{"as_of":"2026-08-07T23:08:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cd2e543d3a0544058684ae89f2c0eb1252d41dd29ae203129bc6b7ff7626b1c5","coverage":[{"denominator":194,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":100,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:45:04.799611Z","state":"measured"},{"denominator":102,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":102,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+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":"2026-06-30T14:22:39.302334Z","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":"2026-06-30T14:24:44.901120Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"cited_work":{"arxiv_id":"2506.04553","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.04553","snapshot_observed_at":"2026-06-30T14:24:44.901120Z","title":"Unsupervised machine learning for scientific discovery: Workflow and best practices.arXiv:2506.04553","venue":null,"work_id":"56ebbb33-0d30-4ff2-9aa2-16a10b0ab21d","year":2025},"citing_paper":{"arxiv_id":"2604.03488","last_updated":"2026-04-09T19:27:44Z","snapshot_observed_at":"2026-08-02T08:39:44.952222Z","submitted_at":"2026-04-03T22:27:27Z","title":"Inference for Clustering: Conformal Sets for Cluster Labels","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-05-13T18:02:05.474011Z"},"links":{"cited_paper":"/paper/2506.04553","citing_paper":"/paper/2604.03488"},"observation_digest":"sha256:453853f9f5a74079ab64ecc423d1e95e2b71da921069d1d30d2e90b7b7acf27a","observation_id":"c5895b59-4652-43eb-90c4-2f932bb5d97f","resolution":{"observed_at":"2026-05-13T18:03:04.323448Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"cited_work":{"arxiv_id":"2506.04553","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2506.04553","snapshot_observed_at":"2026-06-30T14:24:44.901120Z","title":"Unsupervised machine learning for scientific discovery: Workflow and best practices.arXiv:2506.04553","venue":null,"work_id":"56ebbb33-0d30-4ff2-9aa2-16a10b0ab21d","year":2025},"citing_paper":{"arxiv_id":"2605.24244","last_updated":"2026-05-22T21:45:12Z","snapshot_observed_at":"2026-07-06T23:34:18.555542Z","submitted_at":"2026-05-22T21:45:12Z","title":"MEDAL: Manifold Embedding Distillation via Autoencoder Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-30T14:22:39.302334Z"},"links":{"cited_paper":"/paper/2506.04553","citing_paper":"/paper/2605.24244"},"observation_digest":"sha256:d10d8887dd7e2f4d962c73dca97342fe3737daaa55e3dbddca779b39e9bcb3fe","observation_id":"cff51514-f405-4ea1-a6cc-64f87cfc0783","resolution":{"observed_at":"2026-06-30T14:24:44.902810Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2506.04553/citation-record","integrity":"/paper/2506.04553/integrity","json":"/paper/2506.04553/citation-record.json","paper":"/paper/2506.04553"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:45:04.513522Z","title":"Alam and N","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.513522Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:be1e2b6af9aadc3029d48f050651615ee0a7e117e6cfa206f23356e94650017f","observation_id":"8931f555-f140-4ab6-bf0c-39902db12f0d","resolution":{"observed_at":"2026-08-07T10:45:04.513522Z","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":"2026-08-07T10:45:04.516996Z","title":"Allen, L","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.516996Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:57f7f51fd92c4fbd3872bd86df07d39abbb10c79c10a5b02436d8a66cc761f49","observation_id":"90102514-b4fd-496f-8b56-f77453e22232","resolution":{"observed_at":"2026-08-07T10:45:04.516996Z","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":"2026-08-07T10:45:04.520337Z","title":null,"venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.520337Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:71a2f6b701c25b385d327cb4cd45051b2bb9adc926bd8f9891b84e51b960ecd8","observation_id":"b84d1b78-65fb-4547-bcf3-3d2d5dbea617","resolution":{"observed_at":"2026-08-07T10:45:04.520337Z","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":"2026-08-07T10:45:04.523349Z","title":"Anders, C","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.523349Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:51a8a72cadab3bc7446999076f6a98e61dea943bcd370f8fd975c89a78b35a05","observation_id":"dcfe1b8e-1901-48b4-b966-2966cf2e642a","resolution":{"observed_at":"2026-08-07T10:45:04.523349Z","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":"2026-08-07T10:45:04.526320Z","title":"Anders, P","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.526320Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:fecf85bc2f1498dd8d5bb0db4d1264e7ce50cb41b2320fa8d8130f386005bc1d","observation_id":"38532eb3-556d-4d6a-8547-81881304bafd","resolution":{"observed_at":"2026-08-07T10:45:04.526320Z","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":"2026-08-07T10:45:04.529352Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.529352Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:c499a4f343a5eb5797fe8cbfd5321c58bd214df5855a937ec50202e9d56ea0cc","observation_id":"45f30b75-6cfe-44f5-9e36-2b534ef9baa4","resolution":{"observed_at":"2026-08-07T10:45:04.529352Z","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":"2026-08-07T10:45:04.532809Z","title":"Armstrong, G","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.532809Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:7c891634c3823e10782f1455464bb94312964b9f35e680ccbe5373d4c3a66732","observation_id":"a5e2cb09-1507-48ce-b2b6-73b4802d99a1","resolution":{"observed_at":"2026-08-07T10:45:04.532809Z","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":"2026-08-07T10:45:04.535451Z","title":"Arnold, L","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.535451Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:2a6c871cdec73edde3db437bec8eab42b200f382950c0026704dd3bb62a12ed5","observation_id":"fc336b91-b4b3-4f32-8e77-d6fe8759586b","resolution":{"observed_at":"2026-08-07T10:45:04.535451Z","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":"2026-08-07T10:45:04.538346Z","title":"Arthur