The Double Well energy is: EDW(x1, x2) =x 4 1 −6x 2 1 − 1 2 x1 + 1 2 x2","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.106490Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:cc35ee743f68ef4f12b115120f4985a65059920ddfbaa652b98cc1db980aaf0d","observation_id":"414f5831-05c1-4689-9f69-06960477a67e","resolution":{"observed_at":"2026-08-04T10:09:47.106490Z","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":"2026-08-04T10:09:47.190028Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.190028Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:5f603afadae29928a25b3f239706239fb0820b6f45befcd141ba938c433a2392","observation_id":"6bfc475d-2783-4a13-b254-820e9fd31a11","resolution":{"observed_at":"2026-08-04T10:09:47.190028Z","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":"2026-08-04T10:09:48.018880Z","title":"We generate DNA sequences of length 8, where each token is a DNA nucleotide (A, G, C, or T)","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:48.018880Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:4ba3561533f6d2d6929dcbe82c65340fc6cfa69a093a34e918bffa6be6a43eb5","observation_id":"b75be19d-67d4-4162-943e-c9376259c8f3","resolution":{"observed_at":"2026-08-04T10:09:48.018880Z","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":"2026-08-04T10:09:47.503933Z","title":"Lett 2 be the density of Student’s t-distribution with degree 2 andν i be the shift of componenti","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.503933Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:ab71a7f5d065ce4d94a4456d445ba4dea426622ba57a5b94e4b4e14d3a2225f1","observation_id":"eb80afee-7458-48dd-8faf-ee28ce1aeb1c","resolution":{"observed_at":"2026-08-04T10:09:47.503933Z","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":"2026-08-04T10:09:47.733839Z","title":"We adopt the visualisation method in Chen et al","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.733839Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:936474fcc2b356e1484db7d4c0774a404a261905c66840ed38ec00cf92e382e0","observation_id":"5c5658b7-6643-4d27-ad61-39a3306dd1ed","resolution":{"observed_at":"2026-08-04T10:09:47.733839Z","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":"2026-08-04T10:09:47.887728Z","title":"Similar to QM9, we create string representations of small molecular graphs with 6 blocks, each from a predefined set of 18 building blocks with 2 stems","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.887728Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:b4a1c7e923149181a1f63d010f5a06cb7e30ab781bf8fbc645ae493fa477abfc","observation_id":"e7b52716-e518-4f84-abf9-b7b0b41773b0","resolution":{"observed_at":"2026-08-04T10:09:47.887728Z","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":"2026-08-04T10:09:48.137633Z","title":"We generate RNA sequences of length 14, where each token is an RNA nucleotide (A, G, C, or U)","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:48.137633Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:e550e3a5317aefbcd44b2f5c1784a69bb43c354ab403dae704ea7a38f2887f5b","observation_id":"ff321923-18ab-4a2b-a0f5-c570dfc28413","resolution":{"observed_at":"2026-08-04T10:09:48.137633Z","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":"2026-08-04T10:09:48.219574Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:48.219574Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:71f6f24770b710bbe98cea20e5fe2ae4c910b2680a0a70f6536053adfd4f7134","observation_id":"a6bcafbe-95e2-4e25-94d4-f6114e2ca508","resolution":{"observed_at":"2026-08-04T10:09:48.219574Z","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":"2026-08-04T10:09:45.081740Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:45.081740Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:52766534a8beeacc4284a4edcdf53408559963d5648d19409eefe4d032262d3b","observation_id":"edb9508c-69c7-462b-b391-0d90c82e5153","resolution":{"observed_at":"2026-08-04T10:09:45.081740Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2502.06601","last_updated":"2025-02-10T16:00:48Z","snapshot_observed_at":"2026-08-08T14:52:49.131015Z","submitted_at":"2025-02-10T16:00:48Z","title":"Amortized In-Context Bayesian Posterior Estimation","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2502.06601","snapshot_observed_at":"2026-08-04T10:09:45.545917Z","title":null,"venue":null,"work_id":null,"year":1955},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":401,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:45.545917Z"},"links":{"cited_paper":"/paper/2502.06601","citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:4bf45f40ec18ac5de63838c55fc1ba5f2395195eb78ff7f540a6b1bff1b65b33","observation_id":"eb01820d-1f92-4021-9582-b356fce9f443","resolution":{"observed_at":"2026-08-04T10:09:45.545917Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2306.03081","last_updated":"2023-11-26T21:40:00Z","snapshot_observed_at":"2026-08-06T00:28:41.089802Z","submitted_at":"2023-06-05T17:55:05Z","title":"Sequential Monte Carlo Steering of Large Language Models using Probabilistic Programs","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2306.03081","snapshot_observed_at":"2026-08-04T10:09:45.350776Z","title":"K., Zhi-Xuan, T., Grand, G., and Mans- inghka, V","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":470,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:45.350776Z"},"links":{"cited_paper":"/paper/2306.03081","citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:1bf0b1f44937821d5798a424a9d3273b10002a7a9b815b64d7d66b473b219554","observation_id":"bad64ee8-a4d0-4347-af1e-23b28fea839a","resolution":{"observed_at":"2026-08-04T10:09:45.350776Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2201.12324","last_updated":"2022-01-28T18:43:41Z","snapshot_observed_at":"2026-08-09T00:29:12.885708Z","submitted_at":"2022-01-28T18:43:41Z","title":"Optimal Transport Tools (OTT): A JAX Toolbox for all things