{"as_of":"2026-08-12T10:41:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:0bec59e8d9a82e2dfc4589efcc75a59793587c254898ae4a80cf40eb93888940","coverage":[{"denominator":35,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":35,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-05T15:11:46.375626Z","state":"measured"},{"denominator":35,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":35,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-12T06:34:41.77262+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/2508.20381/citation-record","integrity":"/paper/2508.20381/integrity","json":"/paper/2508.20381/citation-record.json","paper":"/paper/2508.20381"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T15:11:47.893592Z","title":"Cdul: Clip-driven unsupervised learning for multi-label image classification","venue":null,"work_id":"3334c476-f4e4-4db3-bb38-e5337f5ffcaf","year":2023},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:43.816548Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:37575b6ede959d4e0c6ecd8312a8c91a8d9850a33fb5672d03f41eec345cbc28","observation_id":"d9d37942-7f38-4399-8e08-10bfcfb7c0e1","resolution":{"observed_at":"2026-08-05T15:11:47.924848Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.817524Z","title":"Boosting single positive multi-label classifica- tion with generalized robust loss","venue":null,"work_id":"affa6efb-4e81-4efa-bd4a-d416cf24e2c3","year":2024},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:43.894974Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:7370ecfe304173ee8b9b544c95a52c42e2a05f402de2fe842712fedd80215e04","observation_id":"6510e78c-ab2d-4b65-ab12-2fce6329ba63","resolution":{"observed_at":"2026-08-05T15:11:47.845857Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.776086Z","title":"Multi-label image recognition with graph convolu- tional networks","venue":null,"work_id":"439d62cf-a726-436c-9b74-f47a24614ce0","year":2019},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:44.054846Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:5214fc61907afafd759b4834705579f5a6e44c1d2d20903e13b49c8768bb2df6","observation_id":"849c6df0-f6ec-4628-8a90-39f46e580ede","resolution":{"observed_at":"2026-08-05T15:11:47.789874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.735052Z","title":"Nus-wide: a real-world web im- age database from national university of singapore","venue":null,"work_id":"9b06440c-9b4b-427b-9e5d-fe27f855c6e8","year":2009},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:44.221150Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:944c20a2b2731e01513424e8cb195f70d9f3ec8114eda7b568e832d60232cf46","observation_id":"67890e31-0a28-4570-9fcd-3a75e5d1d0e2","resolution":{"observed_at":"2026-08-05T15:11:47.753635Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.689864Z","title":"Multi-label learning from single positive labels","venue":null,"work_id":"a03b3916-f630-48b9-8179-75900cd1b21a","year":2021},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:44.454760Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:41bb2b0e718dd611e3d43a15579c479f1f163dfc3e1429cd6ea318c73e11b5cd","observation_id":"cf4168c3-2453-48cc-9383-7424ede04eca","resolution":{"observed_at":"2026-08-05T15:11:47.710497Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:44.614847Z","title":"Imagenet: A large-scale hierarchical image database","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:44.614847Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:fa72030348a189cf0d6b0231eee7ef2a74db3ff432b09e6d30175156e496a85d","observation_id":"81fd2ecd-3450-4e83-80ef-d6b7ed67a845","resolution":{"observed_at":"2026-08-05T15:11:44.614847Z","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":"2026-08-05T15:11:47.640921Z","title":"Scalable multi-label annotation","venue":null,"work_id":"05e819d4-c6e3-470c-b3ad-b63db5e2131f","year":null},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:44.762897Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:5bbe29d14e5d4f22fb1d252537367dd470e7dbcd4930c643f6bc881eb4d4416e","observation_id":"8bce1bcc-f6cd-4344-b941-0bf2e1682e12","resolution":{"observed_at":"2026-08-05T15:11:47.650627Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.611774Z","title":"Explor- ing structured semantic prior for multi label recognition with incomplete labels","venue":null,"work_id":"33bbcda6-221d-45f5-9575-9858fc416eff","year":2023},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:44.947351Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:87bdfbcc6fc221b95411b555dee77881f085b14ab6fd5edbc75674ef4f00fda7","observation_id":"8d4a3bca-9b98-4fbf-8daa-4b629a12c60a","resolution":{"observed_at":"2026-08-05T15:11:47.620666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.564003Z","title":"An image is worth 16x16 words: Transformers for image recognition at