{"as_of":"2026-08-08T15:46:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:372ba6558c9682f4e44de166e306f68bc9db567f27fdf23129d0743200ab5a1e","coverage":[{"denominator":60,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":60,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-03T15:16:01.640866Z","state":"measured"},{"denominator":60,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":60,"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/2512.17788/citation-record","integrity":"/paper/2512.17788/integrity","json":"/paper/2512.17788/citation-record.json","paper":"/paper/2512.17788"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:54.997915Z","title":"A brief introduction to weakly supervised learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:54.997915Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:dd6b221a842e72bacf48252cbda5a91644f1a9a49de5ae6d828cfa8a54590af2","observation_id":"5edf96b1-2304-4030-9f4e-b7902344b978","resolution":{"observed_at":"2026-08-03T15:15:54.997915Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:55.073498Z","title":"Multiple instance classification: Review, taxonomy and comparative study,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:55.073498Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:b4619d7d2d6be1b6d46996705418e8d1e46ae4244cf8b52da8690d1b67ac04a9","observation_id":"aa237031-36c8-4b12-891d-2343e7d664a5","resolution":{"observed_at":"2026-08-03T15:15:55.073498Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:55.235529Z","title":"Multiple instance learning: A survey of problem characteristics and applications,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:55.235529Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:2e25c254048afa76167d46f3e3a447e6d775053d3e7218f6cfa7cc28816b118c","observation_id":"833464c7-6186-411b-980b-f27bee4c8071","resolution":{"observed_at":"2026-08-03T15:15:55.235529Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:55.347088Z","title":"Attention-based deep multiple instance learning,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:55.347088Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:1e56b56002febd0dcafe699961e728604dabf1b57adfd6d6b5bc7a3459812446","observation_id":"f10d2197-71f8-4ac6-85ea-b2341e8a099f","resolution":{"observed_at":"2026-08-03T15:15:55.347088Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:55.463246Z","title":"Revisiting multiple instance neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:55.463246Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:936c58ee28f6875ac7b644d88d12c65104dafa0bdb97c42ab9b27153092008ae","observation_id":"a9cc209b-de26-4a43-85f3-fa644654216b","resolution":{"observed_at":"2026-08-03T15:15:55.463246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:55.557235Z","title":"Multi- instance causal representation learning for instance label predic- tion and out-of-distribution generalization,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:55.557235Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:191c30df2a5c5b622eda899f0059649b19f82c21dad36b759668e98ab7b62136","observation_id":"51638117-77ea-444d-9ea5-52b8a61841af","resolution":{"observed_at":"2026-08-03T15:15:55.557235Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:55.663393Z","title":"DTFD-MIL: Double-tier feature distillation multiple instance learning for histopathology whole slide image classifi- cation,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:55.663393Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:881f3b989caa0d24da8e2ede0a02aa5b5caa455909901980ed9b36ac373d3ae2","observation_id":"fe706f9b-8a54-404b-b751-a562ef8f8ffe","resolution":{"observed_at":"2026-08-03T15:15:55.663393Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:55.760291Z","title":"Incorporating probabilistic domain knowledge into deep multiple instance learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:55.760291Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:b9224b8e0854386f6a38a5e902ad1b3da9fc1c308fd88b6d1e2d6d3335400fa4","observation_id":"c209aa89-e5c7-41da-b0a4-193f4ffb84e7","resolution":{"observed_at":"2026-08-03T15:15:55.760291Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:55.859588Z","title":"Data- driven knowledge fusion for deep multi-instance learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:55.859588Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:c2db250c2b226033a66e409b4cb864ad55697dfc4b1eaf7dc795384c954803c5","observation_id":"2777e7e5-3f33-4d7d-af6e-fd139c7f34e0","resolution":{"observed_at":"2026-08-03T15:15:55.859588Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:55.971068Z","title":"Learning from partial