and S","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.538346Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:93a018058cadfbab03952e746b4d4dbad30c07413ae709179f0cd5d306ae76f0","observation_id":"48188800-40be-4b95-aa84-1ce924212fa6","resolution":{"observed_at":"2026-08-07T10:45:04.538346Z","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":"2026-08-07T10:45:04.541266Z","title":"Ashtari, R","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.541266Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:73db6d5a750de01a6ac4fd9c2d4a53b2382194734c00dedc4022c09dfafd65f1","observation_id":"144765bc-1972-421a-9994-27e7e87574bd","resolution":{"observed_at":"2026-08-07T10:45:04.541266Z","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":"2026-08-07T10:45:04.544634Z","title":"Baeza, J","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.544634Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:ae18f0e08a7715ecb566c9c39fe0430276a3abf5b57ad00c4c6ef961ba41e84e","observation_id":"c11ade71-b9eb-4777-b20d-16ed69213527","resolution":{"observed_at":"2026-08-07T10:45:04.544634Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1611.07526","last_updated":"2016-11-22T21:00:02Z","snapshot_observed_at":"2026-07-06T05:19:45.842124Z","submitted_at":"2016-11-22T21:00:02Z","title":"The weirdest SDSS galaxies: results from an outlier detection algorithm","version":1},"cited_work":{"arxiv_id":"1611.07526","doi":null,"metadata_source":"pith","pith_arxiv_id":"1611.07526","snapshot_observed_at":"2026-08-07T10:45:05.282371Z","title":"The weirdest SDSS galaxies: results from an outlier detection algorithm","venue":"astro-ph.GA","work_id":"1dd7ae41-a42b-4160-ba5f-593f546b32e8","year":2016},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.547496Z"},"links":{"cited_paper":"/paper/1611.07526","citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:7f733d6584063249c8c67780c81ac9281dedc842ec6ecc6a89293f4b85b42d14","observation_id":"1ad56a24-5de2-435f-ad13-169c39397307","resolution":{"observed_at":"2026-08-07T10:45:05.285898Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:45:04.550693Z","title":null,"venue":null,"work_id":null,"year":1991},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.550693Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:e72e7f77792127dce39f0533511f2ad2772fe41fc6f606507b445991936933b9","observation_id":"050a80b9-e63a-4acb-8ac5-a3b4eb38a746","resolution":{"observed_at":"2026-08-07T10:45:04.550693Z","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":"2026-08-07T10:45:04.553688Z","title":"Belokurov and A","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.553688Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:ea27c15b638e1cb1596cabd4293a28e26d1baa50e227ffc77ba05a21d19ec2d8","observation_id":"95aafe93-4431-4424-89fa-a467bad478a5","resolution":{"observed_at":"2026-08-07T10:45:04.553688Z","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":"2026-08-07T10:45:04.556251Z","title":"Belouafa, F","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.556251Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:9c4c47dec311fdb7b2cbc1692e9fb777c19aa0263487753b2543c947085752d4","observation_id":"8781c4ff-2785-434b-ae67-3ee2cf648bb0","resolution":{"observed_at":"2026-08-07T10:45:04.556251Z","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":"2026-08-07T10:45:04.559056Z","title":"Ben-Hur, A","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.559056Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:54b73d1ca282553764c10bf54f3773c993d40b58075a75437d5fe38f2174a6d0","observation_id":"3984f4fb-d57c-4866-bd71-5f6d00350bd0","resolution":{"observed_at":"2026-08-07T10:45:04.559056Z","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":"2026-08-07T10:45:04.561720Z","title":null,"venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.561720Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:b1d8ccd4d54306dc3f6b1a57dc8e9e6efc580c184e5b608b76882233c649b993","observation_id":"4246b97d-8113-4cf0-8fa3-03d0f8013344","resolution":{"observed_at":"2026-08-07T10:45:04.561720Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.11429","last_updated":"2024-09-13T18:05:05Z","snapshot_observed_at":"2026-07-06T19:17:02.745056Z","submitted_at":"2024-09-13T18:05:05Z","title":"Searching for chemo-kinematic structures in the Milky Way halo with deep clustering algorithms","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.11429","snapshot_observed_at":"2026-08-07T10:45:04.564518Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.564518Z"},"links":{"cited_paper":"/paper/2409.11429","citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:f060fe1fbf1c2f8c4ee234e4bec37ea7143a54c90c027a33e20c4339c0cb8c5b","observation_id":"b34e9f7f-5b0e-4fd9-a16e-6d04634d5e38","resolution":{"observed_at":"2026-08-07T10:45:04.564518Z","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":"2026-08-07T10:45:04.568150Z","title":"Bialopetravičius and D","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.568150Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:84019399b8f5c16a91fc2e6c8b6f6a15dcc89c6330241dc5075203658efdaa6b","observation_id":"bc1ba512-6c57-4fae-a5cc-ea6c17d55aaa","resolution":{"observed_at":"2026-08-07T10:45:04.568150Z","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":"2026-08-07T10:45:04.571136Z","title":"Biswas, M","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.571136Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:9816f26eaea1a32be17d005997bc9146b67c237c6e9eec2d128f153c1a4456e1","observation_id":"abbc7fec-4196-483f-9a3e-a1bfe2c8e8d9","resolution":{"observed_at":"2026-08-07T10:45:04.571136Z","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":"2026-08-07T10:45:04.573909Z","title":"Bousquet and A","venue":null,"work_id":null,"year":2002},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.573909Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:c47b9b6164d0109e5e6e08b2da3bd63c9782437a53a49fcfa93a8fbbf6bf6475","observation_id":"87c54d51-68d2-4681-a5ed-f8265c6ec340","resolution":{"observed_at":"2026-08-07T10:45:04.573909Z","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":"2026-08-07T10:45:04.576647Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.576647Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:a4d56c3cf9430a50b7c5df380fa78d82ff0cce6c1dd0f4c86a596ab3dad4de7e","observation_id":"ace63211-afd4-474e-91cf-d5521ce28f33","resolution":{"observed_at":"2026-08-07T10:45:04.576647Z","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":"2026-08-07T10:45:04.579444Z","title":"Bovy, H.