scale","venue":null,"work_id":"6b86d8ba-f53a-465e-9728-3ed5183e11bb","year":2021},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.094746Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:66766daccd1d97509d4e5d89b2231361bc5be8f7c5d3c6bac5d17e307051f8a1","observation_id":"0a52bf85-cf07-4378-b7f7-9c67f43256c4","resolution":{"observed_at":"2026-08-05T15:11:47.576529Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.537901Z","title":"The pascal visual object classes (voc) challenge","venue":null,"work_id":"b01f006d-f5d9-40d0-a67d-83a499345cc3","year":2010},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.259716Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:6f765f2ea6545fb9268a414afd99b65c846fda1a68e993f9a4868bfef85c6729","observation_id":"1ab298e0-c8bc-4de2-b3aa-b7ebe8057861","resolution":{"observed_at":"2026-08-05T15:11:47.545059Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:45.414751Z","title":"Deep residual learning for image recognition","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.414751Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:0b4680284895976def7eaa86b1fd40d0431ab9cb3079dd4e1d0c0b8f3a26f1d1","observation_id":"53126c3a-b66c-4448-9793-a9b68011e657","resolution":{"observed_at":"2026-08-05T15:11:45.414751Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2310.05914","last_updated":"2023-10-10T17:31:00Z","snapshot_observed_at":"2026-08-12T05:13:32.551469Z","submitted_at":"2023-10-09T17:58:34Z","title":"NEFTune: Noisy Embeddings Improve Instruction Finetuning","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.05914","snapshot_observed_at":"2026-08-05T15:11:45.545007Z","title":"Bar- toldson, Bhavya Kailkhura, Avi Schwarzschild, Aniruddha Saha, Micah Goldblum, Jonas Geiping, and Tom Goldstein","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.545007Z"},"links":{"cited_paper":"/paper/2310.05914","citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:9f139e4b096e9d1b6574940a84d12a680bd307910a8c29e3e3e3577e785663e5","observation_id":"98e18584-629f-4bb2-bbe0-220329686f40","resolution":{"observed_at":"2026-08-05T15:11:45.545007Z","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":"2026-08-05T15:11:47.427362Z","title":"Large loss matters in weakly supervised multi- label classification","venue":null,"work_id":"a2e1ec0c-03a4-475a-b4ac-8bd21e4e39e7","year":2022},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.626368Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:d39b47c6b9ef74b83863d705e5ba9ce475a17c7143167c1da8ae50b5ac0c78af","observation_id":"4b2de954-e703-4913-b94c-b42fb4502fb7","resolution":{"observed_at":"2026-08-05T15:11:47.454816Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.400152Z","title":"Bridging the gap between model explanations in partially annotated multi- label classification","venue":null,"work_id":"abee506a-0b66-4182-a9b4-6bc934e24f20","year":2023},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.704750Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:92983c74ba5a97dcefdfd4719599ffdd9c2ffa67a7e09ec5f6fc11de3df9e1fe","observation_id":"bff04cfd-d6a7-405b-91be-2c007fd018f0","resolution":{"observed_at":"2026-08-05T15:11:47.408153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:45.744750Z","title":"Kingma and Jimmy Ba","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.744750Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:6bf6641c799fe1d6ec2bf8199e51a58ed3550eeedbec75b5c55b43ce9f5fdf68","observation_id":"0bb31f09-1e87-4895-92cf-f5b73353c673","resolution":{"observed_at":"2026-08-05T15:11:45.744750Z","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":"2026-08-05T15:11:47.338597Z","title":"Kipf and Max Welling","venue":null,"work_id":"adbb2c2d-75bb-497c-b786-0bf8af3c6607","year":2017},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.794749Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:065a49f17925775af5f0681e1c8dca9d5ea7b8eb93c6d32b309fd3dc3670a645","observation_id":"9aec6396-5654-4a80-aabd-3f6330e6c74a","resolution":{"observed_at":"2026-08-05T15:11:47.357258Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.288978Z","title":"Robust optimization as data augmentation for large-scale graphs","venue":null,"work_id":"b38df985-eae3-4363-b004-41e92ae57ec4","year":2022},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.834830Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:ec5a853c2cf33dd5bddfcc394a9361120b4686093b4d62b7836eb55510a4d3f9","observation_id":"71a1fa05-f47e-4082-90e7-3e29a4f2258f","resolution":{"observed_at":"2026-08-05T15:11:47.302279Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.258799Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":"bdfc8915-434b-4992-b052-15aecb35ab34","year":2014},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.887168Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:6df542cac39418660c5cda569ab62708aff9dc58c1233ab291e26981d97af36c","observation_id":"99f33e87-56bd-4e30-9b9c-502f7838bf19","resolution":{"observed_at":"2026-08-05T15:11:47.263917Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.210901Z","title":"Revisiting