labels,","venue":null,"work_id":null,"year":2011},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:55.971068Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:7079447861e98098d4b2e4d1717e097d815784395b4911d868e3b9e17535f6b3","observation_id":"087b4530-108c-4f20-ac4f-5d648c0c215b","resolution":{"observed_at":"2026-08-03T15:15:55.971068Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:56.113454Z","title":"Exploiting class activation value for partial-label learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:56.113454Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:f21af8e0b45c24b15bcf980a11713f4292e5ebbb8de684eeef3a3608314f358f","observation_id":"6044019a-f005-47f2-8607-906d7035d809","resolution":{"observed_at":"2026-08-03T15:15:56.113454Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:56.267673Z","title":"Partial label learning with semantic label representations,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:56.267673Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:1703e31ff4e9dac57be1fb8137e67c9fcde4f79c3ad300310d86c5e7ef38233a","observation_id":"08176795-677c-4288-90ce-5b58e78de0cf","resolution":{"observed_at":"2026-08-03T15:15:56.267673Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:56.400489Z","title":"A unifying probabilistic framework for partially labeled data learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:56.400489Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:0ee85203382f6b4622a66fb38bc07ce7da47d8b6952772851a7405bd62ac1c0d","observation_id":"2175acb2-598a-440f-b2fb-11585bcf5bc1","resolution":{"observed_at":"2026-08-03T15:15:56.400489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:56.528607Z","title":"Learning with partial labels from semi-supervised perspective,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:56.528607Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:f2c08f017f7651fb2a72721b828788a3491a416c6db0610eb5af35e62925eb84","observation_id":"5599867e-3009-4726-9e5f-36474ac3c021","resolution":{"observed_at":"2026-08-03T15:15:56.528607Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:56.620292Z","title":"Progressive purification for instance-dependent partial label learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:56.620292Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:c3199016d4e1d4d6f2783f8d78e64ea91cb15c7776dd58203373b0ff9eb82171","observation_id":"121fe5dd-caff-4d47-8ecf-1d12728a7a9f","resolution":{"observed_at":"2026-08-03T15:15:56.620292Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:56.694968Z","title":"Distilling reliable knowledge for instance-dependent partial label learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:56.694968Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:92ca1c14bb91fefda108d17e266a4a5df3e8c0dd6e73a34e6e63a4a70c1d2417","observation_id":"ac1f3212-ef7b-454c-81c5-02689904593d","resolution":{"observed_at":"2026-08-03T15:15:56.694968Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:56.810285Z","title":"Partial label causal representation learning for instance-dependent supervision and domain generalization,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:56.810285Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:5ee705ed690caf6995efb041d2cff6912a96e91f038ea97a59a43157791e935b","observation_id":"0806892b-7073-4a1f-8e44-61ef295795e5","resolution":{"observed_at":"2026-08-03T15:15:56.810285Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:56.895301Z","title":"Disambiguated attention embedding for multi-instance partial-label learning,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:56.895301Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:72cf536f43868a8c851cec98ef992167a6b08a9677008c6b917d31f803b98b68","observation_id":"bec61196-a3ff-4916-8239-452e5b01e241","resolution":{"observed_at":"2026-08-03T15:15:56.895301Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.086367Z","title":"Multi-instance partial-label learning: Towards exploiting dual inexact supervision,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.086367Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:e06bba4e8213773818b2723f55b429e330bfe4bc4d26cfb02b281b0ab254b638","observation_id":"d99cce5f-6760-456d-bb47-504a361ddec3","resolution":{"observed_at":"2026-08-03T15:15:57.086367Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.289493Z","title":"Clinical-grade computational pathology using weakly supervised deep learning on whole slide images,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.289493Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:bb08a317f686530e06974e6fd4b3911f7cbf634bcb4a72fedd21319d11553155","observation_id":"96334646-8f95-4036-b0aa-a4e73e68c997","resolution":{"observed_at":"2026-08-03T15:15:57.289493Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.421034Z","title":"Crowdsourcing of histological image labeling and object delineation by medical