-W","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.579444Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:ad8a13e2ea5bfce212a2f1641d41d7a41083eee4a685e4d215106aaf95cd1bd3","observation_id":"3181a17b-ab9c-42ff-a541-9f939da05e4c","resolution":{"observed_at":"2026-08-07T10:45:04.579444Z","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":"2026-08-07T10:45:04.582010Z","title":"Bravo-Merodio, J","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.582010Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:e9f5c174fa88d87bed599faf11bbbf701d32b372dff69a15e1c5fd11c0240f62","observation_id":"2db4427e-091b-42fe-a7cc-ccc511240540","resolution":{"observed_at":"2026-08-07T10:45:04.582010Z","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":"2026-08-07T10:45:04.584746Z","title":"Bresciani and M","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.584746Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:d64f937641094c5faaa0e0eb04476d4b38201cb33c02e7e0a5f522dda21c1e95","observation_id":"bde08926-937b-4f43-9150-9d9e6fbb2463","resolution":{"observed_at":"2026-08-07T10:45:04.584746Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2409.19858","last_updated":"2025-03-11T05:28:12Z","snapshot_observed_at":"2026-08-04T17:34:56.311553Z","submitted_at":"2024-09-30T01:34:01Z","title":"The GALAH Survey: Data Release 4","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2409.19858","snapshot_observed_at":"2026-08-07T10:45:04.587790Z","title":"Buder, J","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.587790Z"},"links":{"cited_paper":"/paper/2409.19858","citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:793040eae63da86c6e2c7e453f735611f8efab1c6b5a4a3f74e71ca1148c6e80","observation_id":"bac390ba-89db-4074-bfd7-60003dec0a0c","resolution":{"observed_at":"2026-08-07T10:45:04.587790Z","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":"2026-08-07T10:45:04.591232Z","title":"Bullmore and D","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.591232Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:4df78626af636f6a8a6ba47f01cfbc580832edee3b63b0bd5a13a733e6fe0c0a","observation_id":"4ec949f9-9611-45a8-b18a-23189fefc146","resolution":{"observed_at":"2026-08-07T10:45:04.591232Z","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":"2026-08-07T10:45:04.593915Z","title":"Carpenter, J","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.593915Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:78569cc6f570bff5f663ef2934dcc331f5ea4a737415708ded3c84012f5bb457","observation_id":"c1faa15e-6618-46ed-817e-54f26d4e4579","resolution":{"observed_at":"2026-08-07T10:45:04.593915Z","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":"2026-08-07T10:45:04.596805Z","title":"Casamiquela, A","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.596805Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:2d5b132178cc5579b2bb362ba77f15aa8f8eeb44cb6eb2ee0466cb8eff2fbd2b","observation_id":"eb805804-cdef-4a1a-a47c-5361a7460d65","resolution":{"observed_at":"2026-08-07T10:45:04.596805Z","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":"2026-08-07T10:45:04.599723Z","title":"Cavallo, L","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.599723Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:5043d7ffac7cdc785cded4f94d28aa876a41e21abec18414b27018eb75009456","observation_id":"68fd34aa-51a3-449b-bba8-943d53999a06","resolution":{"observed_at":"2026-08-07T10:45:04.599723Z","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":"2026-08-07T10:45:04.602670Z","title":"Chandola, A","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.602670Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:bca188107429c41d35b290221dbb47df534038ada3ffea0f5528e46bd949526c","observation_id":"f9deb8ea-4396-49d1-b64b-9f30747a946c","resolution":{"observed_at":"2026-08-07T10:45:04.602670Z","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":"2026-08-07T10:45:04.605453Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.605453Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:030db2ecad66b976beaac34dfec2a73a532b05b6f703a2ba78461cd1808bef1e","observation_id":"aef6e917-ab5c-45e1-937b-f8e621369da3","resolution":{"observed_at":"2026-08-07T10:45:04.605453Z","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":"2026-08-07T10:45:04.608496Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.608496Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:aa0510671dba9c785d63e31183f51efe5a9790ae21dfd5256581c19d1ad61b27","observation_id":"f9edcd28-9e1f-42bf-9f08-7bc5d883cdf9","resolution":{"observed_at":"2026-08-07T10:45:04.608496Z","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":"2026-08-07T10:45:04.612406Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.612406Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:59a704173c6d417728a64606b0e2d423338f2e8f97459457bfaa0310b3258ff9","observation_id":"05c2f5f3-270d-4ed4-ba64-7a5de755a24c","resolution":{"observed_at":"2026-08-07T10:45:04.612406Z","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":"2026-08-07T10:45:04.615753Z","title":"Chiappini, F","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.615753Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:c4bcb531e2a361dea86258ba954e59ec7260f5fd2d64defbc55ebf9c9167fa5d","observation_id":"84492f34-0d2b-4957-aed4-1a5ed9ec627b","resolution":{"observed_at":"2026-08-07T10:45:04.615753Z","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":"2026-08-07T10:45:04.618575Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.618575Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:38e2a9819d1d3055d1f156b68a1243d6022d3d52a2b7c75759e6829231765599","observation_id":"2731fef3-d92a-4306-91d2-fdaaef05c14b","resolution":{"observed_at":"2026-08-07T10:45:04.618575Z","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":"2026-08-07T10:45:04.621534Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.621534Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:3ecab634e19362bc4819a5fe551c2fccd43081d396d9e3f2e40266a4ff15268f","observation_id":"0a5880df-60a0-4f78-a963-a21eef218244","resolution":{"observed_at":"2026-08-07T10:45:04.621534Z","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":"2026-08-07T10:45:04.624138Z","title":"Clare.Communicating