{"as_of":"2026-08-08T11:35:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:4b316fdde37620e32ce09e1eef3e145467184af8fef452283c55723c041199d3","coverage":[{"denominator":57,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":57,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T10:21:25.556772Z","state":"measured"},{"denominator":57,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":57,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-08T06:32:00.761636+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2506.05721/citation-record","integrity":"/paper/2506.05721/integrity","json":"/paper/2506.05721/citation-record.json","paper":"/paper/2506.05721"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.156654Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":"a668e36b-8628-45b0-adbe-b2d049747a16","year":2014},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:20.701157Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:e77970c14bb0d0c27ca37001d7a4623f479b60921c558f33edb0f34bff2621d4","observation_id":"02c2287f-94f6-42e0-8b68-1492ffe1e3c0","resolution":{"observed_at":"2026-08-07T10:21:30.159418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.149013Z","title":null,"venue":null,"work_id":"ee00b31c-a81e-4fa0-8066-a54b97f08159","year":1956},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:20.742003Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:b5ecb6f9378156653a41b4667f9ab9f7ce2040b116eb7f63c56fa94ff063094a","observation_id":"4e3e39ff-6db0-4ab1-8a5f-3c83e4cc1803","resolution":{"observed_at":"2026-08-07T10:21:30.151643Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.141063Z","title":"Improving transfer learning for movie trailer genre classification using a dual image and video transformer.Information Processing & Management, 60(3):103343, 2023","venue":null,"work_id":"a2e4fd25-e12a-4c29-b2f8-45133ac763bb","year":2023},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:20.798001Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:5e222f415833e2b11f2318f021f442f313d68f83feeb822b95ac8c8cef9b48af","observation_id":"7b7c5468-3e3e-4652-a63f-afae4bf09a1c","resolution":{"observed_at":"2026-08-07T10:21:30.143934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.133533Z","title":"Neural legal judgment prediction in English","venue":null,"work_id":"6e12cbfd-8369-4b89-b691-44d41e767e50","year":2019},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:20.853623Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:bd324d2e8a156b6515ad05322711832f9a6eec6d93d0437ff530dcf3b6bad379","observation_id":"4bba786e-c6bc-4ccd-ad59-6de40b39e3a8","resolution":{"observed_at":"2026-08-07T10:21:30.136105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.124843Z","title":"Efficient few-shot learning for multi-label classification of scientific documents with many classes","venue":null,"work_id":"c4d75c0b-1f92-4213-b8ce-5089d69bda7a","year":2024},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:20.925217Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:9562cc101972838b94f7538a1a57ad6203338e2d2be711d114ce97f8cd884904","observation_id":"3d8d3dbe-004d-411f-98f9-e596f15e128c","resolution":{"observed_at":"2026-08-07T10:21:30.128295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.117083Z","title":"Toward purifying defect feature for multilabel sewer defect classification.IEEE Transactions on Instrumentation and Measurement, 72: 1–11, 2023","venue":null,"work_id":"4972091c-b2f1-47d4-9ad9-604233717a92","year":2023},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:20.997186Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:f857ae5ffd186cc534235128620c037100680cff1521b0968771f9c82e03a4cd","observation_id":"6fe791d2-b3d3-4c43-b87f-08d256f4ceab","resolution":{"observed_at":"2026-08-07T10:21:30.119996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.108449Z","title":"Defecttr: End-to-end defect detection for sewage networks using a transformer.Construction and Building Materials, 325: 126584, 2022","venue":null,"work_id":"eb6f3ac4-8334-4782-a335-8d77469f9649","year":2022},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.087789Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:0dccb84142966d6de71f287502d1ff70e7bc1bd9f44701a7a244854d1ee931a0","observation_id":"533aa675-c320-4bda-a1e8-2e3105bd73bc","resolution":{"observed_at":"2026-08-07T10:21:30.111540Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.100280Z","title":"Chestx-ray8: Hospital-scale chest x-ray database and benchmarks on weakly-supervised classification and localization of common thorax diseases","venue":null,"work_id":"a34ef73b-fa57-4595-8adc-37b4a752dfe4","year":2017},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.144714Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:00e12e14fa92dc0c9f62b00935764a8d53c27070099686a39c1eba52426ab8e0","observation_id":"a5d12b91-b8c1-4d45-a992-9491bc0f26c8","resolution":{"observed_at":"2026-08-07T10:21:30.103052Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.091720Z","title":"Chexpert: A large chest radiograph dataset with uncertainty labels and expert comparison","venue":null,"work_id":"1768b225-6fab-4dde-9574-4abe1852acc2","year":2019},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.215117Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:e1d3d888dc41fb04a29eca588d83156b77be0918f89847d8fd15eff00f3b5a5c","observation_id":"946dec32-707f-40ea-8eea-3cac2e0e97d6","resolution":{"observed_at":"2026-08-07T10:21:30.094620Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.083427Z","title":"Deep-learning-assisted diagnosis for knee magnetic resonance imaging: development and retrospective validation of mrnet.PLoS medicine, 15(11): e1002699, 2018","venue":null,"work_id":"99a9006d-de4b-4b1f-9abd-8c6ba9540738","year":2018},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.285235Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:2edb0a9ab61ef6ea1fc41e229d53169f9d9a82c9be6f55a04bc94ad88a4ec471","observation_id":"1aefb8e4-c4c1-42b3-8a2d-bdb9688e9ad5","resolution":{"observed_at":"2026-08-07T10:21:30.086240Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.075236Z","title":"Sewer-ml: A multi-label sewer defect classification dataset and benchmark","venue":null,"work_id":"0c8052d1-3a09-4d26-be10-b37e998a985a","year":2021},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.356000Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:c9b4a05da92791c2b6eb8eacbf93e8dde5f95269d9ae3a91486d5bd89fe4a628","observation_id":"0634ce86-ced3-4f7b-a61f-7dba9a47a38c","resolution":{"observed_at":"2026-08-07T10:21:30.077897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.067352Z","title":"Focal loss for dense object detection","venue":null,"work_id":"da900439-2e17-4e1f-8bf0-480bd3e52fe3","year":2017},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.407593Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:1b0da1a2be2fe9256bd1b44f4839751b9e38c56e78f6eb7c2ea47f33cd95aaee","observation_id":"b4583d4c-20a7-4593-afdb-5f45f083d520","resolution":{"observed_at":"2026-08-07T10:21:30.069923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.058929Z","title":"Class-balanced loss based on effective number of samples","venue":null,"work_id":"43dcad14-2038-49cc-a788-e51119b38f81","year":2019},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.479620Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:e2f5b3c5df770ab145c84cde8b416858409f281f71a163ca2874c03c1bcfd677","observation_id":"22ea2bd0-4eb7-405c-92b5-843408790483","resolution":{"observed_at":"2026-08-07T10:21:30.061902Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.050704Z","title":"On active learning in multi-label classification","venue":null,"work_id":"a185b0fd-ba4a-43d9-b465-d0fba71f8b5a","year":2005},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.552826Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:1f9c41a7d64f6ba95851e7690f9ef9214a88b118c034e2bb4b37f077929a6010","observation_id":"99407d5d-0e5b-4597-988c-c2bad0c3139b","resolution":{"observed_at":"2026-08-07T10:21:30.053673Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:21.605704Z","title":"Comprehensive comparative study of multi-label classification methods.Expert Systems with Applications, 203:117215, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.605704Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:e111841823386a40b95e47a529580997e3cc8ca7d9ba8d4829abda14b4da3f73","observation_id":"ff6a1003-8f21-4fc8-9180-1456daa34de1","resolution":{"observed_at":"2026-08-07T10:21:21.605704Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.036975Z","title":null,"venue":null,"work_id":"4c4b471e-dff3-4ea9-87ed-809c402c1b68","year":2020},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.670646Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:d02bf464ed19945e94e7064ce70191b1ba08a2ebe75a280c5477a4a408d8180f","observation_id":"0e1f2638-fae2-41ec-a1fc-f920347020a9","resolution":{"observed_at":"2026-08-07T10:21:30.039700Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.028376Z","title":"Learning