Wasserstein","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2201.12324","snapshot_observed_at":"2026-08-04T10:09:45.264711Z","title":null,"venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":812,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:45.264711Z"},"links":{"cited_paper":"/paper/2201.12324","citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:b7d59a68f8c6b39ef8a39b4a60a30a08ccaedb441bee08075b0083615d17ab92","observation_id":"c93abe8f-a1bc-4066-8ef4-56b945bf12c6","resolution":{"observed_at":"2026-08-04T10:09:45.264711Z","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":"2026-08-04T10:09:47.027671Z","title":"•ManyW ell(d∈[32,64]) (N¨ usken and Richter, 2021; Midgley et al.,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2003,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.027671Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:ee4a385b1a2fa380d1f1717255389032bb7de158f07432f694c99271b1183a04","observation_id":"c4a33f38-62f2-4805-a1bb-228c8fe5ce60","resolution":{"observed_at":"2026-08-04T10:09:47.027671Z","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":"2026-08-04T10:09:47.588836Z","title":"Note that EUBO, MMD, and Sinkhorn distance calculations require unbiased samples from the target distribution","venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2012,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.588836Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:da94c9c037a50514d82a4839d3e4db7452513fe8f2f14bbac664d631dd2c4ae5","observation_id":"968ad3ec-3587-4f03-9aea-e42ed7486379","resolution":{"observed_at":"2026-08-04T10:09:47.588836Z","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":"2026-08-04T10:09:45.816812Z","title":null,"venue":null,"work_id":null,"year":1992},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2013,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:45.816812Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:d0733a0180627a1b1f1717beb3e81e46cace299465f1f9d3477e897a404387ea","observation_id":"b2eebe29-527d-409c-8594-3351a319ef28","resolution":{"observed_at":"2026-08-04T10:09:45.816812Z","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":"2026-08-04T10:09:48.298843Z","title":"We do not apply learning rate scheduling","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2015,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:48.298843Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:80311f61835027549ef980be10536dfad40aa65e90786c2b1b2b2aff77ff22c8","observation_id":"0041fb9c-af1b-40f1-a557-175653971b44","resolution":{"observed_at":"2026-08-04T10:09:48.298843Z","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":"2026-08-04T10:09:46.268400Z","title":null,"venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:46.268400Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:dfbc16c69a0a79827544b7927e848497d8cdee47bdcb4c58a88a289904961915","observation_id":"bcf05785-6d33-4315-ba02-66abbcf48e75","resolution":{"observed_at":"2026-08-04T10:09:46.268400Z","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":"2026-08-04T10:09:45.961462Z","title":"Generative flow networks (GFlowNets; Bengio et al., 2021,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:45.961462Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:3d434e04da72a5d22975c02fd8b3cc2e64e82015ebea426e9d703db8a39339d5","observation_id":"c9f5f6c5-3917-4ae6-8586-8159e5468e43","resolution":{"observed_at":"2026-08-04T10:09:45.961462Z","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":"2026-08-04T10:09:47.649584Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.649584Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:745f77172a5b941f4dc30f9c8b0745968ce33d10e2b31792f6b1daff5a3a76fc","observation_id":"ab44cb14-4ea9-429f-9794-5c95bf16fea6","resolution":{"observed_at":"2026-08-04T10:09:47.649584Z","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":"2026-08-04T10:09:46.078361Z","title":"GFlowNets bridge the gap between maximum entropy reinforcement learning (MaxEnt RL) algorithms (Haarnoja et al., 2017, 2018; Nachum et al.,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:46.078361Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:cbf65393a564585ca6cc2023f48421c12601aa54d3f6e5feea724e6cd3c758dd","observation_id":"c1d75544-befb-451c-8181-59900bef40f9","resolution":{"observed_at":"2026-08-04T10:09:46.078361Z","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":"2026-08-04T10:09:46.435321Z","title":"These approaches provide valuable off-policy training examples that improve training efficiency and/or mode coverage","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:46.435321Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:aa448b52294876ffa4e9260c99e9c32653ffd9658eaaeabc97c20ba0937cba51","observation_id":"1f1fa4fe-1ccb-494c-909f-236dac2adcd5","resolution":{"observed_at":"2026-08-04T10:09:46.435321Z","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":"2026-08-04T10:09:47.370465Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling","version":3},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-04T10:09:47.370465Z"},"links":{"citing_paper":"/paper/2510.11711"},"observation_digest":"sha256:7f2fee6af6d0b201273f7cb611882d7c2ae4870b0960eae1c195a73200a556d1","observation_id":"becba1ed-d615-48f9-9162-df26a30c19e9","resolution":{"observed_at":"2026-08-04T10:09:47.370465Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2510.11711","last_updated":"2026-07-31T10:08:26Z","latest_version":3,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T00:29:43.749749Z","submitted_at":"2025-10-13T17:59:11Z","title":"Reinforced sequential Monte Carlo for amortised sampling"},"reference_resolution":{"displayed":30,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":30,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":30},"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":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 30 of 30 outbound references and 0 inbound Pith citation observations for arXiv:2510.11711."}