{"as_of":"2026-08-18T18:23:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:858355bded5b8cb3bc667433449fd479f36cf6a9445337b7ea8f7f4401cd58b4","coverage":[{"denominator":12,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":12,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-16T11:44:34.297954Z","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":"2026-08-18T06:34:40.430872+00:00","state":"measured"},{"denominator":2,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":2,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T09:45:42.783390Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"arxiv_reference","source_observed_at":"2026-05-19T22:12:50.769368Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2504.14889","snapshot_observed_at":"2026-08-03T09:45:42.783390Z","title":"Latent bayesian optimization via autoregressive normalizing flows.arXiv preprint arXiv:2504.14889,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2602.11171","last_updated":"2026-05-28T09:44:38Z","snapshot_observed_at":"2026-08-03T09:45:40.462025Z","submitted_at":"2026-01-19T08:48:03Z","title":"A Language-Guided Bayesian Optimization for Efficient LoRA Hyperparameter Search","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T09:45:42.783390Z"},"links":{"cited_paper":"/paper/2504.14889","citing_paper":"/paper/2602.11171"},"observation_digest":"sha256:51ddf4b75f4f88ea97233b437da594313d83b560066183e9e2561274601f1094","observation_id":"61b69e70-789f-428b-930c-667b30d21aa9","resolution":{"observed_at":"2026-08-03T09:45:42.783390Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"cited_work":{"arxiv_id":"2504.14889","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2504.14889","snapshot_observed_at":"2026-06-05T21:23:00.469572Z","title":"Latent bayesian optimization via autoregressive normalizing flows","venue":null,"work_id":"b480e67b-84c3-4e16-8925-797f441cd672","year":2025},"citing_paper":{"arxiv_id":"2605.17546","last_updated":"2026-05-17T17:00:39Z","snapshot_observed_at":"2026-08-17T11:57:59.834623Z","submitted_at":"2026-05-17T17:00:39Z","title":"Accelerating Redshift-Conditioned Galaxy Image Synthesis with One-step Generative Modeling","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-05-19T22:09:58.701479Z"},"links":{"cited_paper":"/paper/2504.14889","citing_paper":"/paper/2605.17546"},"observation_digest":"sha256:f4785025a42da1bea55b0d4de71b3d5de55afd82ce446d4c2c1555a0d92e9738","observation_id":"d1a4ac89-f8d9-4fd4-8873-314191cb5635","resolution":{"observed_at":"2026-05-19T22:12:50.775541Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2504.14889/citation-record","integrity":"/paper/2504.14889/integrity","json":"/paper/2504.14889/citation-record.json","paper":"/paper/2504.14889"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-16T11:44:34.472388Z","title":"Light sky blue areas indicate regions with lower density compared to the darker regions","venue":null,"work_id":"dc16b271-bc0e-450d-a759-4c8fafe72a5d","year":2025},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.266211Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:b4670587e07af05b904eb835aea167208c106e172d0445d6d067665f2a5aa9af","observation_id":"d402ca05-1071-44a7-9512-54fa9f075323","resolution":{"observed_at":"2026-08-16T11:44:34.477988Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T11:44:34.437334Z","title":null,"venue":null,"work_id":"c17d18d8-e20a-4546-80e2-619866206ac7","year":2019},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.276826Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:c6d7063483c61ef113d17d60c1dffb8553c22aa9c6760d0ecbdb79ae2b3b718d","observation_id":"46955813-709d-4b32-abee-30adf7373a83","resolution":{"observed_at":"2026-08-16T11:44:34.443388Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T11:44:34.507180Z","title":"The table presents scores and standard deviations across 6 evaluation metrics, with each score representing the mean of 5 independent runs","venue":null,"work_id":"8d7066ad-f91e-4d99-a91d-3c3758fb5bbb","year":2025},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.255445Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:0db671c87718044fcdb6d76d092d36f9a5000b5dc5920b15df8e5fc2d4c92bd6","observation_id":"4f7cc546-fa4e-4d58-ae39-79ad8bb164fe","resolution":{"observed_at":"2026-08-16T11:44:34.513071Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T11:44:34.455161Z","title":null,"venue":null,"work_id":"c1e8ab5e-cee1-4f91-9205-8f840c829259","year":2025},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.271586Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:368f66a93129328d43f9804352ec7615026db11dfcaee45a6940d921b3dfee0c","observation_id":"df8dc39e-db44-4abb-b971-b38b7370cf85","resolution":{"observed_at":"2026-08-16T11:44:34.461226Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T11:44:34.420814Z","title":"From the table, our SeqFlow model achieves better perfor- mance with fewer parameters compared to the baseline