a deep convnet for multi-label classification with partial labels","venue":null,"work_id":"f4e719c3-4a73-4867-8fc0-d01fe3935ca5","year":2019},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.742680Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:beab62c3950df0216eb849cbdbbb0ea410ce257461644b248fb7e89127511fb3","observation_id":"facd6797-41b9-4835-9333-6dd7308890c2","resolution":{"observed_at":"2026-08-07T10:21:30.031733Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.019896Z","title":"Binary relevance for multi-label learning: an overview.Frontiers of Computer Science, 12:191–202, 2018","venue":null,"work_id":"48ebe008-8171-4710-82ee-7c3853772fa4","year":2018},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.818507Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:518b7fe470bd59289d7ed62b8213e2a6ad89c375d0cd73ee02712758652ae0df","observation_id":"e486dab9-5617-4ec2-a79a-d1fd95a0455c","resolution":{"observed_at":"2026-08-07T10:21:30.022679Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.011709Z","title":"Multi-label learning with stronger consistency guarantees","venue":null,"work_id":"b9c9ceb6-de8b-4b30-b926-b21e4322aa8a","year":2024},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.886732Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:3273dfc72d583e722cf544971c663b053727ce9af32eea3c5c74b0df1d89b980","observation_id":"64b49876-35ad-48b0-b425-3767d2151e6e","resolution":{"observed_at":"2026-08-07T10:21:30.014456Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:30.003355Z","title":"Multilabel classification via calibrated label ranking.Machine learning, 73:133–153, 2008","venue":null,"work_id":"9e01bc6f-08f5-4714-af0b-b1b39c00a4e2","year":2008},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:21.958375Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:b9a9a59b071e9e0ce618c14d29dd95ef4d524bf7823cbfc76aeda8c5f1b2b374","observation_id":"4650760f-b0ad-44fd-9fc3-9321230d5d43","resolution":{"observed_at":"2026-08-07T10:21:30.006122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.994660Z","title":"Classifier chains for multi-label classification.Machine learning, 85:333–359, 2011","venue":null,"work_id":"9e1e0e92-90c6-409c-8e2d-2ef8c34da845","year":2011},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.043950Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:6458b5933f950108fedac4e11403e319ac64affc4b353bb44a0afc76014f43f3","observation_id":"df74494c-8c92-4612-b663-3d203bf1acdc","resolution":{"observed_at":"2026-08-07T10:21:29.997757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.986194Z","title":"Multi-label learning from single positive labels","venue":null,"work_id":"e0e3ec48-59e4-4540-8880-d168f448cc36","year":2021},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.105673Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:4e4987efb78f8b58a25b3835931dc9d560154ea6d3c3052110dd4549abe8a997","observation_id":"24e0505c-9fb2-49e5-8164-63c8ea018897","resolution":{"observed_at":"2026-08-07T10:21:29.989295Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:22.198041Z","title":"Deep long-tailed learning: A survey.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(9):10795–10816, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.198041Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:5326f2d1265b4e8a88e0402089feb7103828cc1916ebae54f2a04e76cdfcb274","observation_id":"1a0b7f49-cf68-4074-89c9-c48aef376685","resolution":{"observed_at":"2026-08-07T10:21:22.198041Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.972677Z","title":"When noisy labels meet long tail dilemmas: A representation calibration method","venue":null,"work_id":"797c2521-2f4e-40b8-9af7-9fa48ec4f345","year":2023},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.266058Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:7add8b495c955225854ca9525ca5bf165a43666e7e8308c9329f9177327496de","observation_id":"1fa0e010-cb89-4141-bcc5-c11807987e6b","resolution":{"observed_at":"2026-08-07T10:21:29.975548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.964835Z","title":"Long tail multi-label