Clearly about Science and Medicine: Making Data Presentations as Simple as Possible","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.624138Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:d135d363ed8bf876e5bd95da312d8de9cb732724d5348b348b647fdb0dcb5f94","observation_id":"6c5f5dfe-323e-4ecb-8b02-b59a793ced8d","resolution":{"observed_at":"2026-08-07T10:45:04.624138Z","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":"2026-08-07T10:45:04.626918Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.626918Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:e1f0c02068ea9f201f3bd47192d90ec1ec52a06275492f47fab84a5f661307e2","observation_id":"a54ed17b-9059-4341-a275-6dda03fe34d7","resolution":{"observed_at":"2026-08-07T10:45:04.626918Z","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":"2026-08-07T10:45:04.629704Z","title":"Collaboration et al","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.629704Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:7614f6054a7308b17c0cac55151fc7f2ff47e2972471e68b7329352a9abf5d95","observation_id":"43424425-3fd4-4ac4-9ae4-4e64620881d3","resolution":{"observed_at":"2026-08-07T10:45:04.629704Z","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":"2026-08-07T10:45:04.632513Z","title":"Crone, S","venue":null,"work_id":null,"year":2006},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.632513Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:555a91fe0f5cded5e1a3212fbb596c4e454990819cafcb564a69e2373485a918","observation_id":"08e7f240-6325-43fb-a9f9-1e95eab8c1ce","resolution":{"observed_at":"2026-08-07T10:45:04.632513Z","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":"2026-08-07T10:45:04.635496Z","title":"De Silva, K","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.635496Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:6911d5cc3f69e1d2bfff7750d3bdbdc9d00803311f217ad24a7c70cd19c00bbd","observation_id":"956a8093-84be-4a70-aaca-a74a5490daf7","resolution":{"observed_at":"2026-08-07T10:45:04.635496Z","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":"2026-08-07T10:45:04.638641Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.638641Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:444d04596fc9b1ee63466da35c32b6f47f4ff4f660a20364bc3527fb870844db","observation_id":"ae0285dd-1c8c-4fab-b681-15cc79b8d6f0","resolution":{"observed_at":"2026-08-07T10:45:04.638641Z","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":"2026-08-07T10:45:04.641367Z","title":"Denny and A","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.641367Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:3378c2ad6d3ab08991c233c97e1318979c10a7682c1c713aeadfad844ff312e1","observation_id":"b512e299-0592-428a-b586-00d3582e72ad","resolution":{"observed_at":"2026-08-07T10:45:04.641367Z","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":"2026-08-07T10:45:04.644249Z","title":null,"venue":null,"work_id":null,"year":2000},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.644249Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:e271537667adab12087293197e1e2bfbf2a83759da98a32147c273dd6c16d4c2","observation_id":"09bb0f9f-ab90-4eb8-a94f-a6c3532256f7","resolution":{"observed_at":"2026-08-07T10:45:04.644249Z","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":"2026-08-07T10:45:04.647033Z","title":null,"venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.647033Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:9576329bfc75c3b66f0bc42375c2703b54d609c20460ff76962e3016d346053c","observation_id":"d6dc0a10-3001-42d7-8cdc-c2ca2c6c0564","resolution":{"observed_at":"2026-08-07T10:45:04.647033Z","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":"2026-08-07T10:45:04.649740Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.649740Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:d26aefb786c5e32fe7e91531f59a66af78d60b07ae47ae0c7bb405e7d3961833","observation_id":"d1d5efa0-9a46-469e-89d5-863e75bab723","resolution":{"observed_at":"2026-08-07T10:45:04.649740Z","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":"2026-08-07T10:45:04.652406Z","title":"Donor, P","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.652406Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:c321f322a040726d05a671898485ce1dc41557043f07da047fa3449f9a6cd6c0","observation_id":"d25d037d-5512-4fbb-b335-c7ee3c8969c9","resolution":{"observed_at":"2026-08-07T10:45:04.652406Z","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":"2026-08-07T10:45:04.655396Z","title":"Drton and M","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.655396Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:d4dc311634c88cba73e66590ddbf44d0c3dbbcb5ea216a681b295809bce87757","observation_id":"dbd0cf38-d514-47fd-9cb0-70cd4c2b00e4","resolution":{"observed_at":"2026-08-07T10:45:04.655396Z","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":"2026-08-07T10:45:04.658653Z","title":"Ebert-Uphoff and Y","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.658653Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:3d6ecc51f62e2b1b1de1ab2948607e63fa230825083811341948ca29351e0276","observation_id":"678c61c4-51d2-4691-8451-64a8a9a84f3b","resolution":{"observed_at":"2026-08-07T10:45:04.658653Z","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":"2026-08-07T10:45:04.661614Z","title":"El