pseudo-label for single-positive multi-label learning","venue":null,"work_id":"e88edf2e-a61c-46d6-9bb5-47a1d69c5cda","year":2023},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.923597Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:949f98cbda28da1ffd86406e1cfeae4ef8afe746400dd8a55fa4e4f2ec24452d","observation_id":"02d346b8-3539-41eb-b11d-0b8e9878a6a8","resolution":{"observed_at":"2026-08-05T15:11:47.228122Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.184977Z","title":"The emerging trends of multi-label learning","venue":null,"work_id":"4628dff0-df42-4384-8782-e2548ae25e91","year":2021},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:45.954747Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:567adad8df39712be6562ca2c48b1794107e11e03d2700fb5e5016b183926e93","observation_id":"87fc7cf3-5d2b-43e8-a439-2363b5106503","resolution":{"observed_at":"2026-08-05T15:11:47.191795Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:46.004870Z","title":"A convnet for the 2020s","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.004870Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:4b77d2d92ee442c19fb413b0f01dd9adf2aeb8bdbcc59b9f6acd9cc79fcf6602","observation_id":"e9e6b80e-47f8-49a4-9119-fb1265a2364e","resolution":{"observed_at":"2026-08-05T15:11:46.004870Z","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":"2026-08-05T15:11:47.101248Z","title":"Learning transferable visual models from natural language supervi- sion","venue":null,"work_id":"c98194a1-e27b-47d1-959e-dc42900002a7","year":2021},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.054826Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:84bcb0ed0f176e10b457cf99df4a385c1b60b7129fce67ce20e2e76ddffece70","observation_id":"9d2253d5-58a6-4883-8896-e348a261d450","resolution":{"observed_at":"2026-08-05T15:11:47.114739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:47.044743Z","title":"Multi-label classifica- tion with missing labels using label correlation and robust structural learning","venue":null,"work_id":"0c509e5e-eed3-4e01-99b2-ade975617e55","year":null},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.094834Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:ed06986311bb32c99fa6652ca6e1daa0224462417f973439529746b902ab317b","observation_id":"c023abca-4638-450d-81b4-e0b1dda7068e","resolution":{"observed_at":"2026-08-05T15:11:47.053722Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:46.144747Z","title":"The caltech-ucsd birds-200-2011 dataset","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.144747Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:1467908efdd37d84f9ad74a5eecb88234a2754d30a1d93377b7062e35b296233","observation_id":"008aa2af-3a8c-471b-bd08-f383af537684","resolution":{"observed_at":"2026-08-05T15:11:46.144747Z","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":"2026-08-05T15:11:46.968826Z","title":"Multi-label learning with missing labels","venue":null,"work_id":"0e58eba4-1b42-4450-93bc-b8a9eb7d77ba","year":2014},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.171372Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:6dee763eaaa7bb0ef8343a1e611796bbd6a879d91555f5fdcb73388730c38847","observation_id":"173374e0-b30f-46bf-ae76-ecb5238ff469","resolution":{"observed_at":"2026-08-05T15:11:46.976062Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:46.935159Z","title":"Ml-mg: Multi-label learning with missing labels using a mixed graph","venue":null,"work_id":"5f3a90fd-a096-40b5-85d7-32f080c13d9f","year":2015},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.179525Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:89727f6621b771e5a2b1638f87424ea2392ef3e3abb1724dd1bd650b5005fa2b","observation_id":"8c576c15-480f-46d2-8e09-ffe712f0820a","resolution":{"observed_at":"2026-08-05T15:11:46.947123Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:46.889231Z","title":"Vision-language pseudo- labels for single-positive multi-label learning","venue":null,"work_id":"1ad9b205-486c-4698-a44a-e41cd6768918","year":2024},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.194747Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:1f1e8e2d117c0878bc3bc0197b406a1b7e9a0fffd76ba7f44b0f7a940ef78da9","observation_id":"d2af2b57-8f86-4eaa-aa45-6987b98b84a2","resolution":{"observed_at":"2026-08-05T15:11:46.908926Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:46.850537Z","title":"One positive label is sufficient: Single-positive multi- label learning with label enhancement","venue":null,"work_id":"04665dfe-8ef4-4652-ab5b-7c4cc457f8c6","year":2022},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.220376Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:223c85145ad77d58fb5e6494f8d93bf1c689583197bd8a9a4e7ee9044e5393bc","observation_id":"526db189-4772-4b00-9d19-4d2666578931","resolution":{"observed_at":"2026-08-05T15:11:46.870237Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:46.787728Z","title":"Large-scale