learning","venue":null,"work_id":"585b15f3-4ff7-47c5-b91b-0e471ac74fea","year":2019},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.353295Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:8c277129d7f7b96e19c3f742fd9b6a759b63336d48ed47dd9b92df5c0a9de2c3","observation_id":"61b60b62-502b-4e30-84b5-683267b4b95c","resolution":{"observed_at":"2026-08-07T10:21:29.967793Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.956816Z","title":"Distribution-balanced loss for multi-label classification in long-tailed datasets","venue":null,"work_id":"a44e88a4-97ed-4497-8786-bfce5a035070","year":2020},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.440242Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:d1b351ad9d06a3ffcd8a3c3eb143cc89a6a4aaad29ed162efecdcb2aa1891070","observation_id":"ea102062-83b0-4ef7-af0b-eb78ad7067af","resolution":{"observed_at":"2026-08-07T10:21:29.959645Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.947642Z","title":"Edcloc: a prediction model for mrna subcellular localization using improved focal loss to address multi-label class imbalance.BMC genomics, 25(1):1252, 2024","venue":null,"work_id":"3d66555a-434d-4f99-933b-926c4bf743e1","year":2024},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.534728Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:bf76bf6dea24368be3e648256d5724a7a18058ad8d05e88a7556999ec9f86779","observation_id":"425555d1-0fe6-4eb3-85b7-9d496620f40b","resolution":{"observed_at":"2026-08-07T10:21:29.950756Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.939007Z","title":"Asymmetric loss for multi-label classification","venue":null,"work_id":"dbf3399f-f744-4b9e-8a58-dcd5d8fff43c","year":2021},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.633193Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:bff14e087e2736a775dd60ae73d34e88b64e52efe049bbe78af608dfcae7d558","observation_id":"dc22a61a-1176-410e-8929-93d2cff81584","resolution":{"observed_at":"2026-08-07T10:21:29.941933Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.929860Z","title":"Semi-supervised multi-label learning with balanced binary angular margin loss.Advances in Neural Information Processing Systems, 37: 97884–97906, 2024","venue":null,"work_id":"f877dbe8-7c1c-4420-9726-f2435aebfcd9","year":2024},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.703831Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:5360802ad4880510d66300039185263325f5bd12ff01a47c736e0826f47ce1cc","observation_id":"3582a3eb-dd45-4517-a7b9-af51ad91712e","resolution":{"observed_at":"2026-08-07T10:21:29.933476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.764874Z","title":"Long-tail learning via logit adjustment","venue":null,"work_id":"74eaa725-0e21-4f02-820e-e88dc7bd8859","year":null},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.732431Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:dab0bca1339a868afb8a9c1de1f215b10cb58cbb18107d506ede6d5b494bf7af","observation_id":"adda393b-d64c-4de6-988f-e843f3e8ad86","resolution":{"observed_at":"2026-08-07T10:21:29.887297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.388355Z","title":null,"venue":null,"work_id":"133ecb68-e977-42d6-a66a-8a7e06f488d5","year":2024},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.863166Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:ef4550e22a306ab24c76928737d3ffc3243262ec430db47c41875a58e67f72e4","observation_id":"1d6b7b35-9126-4a38-aca5-e75b1adaf47a","resolution":{"observed_at":"2026-08-07T10:21:29.487085Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:22.964993Z","title":"Revisiting deep learning models for tabular data.Advances in Neural Information Processing Systems, 34:18932–18943, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.964993Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:6a3ac1c473cf56c7225c34517ea373d05136fe633341fdc3b81b569ae7bbbb06","observation_id":"21913f61-c6da-400d-b83a-dcf5e073c931","resolution":{"observed_at":"2026-08-07T10:21:22.964993Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.185220Z","title":"The emerging trends of multi-label learning","venue":null,"work_id":"cf09dfbe-354a-4bed-9bba-0e325a010371","year":2021},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.061243Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:6f675b049b3dc02c1fa1edc0e305eb72d25a20af50ce3b821d1ee4f181c06849","observation_id":"b4ed11be-94b2-4763-8a10-f1b873b76461","resolution":{"observed_at":"2026-08-07T10:21:29.266792Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.014319Z","title":"Multi-label local awareness and global co-occurrence priori