Naqa, D","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.661614Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:b3de560004ee1333869cadcea2a5885dc6bf3876e7ac82453c6e7b655c3bc3f9","observation_id":"a72e2f3b-35c1-49d8-83d6-44eae312ddf3","resolution":{"observed_at":"2026-08-07T10:45:04.661614Z","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":"2026-08-07T10:45:04.664482Z","title":"Evergreen","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.664482Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:a5ebd165b800f952b42e360e4b1806eb4d30204c11df47e0cf3072513c8d2eac","observation_id":"224b3fe5-900a-4b7d-87ac-63fecf387846","resolution":{"observed_at":"2026-08-07T10:45:04.664482Z","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":"2026-08-07T10:45:04.667351Z","title":"Farahani, W","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.667351Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:a8dcfac3fe3a8b8640bbdece2b33b5fcbfdf847aef055c9774dd1ff99092528e","observation_id":"6dc7eeac-597d-48e8-a916-f68b52e0c5ac","resolution":{"observed_at":"2026-08-07T10:45:04.667351Z","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":"2026-08-07T10:45:04.670124Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.670124Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:795b6666e0c28495dab14b5b00cf7b06c224dd6dc03c8dfbb54ce3dd9abc13d4","observation_id":"0aa66ae0-ff26-4a52-b40e-a1eb86327658","resolution":{"observed_at":"2026-08-07T10:45:04.670124Z","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":"2026-08-07T10:45:04.672749Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.672749Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:5509f75d28f067c00c1af8ab1f7a31336484e049410c0a9983d239ffb6752fd0","observation_id":"330be798-df4b-445c-8265-d6fb5b667178","resolution":{"observed_at":"2026-08-07T10:45:04.672749Z","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":"2026-08-07T10:45:04.675503Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.675503Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:1809a475d6cc3555e2f11d0c68cfce3575cb48bee2f6c76a68630879e0b2bbd3","observation_id":"643917b2-2f0c-4a0a-af60-20fb42d945ec","resolution":{"observed_at":"2026-08-07T10:45:04.675503Z","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":"2026-08-07T10:45:04.678395Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.678395Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:993a09d938366be915684ba4ea217bea63b247d611f914eb9a81c635fd4b9ef4","observation_id":"f4c4efd5-51c6-473e-a5fe-ddf26ec41744","resolution":{"observed_at":"2026-08-07T10:45:04.678395Z","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":"2026-08-07T10:45:04.681007Z","title":"reproducibility and replicability in science","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.681007Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:5d43b8bb26412cdf1a3e700a72a5fc88ee6ccca741af94697c3f872dff53fee2","observation_id":"abc87559-cfde-4a4e-8f41-baffbfc72129","resolution":{"observed_at":"2026-08-07T10:45:04.681007Z","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":"2026-08-07T10:45:04.684034Z","title":"Fornito, A","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.684034Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:91c235521fb19a7bcee77b53f7967bd166c71a8c986817b4f439380e8e229d66","observation_id":"d37615a2-52b3-4d31-aac1-e87d18b794ae","resolution":{"observed_at":"2026-08-07T10:45:04.684034Z","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":"2026-08-07T10:45:04.686675Z","title":"Fraix-Burnet, C","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.686675Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:ababc0b02bc1fdc75a683fb9fcc01f2c6f92b2aa9f9545adad3191ba402c6d0b","observation_id":"9e1c0b8f-01c7-4eb7-84fd-b535eb1eeb59","resolution":{"observed_at":"2026-08-07T10:45:04.686675Z","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":"2026-08-07T10:45:04.689175Z","title":"Frank and I","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.689175Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:aeabfcefda6a1054f5d03131db62e70b4c225dc933adb98947ac0f183dc746e0","observation_id":"94fff7ef-01f2-4302-a515-66f83a65e881","resolution":{"observed_at":"2026-08-07T10:45:04.689175Z","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":"2026-08-07T10:45:04.691891Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.691891Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:24d5577c7b070d1ba93836b90e60d75fd61c1b0983c5155f7e57cc1c61ea7445","observation_id":"4a415404-16f4-48bb-a829-5ccca7c9316c","resolution":{"observed_at":"2026-08-07T10:45:04.691891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2505.15728","last_updated":"2025-05-21T16:34:11Z","snapshot_observed_at":"2026-08-07T15:10:12.313877Z","submitted_at":"2025-05-21T16:34:11Z","title":"Are machine learning interpretations reliable? A stability study on global interpretations","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2505.15728","snapshot_observed_at":"2026-08-07T10:45:04.694680Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.694680Z"},"links":{"cited_paper":"/paper/2505.15728","citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:e2979a315ee1d8a1dfaf4df87428552d170abc10188fba99644aa24f4a50144f","observation_id":"f563b73a-38cf-46be-8d56-daa535ca61d7","resolution":{"observed_at":"2026-08-07T10:45:04.694680Z","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":"2026-08-07T10:45:04.697703Z","title":"Garcia-Dias, C","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":64,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.697703Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:abdcaa7b5ef4552cbb38b470ca2d426ed11b882719e36aa16349287253dc0a61","observation_id":"8ed514ec-f913-4700-863c-5353ec83724d","resolution":{"observed_at":"2026-08-07T10:45:04.697703Z","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":"2026-08-07T10:45:04.700731Z","title":"Gastner and