students,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.421034Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:b7f552d587da17707233dcf3a58cc9be27160cd1d3a58f21dba3e41226895d6a","observation_id":"c45f8afc-e90d-4011-a6c0-7a075f2e4d8d","resolution":{"observed_at":"2026-08-03T15:15:57.421034Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.491029Z","title":"Exploiting conjugate label information for multi-instance partial-label learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.491029Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:8ba174c0923dd2213386c43be9f6af6a8ce1bd9d888bcf44ccbd266c252793cc","observation_id":"4209869b-6002-4a50-82c4-7e3d047b4c65","resolution":{"observed_at":"2026-08-03T15:15:57.491029Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.560246Z","title":"Multi-instance partial-label learning with margin adjustment,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.560246Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:a8f23a981335d7030ea2301dfaf016ae86ef2924a763283b0acdbeac5609ad6a","observation_id":"a50bc408-ca8f-4365-a4cb-f23a5bcc5626","resolution":{"observed_at":"2026-08-03T15:15:57.560246Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.641573Z","title":"Pro- gressive identification of true labels for partial-label learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.641573Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:838f8f1e570a3a228c6cf211f6d1fa787160a6021620ec67c6985b43e2d7d44b","observation_id":"599e10c8-8933-4381-a105-d46ad8b70438","resolution":{"observed_at":"2026-08-03T15:15:57.641573Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.715296Z","title":"Solving the multiple instance problem with axis-parallel rectangles,","venue":null,"work_id":null,"year":1997},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.715296Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:636c8b948b89ada4a50743456718da437403d5485e4e4efce84bf6b33684af2f","observation_id":"153ec97c-fd3e-4d18-9a0b-5c9ca365c7d4","resolution":{"observed_at":"2026-08-03T15:15:57.715296Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.790891Z","title":"Multi-instance learning by treating instances as non-i.i.d. samples,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.790891Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:9ecc66308e5dd7d0e1f825d419a3e36493f08c8cd76dbfd0cddfaa8b5205a904","observation_id":"8e2d70c6-4ecc-408a-8ddb-7a0cd48544d3","resolution":{"observed_at":"2026-08-03T15:15:57.790891Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.848514Z","title":"Multiple instance active learning for object detection,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.848514Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:eef9f206f0c2aacd25e8ee050fcea6864d740c03fa0c2431cc5f3fba2f15ba45","observation_id":"53445523-2c72-460e-add5-239122dd7707","resolution":{"observed_at":"2026-08-03T15:15:57.848514Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.921691Z","title":"Unbiased multiple instance learning for weakly supervised video anomaly detection,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.921691Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:e715ed139720958445958ae94a877d5b2f810818e50f68c1b044631ba1caf8ce","observation_id":"ec6abafb-1c10-4ab1-a455-8053f5dd187f","resolution":{"observed_at":"2026-08-03T15:15:57.921691Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:57.996761Z","title":"Loss-based attention for deep multiple instance learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:57.996761Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:47e8e6bb19aeb06db2d7f243f4528537dcb07e396f90464fd31efbc555e69382","observation_id":"e8e632f7-f191-40ae-988a-f0850483772a","resolution":{"observed_at":"2026-08-03T15:15:57.996761Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:58.067290Z","title":"Bayes-MIL: A new probabilistic perspective on attention-based multiple instance learning for whole slide im- ages,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:58.067290Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:9d6335f68b7c2f831ffcaa77c2ceca8b49ef7ea6e7be1c5555d7e4d1f8e65317","observation_id":"2855a46c-11f9-43f0-af4c-2676228f3b80","resolution":{"observed_at":"2026-08-03T15:15:58.067290Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:58.202380Z","title":"CAMIL: context-aware multiple instance learning for cancer detection and subtyping in whole slide images,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:58.202380Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:44559c27cf7ef4bbe91d8ca94c96851a77dcb1a9d7e8cea386951789680e83df","observation_id":"ce9bcfde-02dd-42c8-9a2c-0b8e6bdd77df","resolution":{"observed_at":"2026-08-03T15:15:58.202380Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:58.328932Z","title":"Inherently interpretable time series