learning improve chest x-ray classification.Multimedia Systems, 30(3):132, 2024","venue":null,"work_id":"1877646f-b0de-4fbc-84cd-f0767db05d49","year":2024},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.152465Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:25cf9c34436a4a24f95acc5891798d53ad04d2ad52b5a774263b254073a6d4ac","observation_id":"bad8503c-42c3-4d10-896d-f505d49c4f07","resolution":{"observed_at":"2026-08-07T10:21:29.087896Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:28.909050Z","title":"Improving multi-label recognition using class co-occurrence probabilities","venue":null,"work_id":"4389fb46-c9d7-4750-bd79-313c91ec6475","year":2025},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.236736Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:55d2415239fea0713e309edad390f73bea5d24aac5dc780f89a8a1e21baf08c5","observation_id":"d2e0cd46-a3d3-4c5a-bd2e-2315b35e7096","resolution":{"observed_at":"2026-08-07T10:21:28.958883Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:28.776496Z","title":"Multi-label out-of-distribution detection via exploiting sparsity and co-occurrence of labels.Image and Vision Computing, 126:104548, 2022","venue":null,"work_id":"28a062df-8140-4577-9226-ea088d089d52","year":2022},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.329333Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:d50b54e5717f6992a96f8de3661c7aa74ac54d00e95421e4f05b6694291c7167","observation_id":"6725b05d-74df-4a6b-87e7-acd3dd6351d8","resolution":{"observed_at":"2026-08-07T10:21:28.848420Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:28.628874Z","title":"Evidential mixture machines: Deciphering multi-label correlations for active learning sensitivity","venue":null,"work_id":"53610044-ea3d-4790-bd05-0db5dd616aad","year":2024},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.424101Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:b1d2f138ef18834c51e72b9d7bed6515f63b640e92b83f1be050db8460ef3b3a","observation_id":"945bf2c3-82a9-44a6-9d49-37d04eebd256","resolution":{"observed_at":"2026-08-07T10:21:28.724557Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:28.487725Z","title":"In pursuit of causal label correlations for multi-label image recognition","venue":null,"work_id":"334909f3-fccd-4def-9661-6710aeff9d54","year":null},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.511658Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:903a58cd86362ea1f385a7e44c38050e61af60c4499bb1bfa2af1fdc304f5ee6","observation_id":"2995fa7a-87a2-40b4-a161-6a3aa8e97f1b","resolution":{"observed_at":"2026-08-07T10:21:28.575367Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:28.177653Z","title":"Ml-decoder: Scalable and versatile classification head","venue":null,"work_id":"dc449706-5e99-4a41-b030-656ff86b0509","year":2023},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.680401Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:38db60be1a67e853ae7a4e0dd7a7e85c2ce4cc1e4cc23c046eba77c1be924e9d","observation_id":"4373118a-cd35-46ff-b280-8b8c93f189a1","resolution":{"observed_at":"2026-08-07T10:21:28.242118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:28.045466Z","title":"Coocnet: a novel approach to multi-label text classification with improved label co-occurrence modeling.Applied Intelligence, 54(17):8702–8718, 2024","venue":null,"work_id":"652c646c-9ed2-499b-9939-58f1d85c5fde","year":2024},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.771144Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:126180d52cea6fbe234ffa138f5b7ecf3d167ee95271d8f3008ba7ad1ebae9c0","observation_id":"bcf95e29-bb8b-425b-92b1-af2672803766","resolution":{"observed_at":"2026-08-07T10:21:28.115066Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:27.910161Z","title":"Dao, Ethan Zhao, Dinh Phung, and Jianfei Cai","venue":null,"work_id":"23eece25-9c56-4e26-95bc-a935b2aa9a4a","year":2021},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.904130Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:618bf3c4f95c8adfde44d7ec95525327c9b27e2fca17f12f39e7f4d4681ed32c","observation_id":"47206fa8-3aab-43c0-af86-c64e2cf7f5ad","resolution":{"observed_at":"2026-08-07T10:21:27.979539Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:27.778813Z","title":"A review of methods for imbalanced multi-label classification.Pattern Recognition, 118:107965, 