G","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":65,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.700731Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:2ad34650e70e74ff2602cc64d1d35b7aeb880ee876093ff0781040176e3c55ca","observation_id":"adf49422-90ef-4b40-9907-bd28fdf82817","resolution":{"observed_at":"2026-08-07T10:45:04.700731Z","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":"2026-08-07T10:45:04.703973Z","title":"Ghojogh, M","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":66,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.703973Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:7d9f735b4ef16a2cf69da49a31575c32ec615fb7f3fac47698decc1f1ce8ce50","observation_id":"a13794b9-8c04-4539-8355-791ee471eeb0","resolution":{"observed_at":"2026-08-07T10:45:04.703973Z","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":"2026-08-07T10:45:04.706842Z","title":"Gilmore, S","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":67,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.706842Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:3aa179696a70ff7aa6c2f1fb8ea9782b7b0935f6c4e8d4b3119767cbb45d2e1d","observation_id":"0bd17834-6d42-40d1-925c-46a3c416bbac","resolution":{"observed_at":"2026-08-07T10:45:04.706842Z","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":"2026-08-07T10:45:04.709507Z","title":"Gleicher, D","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":68,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.709507Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:3ae4312d73f81e878364b49747e868216fe6a9d1f376aaf0baf65a25d456818f","observation_id":"7542803d-d6b0-4b4a-8ccd-0121909e6986","resolution":{"observed_at":"2026-08-07T10:45:04.709507Z","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":"2026-08-07T10:45:04.712470Z","title":null,"venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":69,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.712470Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:e61dcaf5257edbc17ed71bf73c85d8efb99ed480eb7f6c6546f8828311a98806","observation_id":"35e3993f-b322-4c00-aa8b-6275047813a9","resolution":{"observed_at":"2026-08-07T10:45:04.712470Z","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":"2026-08-07T10:45:04.715052Z","title":"Goder and V","venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":70,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.715052Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:dd7ce12d92d1da09ade126bfe91610a71f84fe0e9aae97e47b4f9fc2250c8608","observation_id":"392a52f1-da78-43db-9220-40a3e9ce6a46","resolution":{"observed_at":"2026-08-07T10:45:04.715052Z","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":"2026-08-07T10:45:04.717769Z","title":"Gratton, C","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":71,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.717769Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:d94e538982792d758eed15ea99276de62b711a57be8d0bdddba4baba63518c6d","observation_id":"34375ee7-a939-4f56-9a06-c67e4400669f","resolution":{"observed_at":"2026-08-07T10:45:04.717769Z","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":"2026-08-07T10:45:04.720565Z","title":"Greene, P","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":72,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.720565Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:e2b877ca34d4fb16608dfa2fb32c320e2ac50cf9083da52db9868c1791928712","observation_id":"2eecc47b-b5be-4f71-a97e-760f1cc4c8c3","resolution":{"observed_at":"2026-08-07T10:45:04.720565Z","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":"2026-08-07T10:45:04.725940Z","title":"Handl, J","venue":null,"work_id":null,"year":2005},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":73,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.725940Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:b3643377cd9c424f122464c2fbb374856081f93ee52c435ee9084eb10f12205e","observation_id":"de8272fc-8830-498b-807d-1b8d9460e108","resolution":{"observed_at":"2026-08-07T10:45:04.725940Z","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":"2026-08-07T10:45:04.728789Z","title":"Hastie, R","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":74,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.728789Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:b8be308f1be7aa11ce97b157d537d0807a55333075acd5723eb3063d1cc559ff","observation_id":"ddaca8fc-f873-48bd-bf0e-c5829c15da6e","resolution":{"observed_at":"2026-08-07T10:45:04.728789Z","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":"2026-08-07T10:45:04.731533Z","title":"Hawkins, P","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":75,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.731533Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:49c08e93ee7d52512fcb538f2037dc6a491ac31f8250255a0a331ee0a9049dc0","observation_id":"2a92d7d7-3c12-4e6b-bd8d-2920c5c18a43","resolution":{"observed_at":"2026-08-07T10:45:04.731533Z","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":"2026-08-07T10:45:04.734265Z","title":null,"venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":76,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.734265Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:895892c76ec256e9c9b372f4859df0bd504c7bef12837a8dc040cb23eaf95231","observation_id":"3abff447-c802-456e-bcdd-29f0784c810a","resolution":{"observed_at":"2026-08-07T10:45:04.734265Z","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":"2026-08-07T10:45:04.736980Z","title":"Healy.Data Visualization: A Practical