model","venue":null,"work_id":"e59bd4d2-7838-423a-8f7b-979ee4784276","year":2025},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.281632Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:27e0d4f8346c67fce2f5630fa8de999bb6910c06fa37b436d245c517c539c11c","observation_id":"e995bec5-ae16-4ef8-b8bc-1f010574f452","resolution":{"observed_at":"2026-08-16T11:44:34.426376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T11:44:34.403891Z","title":"Both the oracle budget and the number of initial data were set to 10,000","venue":null,"work_id":"d92a040e-f135-420a-8c30-9e3e0aa5c3bb","year":2025},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.287282Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:22f589c7c5c4dc7c80e40c5c19ecd1e347e5c0a5b9ccd0dc06dabfc39a3f0f3e","observation_id":"284e5eb7-7714-4192-a67b-5054dc19756f","resolution":{"observed_at":"2026-08-16T11:44:34.408897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T11:44:34.386268Z","title":"Each task’s performance is averaged over five trials","venue":null,"work_id":"2361bd19-37f5-4e65-a34c-6a237eb9b66d","year":2000},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.292755Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:5479dab6365122889f3294de10a4d35ce2c419b0e8ec4d73cb7ca7b8b6a27838","observation_id":"7ec4c647-bd87-45a2-a14f-1c9a4239517e","resolution":{"observed_at":"2026-08-16T11:44:34.392131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-16T11:44:34.488694Z","title":"Figures 8, 9, and 10 display the results for the (100, 500), (10,000, 10,000), and (10,000, 70,000) oracle settings, respectively","venue":null,"work_id":"d670c5f5-0776-4e52-8238-96a28497a7ff","year":2024},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":500,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.260553Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:350ca83658cd3b13a1b481ecc4e01c0a5a5ac752214e84cf7a101ce3044688bb","observation_id":"763182cc-c75e-4f63-843e-4aac94658756","resolution":{"observed_at":"2026-08-16T11:44:34.495202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2406.04739","last_updated":"2024-11-04T10:02:09Z","snapshot_observed_at":"2026-08-17T17:42:13.804208Z","submitted_at":"2024-06-07T08:39:40Z","title":"A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2406.04739","snapshot_observed_at":"2026-08-16T11:44:34.238541Z","title":"A survey and benchmark of high-dimensional Bayesian optimization of discrete sequences","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.238541Z"},"links":{"cited_paper":"/paper/2406.04739","citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:0f9104cff725cef4cf37c6875d853e6d1dea7c1e53828eb7a7fca6a49f4cb9cd","observation_id":"09ff8e28-c54a-434c-ada1-ff3818de04cf","resolution":{"observed_at":"2026-08-16T11:44:34.238541Z","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":"2026-08-16T11:44:34.524521Z","title":"Variational inference with normalizing flows","venue":null,"work_id":"a267a7e4-de41-4bb7-93a7-8b6b1c2e3258","year":2025},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.250165Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:5720e66d76f0464b52d782a941dc3df8c9113232652964728f4bcb5dc97d06a2","observation_id":"bbab8034-f17d-45d4-a311-44224a0b41b4","resolution":{"observed_at":"2026-08-16T11:44:34.529405Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.03609","last_updated":"2021-11-01T11:53:58Z","snapshot_observed_at":"2026-08-16T18:19:06.114218Z","submitted_at":"2021-06-07T13:35:47Z","title":"High-Dimensional Bayesian Optimisation with Variational Autoencoders and Deep Metric Learning","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.03609","snapshot_observed_at":"2026-08-16T11:44:34.244774Z","title":"High-dimensional Bayesian optimisation with variational autoencoders and deep metric learning.arXiv:2106.03609,","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.244774Z"},"links":{"cited_paper":"/paper/2106.03609","citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:d04e4ad40c34b0c459904d7bf43c346ac8441ab87e2f7f7666f41afa3ad40f80","observation_id":"46d03996-8e96-4da0-87ea-f863ef8609ed","resolution":{"observed_at":"2026-08-16T11:44:34.244774Z","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":"2026-08-16T11:44:34.366620Z","title":"ver et al.,","venue":null,"work_id":"579a15a5-2bc3-4976-82f6-069a499bd338","year":2025},"citing_paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows","version":1},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-16T11:44:34.297954Z"},"links":{"citing_paper":"/paper/2504.14889"},"observation_digest":"sha256:79cf8535a1b27f45857b375d75da6e1b468fe821a61629463830a1252175b015","observation_id":"912d4cf1-ddac-49a9-972d-6eaf8922b0f7","resolution":{"observed_at":"2026-08-16T11:44:34.374287Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2504.14889","last_updated":"2025-04-21T06:36:09Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T22:14:33.985727Z","submitted_at":"2025-04-21T06:36:09Z","title":"Latent Bayesian Optimization via Autoregressive Normalizing Flows"},"reference_resolution":{"displayed":12,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":4,"verified_exact":0,"verified_fuzzy":8},"total_outbound_references":12},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 12 of 12 outbound references and 2 inbound Pith citation observations for arXiv:2504.14889."}