2021","venue":null,"work_id":"099cba23-b841-4ad0-ad1f-5e5501bc85f9","year":2021},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.993133Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:93d2e1c8a1028e03841e041944fe2b1e9d34f08cc1ce6aca6dc5a45f3e3fb80b","observation_id":"fce6352f-73ef-418e-8b13-e5d55868b0aa","resolution":{"observed_at":"2026-08-07T10:21:27.845499Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:27.659771Z","title":"Multi-label learning with weak label","venue":null,"work_id":"6d2877f8-fe8d-4816-854f-cc9e1dc5c841","year":2010},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:24.101160Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:36b4ddf59645b8a5688b92c9c09330fb725acc41282d611f5900fd336437f623","observation_id":"9ab37d61-3019-4b0d-9d21-4093158582e0","resolution":{"observed_at":"2026-08-07T10:21:27.721640Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:27.528159Z","title":"Using deep learning for image-based plant disease detection.Frontiers in plant science, 7:215232, 2016","venue":null,"work_id":"3286b75d-0c6d-4667-ae4b-dfa9c7cc42de","year":2016},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:24.256245Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:da218594c3125f5deab244103f2d4040a40986151a4cbd6c1b377581fb96f5e4","observation_id":"3b130fea-1237-4172-8ef4-8a8fa87141dc","resolution":{"observed_at":"2026-08-07T10:21:27.584155Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:27.362550Z","title":"Mvtec ad — a comprehensive real-world dataset for unsupervised anomaly detection","venue":null,"work_id":"e64d1de8-21dd-4bf5-ad90-b59fcc33b0a3","year":2019},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:24.369958Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:9aad1bb4b7e55747c320609ebf239c26bbec47c6396f2b9b3b5fa0d970c35e79","observation_id":"a72357b9-e41f-4563-8109-18afce07b350","resolution":{"observed_at":"2026-08-07T10:21:27.455827Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:27.236188Z","title":"Multi-label classification by exploiting local positive and negative pairwise label correlation.Neurocomputing, 257:164–174, 2017","venue":null,"work_id":"14bf64fa-ccaf-4111-9a8d-65f0f47a66ba","year":2017},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:24.472188Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:447ab578d5da7ec08310df472f28b8cf671d3d40c0f30af9c7cfb6521d7bd832","observation_id":"1e279963-081e-4e1e-9d99-58e69c1b74d0","resolution":{"observed_at":"2026-08-07T10:21:27.300636Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:27.045936Z","title":"V ogel and","venue":null,"work_id":"c51530b8-ed4c-4d1e-98d6-fc62fceb9b41","year":2022},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:24.606161Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:ad898b38817d28a23f3249475aca54857c8d0f9520c5aca3a5bfabc199262555","observation_id":"bdedb18d-a644-4d50-835a-cc4abee78244","resolution":{"observed_at":"2026-08-07T10:21:27.136743Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:26.882896Z","title":"Multi-label classification of chest x-ray abnormalities using transfer learning techniques.Journal of Personalized Medicine, 13(10): 1426, 2023","venue":null,"work_id":"fdbcfb78-a005-4cb0-904e-591edb85cad8","year":2023},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:24.747174Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:2a0bfedd753ab159a5a661f55ef20b2957f1581e8a2cc29ee7f1f96ba198bb0a","observation_id":"3b0f6e7b-f254-4db7-8193-3be7087a9a31","resolution":{"observed_at":"2026-08-07T10:21:26.976381Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:26.758235Z","title":"Tresnet: High performance gpu-dedicated architecture","venue":null,"work_id":"56497d06-cfaf-4a31-b534-3454f9ee479d","year":2021},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:24.910872Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:a90555023fabb8930bd1f2bc4b4bb9c149fdd3817122aa24e036c537dfd8fa8f","observation_id":"ac1dd185-01bf-4db2-b017-96eaeabe75cf","resolution":{"observed_at":"2026-08-07T10:21:26.826501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:26.575585Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"c6f7fc09-10b8-403e-8b71-1fc7e7e4056c","year":2021},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:25.049280Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:2de1e8f45682befce53554112199eccfcdcc20c03d13f14a967730fd422cdbe3","observation_id":"7b28f3a7-b585-47a4-b769-5a36dc52b87a","resolution":{"observed_at":"2026-08-07T10:21:26.693114Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:26.356227Z","title":"Maxvit: Multi-axis vision transformer","venue":null,"work_id":"cb865838-c664-482b-8d27-713f1149bd40","year":2022},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:25.172689Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:1fef902d3f5e74fc8eedd1a053b491fa4bacd6d4b9ea65c552f1aa5e385f9af4","observation_id":"2029b150-15e9-4328-bb13-c71bf9413c32","resolution":{"observed_at":"2026-08-07T10:21:26.512062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:26.208170Z","title":"Decoupled weight decay regularization","venue":null,"work_id":"e19034e8-b426-44a1-b03a-f9e762e821c6","year":2019},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:25.288798Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:4c83ec92e79a6966ad678c37dc49884502695cfb937f5f2a00aa1f7bc7c3b53c","observation_id":"64efc594-5b0a-476a-b91d-b78465700014","resolution":{"observed_at":"2026-08-07T10:21:26.261960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:25.995002Z","title":"SGDR: Stochastic gradient descent with warm restarts","venue":null,"work_id":"030f4de4-dca1-4b35-83f2-87e4e18741de","year":2017},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:25.384069Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:ebd921b6f3c2a44e86a801fa207b26c976a8767160fb2cb2fd28c2c1ecfa8691","observation_id":"466d81c7-a9aa-46c1-945d-683de09d2f45","resolution":{"observed_at":"2026-08-07T10:21:26.077152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:25.834494Z","title":"Multi-scale hybrid vision transformer and sinkhorn tokenizer for sewer defect classification.Automation in Construction, 144: 104614, 2022","venue":null,"work_id":"0013c400-55b7-43c2-bde3-075f09a4c6d1","year":2022},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:25.466812Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:53c783ef29aade4b0ec3f1dde9555e2081c204eafa6e36caa75d21fb3a69057e","observation_id":"726fbc73-5c99-44d9-9710-c027f6a86b1c","resolution":{"observed_at":"2026-08-07T10:21:25.931223Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"0220.4319","doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:25.707551Z","title":"Any-Class","venue":null,"work_id":"b2ab97b2-730d-4fef-a7eb-9010cec6a294","year":2017},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:25.556772Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:60f86f0cafe419733e6cec53e01485bc4bca6e0bac896b748da0185a274a2d56","observation_id":"bae66c8c-9e30-4476-bd9b-f6dd51c3fcca","resolution":{"observed_at":"2026-08-07T10:21:25.784509Z","resolver_source":"raw_fallback","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:29.562041Z","title":null,"venue":null,"work_id":"4961cbf4-620e-4c08-abb7-bb52c5faa7ce","year":null},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:22.779343Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:218a02b7c2e0f0fc9b4e10f879b8095243681d5cf57ad9e189e476710da8f3f3","observation_id":"4dc8c550-589b-46b6-bb76-9198e4ce41b4","resolution":{"observed_at":"2026-08-07T10:21:29.702814Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T10:21:28.324498Z","title":null,"venue":null,"work_id":"b7af451c-bcc2-469d-bc43-e5dffb79f7f6","year":null},"citing_paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data","version":1},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T10:21:23.600940Z"},"links":{"citing_paper":"/paper/2506.05721"},"observation_digest":"sha256:32c0d3a88f94ca15d115beb8b15e379344d700788004ae8e90c5e4c80fc9b52b","observation_id":"a27a945a-a9be-4a00-bad4-b0fb775df618","resolution":{"observed_at":"2026-08-07T10:21:28.409223Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-08T06:32:00.761636+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2506.05721","last_updated":"2025-06-06T03:59:11Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-07T10:11:18.814191Z","submitted_at":"2025-06-06T03:59:11Z","title":"Any-Class Presence Likelihood for Robust Multi-Label Classification with Abundant Negative Data"},"reference_resolution":{"displayed":57,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":1,"verified_fuzzy":48},"total_outbound_references":57},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-08T06:32:00.761636+00:00","source":"crossref"},{"observed_at":"2026-08-08T06:31:55.24221+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 57 of 57 outbound references and 0 inbound Pith citation observations for arXiv:2506.05721."}