Introduction","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":77,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.736980Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:e819c7c36ab49b9a04e76a7dcece959c759ebb980e599310d5e6327ea85f4a88","observation_id":"4a4af215-a38c-439b-913a-fad63ee5f15e","resolution":{"observed_at":"2026-08-07T10:45:04.736980Z","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":"2026-08-07T10:45:04.739997Z","title":null,"venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":78,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.739997Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:b7beee8684e446260d11ed46e542636a96a50e808800c0474267957a50980a2b","observation_id":"003c6174-d7f6-4383-b3fd-a19eb62db785","resolution":{"observed_at":"2026-08-07T10:45:04.739997Z","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":"2026-08-07T10:45:04.743143Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":79,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.743143Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:661cd7c58932aeb143107fa6e0b262194b32e39728ec3bc4496bd97154ca724e","observation_id":"9214b88d-1a2a-4e9e-957e-800370bed4c6","resolution":{"observed_at":"2026-08-07T10:45:04.743143Z","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":"2026-08-07T10:45:04.745879Z","title":"Hotelling","venue":null,"work_id":null,"year":1933},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":80,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.745879Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:2145e24f5f873733f703c37aa65d37035e718d47aa64e63a0d6d89a31a3738c2","observation_id":"992ec526-2af6-467e-be54-3e20ab85f120","resolution":{"observed_at":"2026-08-07T10:45:04.745879Z","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":"2026-08-07T10:45:04.748530Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":81,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.748530Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:69721727a3132a5f89ff1e0bdb49734019c370c6ae622d2a99ade0e08e429cf3","observation_id":"708a3a11-ff1c-4cc6-b7fb-6b7e99cc55ee","resolution":{"observed_at":"2026-08-07T10:45:04.748530Z","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":"2026-08-07T10:45:04.751348Z","title":"Huang, Y","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":82,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.751348Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:d5602e84b84aa4787a12e5c4faf858083980f34aff3632aeaca946ad5a21b294","observation_id":"4ae7774e-b83e-4bd1-9072-dca3bfbbb88c","resolution":{"observed_at":"2026-08-07T10:45:04.751348Z","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":"2026-08-07T10:45:04.753993Z","title":"Islam and S","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":83,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.753993Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:d7e8b5512d934805fa768ed5ef1e841d708f462b87fbafe8dbf6ae4fa7ebfbdb","observation_id":"85bd5a8a-0269-4d98-85ee-469476a2889c","resolution":{"observed_at":"2026-08-07T10:45:04.753993Z","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":"2026-08-07T10:45:04.756643Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":84,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.756643Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:53137ca9f81db85963a258b812c35e7dfaeeb32d6eed77e094fea22045d8394f","observation_id":"4de3e79b-dbff-40c0-a3cd-6dee800d51de","resolution":{"observed_at":"2026-08-07T10:45:04.756643Z","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":"2026-08-07T10:45:04.759376Z","title":"Janvrin, R","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":85,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.759376Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:1a246bcd43fa4399796a46eca5d211186cfb5b1bac9241e01a93d479014aa902","observation_id":"54889cd5-4814-4312-ab90-a3d60999410a","resolution":{"observed_at":"2026-08-07T10:45:04.759376Z","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":"2026-08-07T10:45:04.762084Z","title":"Josse and F","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":86,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.762084Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:9568d7f64c9a6b7e89788535c8ac90d11af94e80dd3320e12076b3235f3c0978","observation_id":"ab5cf6db-c3fb-4fd2-91c9-f809e91d1c18","resolution":{"observed_at":"2026-08-07T10:45:04.762084Z","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":"2026-08-07T10:45:04.764898Z","title":null,"venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":87,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.764898Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:d8beb87adcfd6bb180b39ecdb675bb0db235f73dc2785e51cbf94c593ea7af50","observation_id":"ff5e466e-d114-4467-951b-2bb58a6b0eb1","resolution":{"observed_at":"2026-08-07T10:45:04.764898Z","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":"2026-08-07T10:45:04.767660Z","title":"Kaufman and P","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":88,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.767660Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:a7b289d7330af7561dc4d13350c8936e76d80436f752d48a05e22c3d31a2bf96","observation_id":"6a1cfcfc-847e-4706-a3f8-c8d06ff2f7e1","resolution":{"observed_at":"2026-08-07T10:45:04.767660Z","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":"2026-08-07T10:45:04.770403Z","title":"Kim and Y","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":89,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.770403Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:e9acfe870c423656e724a9db4ecdcaaa453accfb30871563e6bf8fb07532a385","observation_id":"0403146c-10e8-408a-8211-247598a27373","resolution":{"observed_at":"2026-08-07T10:45:04.770403Z","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":"2026-08-07T10:45:04.723293Z","title":null,"venue":null,"work_id":null,"year":2008},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":90,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.723293Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:fd2d6f7099c1e524ff638a204776d47b95a96e7574e5fa6ad2377de8eaee68e5","observation_id":"0d62efca-239b-42f3-973f-06b2c0191406","resolution":{"observed_at":"2026-08-07T10:45:04.723293Z","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":"2026-08-07T10:45:04.773735Z","title":"Kleijnen","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":91,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.773735Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:507b3d4e3e7d4efe345e433813bd475300f75b37cf2573d144191d3cb8b76fe5","observation_id":"90ffeb20-e0fe-440c-861c-f335ebbe6e68","resolution":{"observed_at":"2026-08-07T10:45:04.773735Z","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":"2026-08-07T10:45:04.776338Z","title":"Kobak