multi-label learning with missing la- bels","venue":null,"work_id":"00d9d839-12a7-40b6-91a4-983377c11afb","year":2014},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.253355Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:83f0abaf5bd96068d23dcfee9d20ee37a84050dc271a2ac87396d818d328ce7a","observation_id":"00cc021b-0331-47b8-8b92-a76b92ccba75","resolution":{"observed_at":"2026-08-05T15:11:46.824748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:46.274813Z","title":"Vision-language models for vision tasks: A survey","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.274813Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:17c30d66279e50e66f9c83e5b6a20568b8ba43e97447481470663b45777ea667","observation_id":"0cbda509-404b-495c-9d42-f74aa8b4d155","resolution":{"observed_at":"2026-08-05T15:11:46.274813Z","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":"2026-08-05T15:11:46.724371Z","title":"A review on multi-label learning algorithms","venue":null,"work_id":"eb0c546a-f52d-4b57-b857-091a8804bccd","year":2013},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.309300Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:426b1fc99c63f5342dff2e8b2fc40caba26d3ca93ead39d682bebec259c41c11","observation_id":"cd6a9ffa-317b-4a27-a95a-4ea661c56093","resolution":{"observed_at":"2026-08-05T15:11:46.740303Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:46.662545Z","title":"Learning in im- perfect environment: Multi-label classification with long- tailed distribution and partial labels","venue":null,"work_id":"116d60fa-7728-4f22-8955-93f2c66edf92","year":2023},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.327926Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:256ca7183c729561c04a675ec382772fa6c4ab3c0655f75e599c99199fb3e3d5","observation_id":"6bfb1693-cac9-44c7-b1d1-45a4b0e1e0db","resolution":{"observed_at":"2026-08-05T15:11:46.682060Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2112.07368","last_updated":"2021-12-27T14:23:32Z","snapshot_observed_at":"2026-07-06T12:18:35.507335Z","submitted_at":"2021-12-13T11:39:19Z","title":"Simple and Robust Loss Design for Multi-Label Learning with Missing Labels","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2112.07368","snapshot_observed_at":"2026-08-05T15:11:46.346240Z","title":"Simple and robust loss design for multi-label learning with missing labels","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.346240Z"},"links":{"cited_paper":"/paper/2112.07368","citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:e34136e3f55ff474aea837e2e03450b9e9dfd558fff26d6217d8bbd647212c49","observation_id":"d5f5bb65-84f0-4a2e-a2dd-b0de5391555e","resolution":{"observed_at":"2026-08-05T15:11:46.346240Z","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":"2026-08-05T15:11:46.633071Z","title":"Acknowledging the unknown for multi-label learning with single positive labels","venue":null,"work_id":"68ec7b29-5e02-4986-acb6-62b134829faa","year":2022},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.369127Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:33b97b69e19bde959decedc58822b61c9b4c42d5476f8199eb4071c8e9d58a65","observation_id":"7b1758e6-3537-4972-8c04-55fa1483cfd9","resolution":{"observed_at":"2026-08-05T15:11:46.639728Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+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":"2026-08-05T15:11:46.497215Z","title":"Freelb: Enhanced adversarial training for natural language understanding","venue":null,"work_id":"8cc17789-0f8e-450a-923a-de1df81eea09","year":2020},"citing_paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-05T15:11:46.375626Z"},"links":{"citing_paper":"/paper/2508.20381"},"observation_digest":"sha256:634c7077b87013ef87c912533615f6e0ce5dac2b0b6b149b7fd64bae7a4b37be","observation_id":"7d58e54b-7931-40b6-ba69-947fd0feacbb","resolution":{"observed_at":"2026-08-05T15:11:46.587923Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2508.20381","last_updated":"2025-08-28T03:07:57Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-10T07:07:37.124419Z","submitted_at":"2025-08-28T03:07:57Z","title":"More Reliable Pseudo-labels, Better Performance: A Generalized Approach to Single Positive Multi-label Learning"},"reference_resolution":{"displayed":35,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":27},"total_outbound_references":35},"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":"2026-08-12T06:34:41.77262+00:00","source":"crossref"},{"observed_at":"2026-08-12T06:34:36.333875+00:00","source":"retraction_watch"}],"thesis":"As of 12 August 2026, this Paper Citation Record lists 35 of 35 outbound references and 0 inbound Pith citation observations for arXiv:2508.20381."}