and G","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":92,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.776338Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:8ff4c8dd34d1d0c43f1e70f4d1f9509f9908c235d114d68139174b237e0fcea5","observation_id":"6ff02f9e-efc6-4ae7-8515-4dc421d48719","resolution":{"observed_at":"2026-08-07T10:45:04.776338Z","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":"2026-08-07T10:45:04.778924Z","title":"Koivisto","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":93,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.778924Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:8ecb540cb397d66a367378f1b66a001eb03bfffc5088c4b1a2fc2050c880813b","observation_id":"e67edcbb-6069-42ba-b1cc-9f9f3a72fa8d","resolution":{"observed_at":"2026-08-07T10:45:04.778924Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1401.2473","last_updated":"2014-01-10T21:42:35Z","snapshot_observed_at":"2026-07-06T03:32:59.870796Z","submitted_at":"2014-01-10T21:42:35Z","title":"Star Cluster Formation and Feedback","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1401.2473","snapshot_observed_at":"2026-08-07T10:45:04.781978Z","title":null,"venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":94,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.781978Z"},"links":{"cited_paper":"/paper/1401.2473","citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:0b2760aabe78e61474969316b182fdaa43abe6e1a4c403d645a1d78c4b931eb7","observation_id":"b9ff6417-eccc-4515-bd93-35709a0b37a6","resolution":{"observed_at":"2026-08-07T10:45:04.781978Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2412.12115","last_updated":"2024-12-02T14:05:36Z","snapshot_observed_at":"2026-07-06T20:07:58.873037Z","submitted_at":"2024-12-02T14:05:36Z","title":"Rashomon effect in Educational Research: Why More is Better Than One for Measuring the Importance of the Variables?","version":1},"cited_work":{"arxiv_id":"2412.12115","doi":null,"metadata_source":"pith","pith_arxiv_id":"2412.12115","snapshot_observed_at":"2026-08-07T10:45:05.230779Z","title":"Rashomon effect in Educational Research: Why More is Better Than One for Measuring the Importance of the Variables?","venue":"cs.CY","work_id":"5dd8908b-0ffd-4bf0-9b75-fe5aa97042e4","year":2024},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":95,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.785249Z"},"links":{"cited_paper":"/paper/2412.12115","citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:aa30a695b46efccdfe6099cf9c3707dad3c3a27e658046353200587c7e8cbf94","observation_id":"dafef1ca-76f4-4556-9f6e-75668788ae6b","resolution":{"observed_at":"2026-08-07T10:45:05.234414Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-08-07T10:45:04.788364Z","title":"König, J","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":96,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.788364Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:8c2c191db695c0044fbc90afc41d15289bf9dd79d151aac4738491e33f58b8f3","observation_id":"ae5e2c32-216a-4c65-a173-ac56f54828fe","resolution":{"observed_at":"2026-08-07T10:45:04.788364Z","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":"2026-08-07T10:45:04.791041Z","title":"Lange, V","venue":null,"work_id":null,"year":2004},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":97,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.791041Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:d4cc878168acdd293876610f614ca8fe038a9350a557803b3b56b521c2032697","observation_id":"67b299e6-01fd-498b-83ca-b6c42dfc89d0","resolution":{"observed_at":"2026-08-07T10:45:04.791041Z","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":"2026-08-07T10:45:04.793830Z","title":null,"venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":98,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.793830Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:b9c41b313c331920bcb402aa7daa4bda610b29ba2e82b9b97723214314215361","observation_id":"9705fd17-541d-4539-9447-4c270b949d87","resolution":{"observed_at":"2026-08-07T10:45:04.793830Z","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":"2026-08-07T10:45:04.796843Z","title":"Legnardi, A","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":99,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.796843Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:ef2d52c0683162fee668b076af571f46eb7007011e93f8b4e8d559e111339f81","observation_id":"79cb2ad0-ac2d-4d0a-8630-a125b6b63478","resolution":{"observed_at":"2026-08-07T10:45:04.796843Z","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":"2026-08-07T10:45:04.799611Z","title":null,"venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","version":1},"reference_index":100,"source":"pdf_text","source_observed_at":"2026-08-07T10:45:04.799611Z"},"links":{"citing_paper":"/paper/2506.04553"},"observation_digest":"sha256:0a19ba3982388de16ce554a77dbfae99f503455b8f82de38bbc53137e40b8151","observation_id":"e326b70e-9fe7-4cd4-86f4-fa697f021f4a","resolution":{"observed_at":"2026-08-07T10:45:04.799611Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2506.04553","last_updated":"2025-06-05T01:58:45Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T21:04:55.789191Z","submitted_at":"2025-06-05T01:58:45Z","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices"},"reference_resolution":{"displayed":100,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":98,"verified_exact":2,"verified_fuzzy":0},"total_outbound_references":194},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 7 August 2026, this Paper Citation Record lists 100 of 194 outbound references and 2 inbound Pith citation observations for arXiv:2506.04553."}