classification via multiple instance learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:58.328932Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:1318bc9845b3fef966d188c70c2cda8e858b6b3ae41d2e581861baa709fc6a8f","observation_id":"43c9b572-016e-48f0-894f-e91755c0cd21","resolution":{"observed_at":"2026-08-03T15:15:58.328932Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:58.510841Z","title":"GM-PLL: Graph matching based partial label learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:58.510841Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:4acee595086af87fda7c57aac8b93e6d3f2f465c851afff774be2207f003df60","observation_id":"15e75563-273e-4d77-a742-a2f04268db55","resolution":{"observed_at":"2026-08-03T15:15:58.510841Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:58.654572Z","title":"Deep discriminative CNN with temporal ensembling for ambiguously- labeled image classification,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:58.654572Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:3f011fa6725077971a250881c949cfcb3387f4408aef3ebaac3304f8c3300be8","observation_id":"a693cb82-123e-4d71-81ca-4631da8d572f","resolution":{"observed_at":"2026-08-03T15:15:58.654572Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:58.773588Z","title":"A conditional multinomial mixture model for superset label learning,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:58.773588Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:a3b80d3a943328631f611e3935246b5cf54c7b7bb864c5b6ee4a41f12f9706a8","observation_id":"6967d70d-4bbb-43ce-8869-5aa2fa4c23e8","resolution":{"observed_at":"2026-08-03T15:15:58.773588Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2506.05027","last_updated":"2025-06-05T13:37:33Z","snapshot_observed_at":"2026-08-07T17:31:41.184428Z","submitted_at":"2025-06-05T13:37:33Z","title":"Tuning the Right Foundation Models is What you Need for Partial Label Learning","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2506.05027","snapshot_observed_at":"2026-08-03T15:15:58.930970Z","title":"Tuning the right foun- dation models is what you need for partial label learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:58.930970Z"},"links":{"cited_paper":"/paper/2506.05027","citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:9bc7cecf2e795f218a28b99744cafd6c65c138b23aea6ed2c805fda1d8e40ac3","observation_id":"356584c4-fdb1-4677-9664-3ba12e017f15","resolution":{"observed_at":"2026-08-03T15:15:58.930970Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:59.080051Z","title":"Rank-loss support instance machines for MIML instance annotation,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:59.080051Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:8d97a622aaded2f46873c388833b58cfcaa2fa41670b0a0de4831e2a1cc0b88a","observation_id":"cc8023cd-4895-4034-94d6-0a72fe11ea2d","resolution":{"observed_at":"2026-08-03T15:15:59.080051Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:59.264560Z","title":"Semi-supervised partial label learning via confidence-rated margin maximization,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:59.264560Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:7a489afa0cc06fd7e9d2c2c6c3105633289ed8631745cc1ad054ca11132f20f5","observation_id":"c2648239-72e7-4dc3-9abb-837af3458e0f","resolution":{"observed_at":"2026-08-03T15:15:59.264560Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:59.488749Z","title":"Adaptive graph guided disambiguation for partial label learning,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:59.488749Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:a978a170e96326e38e19783051e02cf5d0e57980d6f049eb7939948bcf95b838","observation_id":"5c8be261-8988-4a6a-b0dc-332b83f7315b","resolution":{"observed_at":"2026-08-03T15:15:59.488749Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:59.573588Z","title":"Provably consistent partial-label learning,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:59.573588Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:8519c6ecdc61f19267b4091376e19cc06b5f9a53e405f317fb736912592556d3","observation_id":"7a03d39e-4b06-4983-84c7-571bdb4b3833","resolution":{"observed_at":"2026-08-03T15:15:59.573588Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:59.752596Z","title":"Leveraged weighted loss for partial label learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:59.752596Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:0c9dd2297809b0182560f8faea00e05e2b987a67dc964497c66700bdf7f4cfba","observation_id":"d8874336-d350-4286-9f0d-30cea2412cf4","resolution":{"observed_at":"2026-08-03T15:15:59.752596Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:59.855747Z","title":"Realistic evaluation of deep partial-label learning algorithms,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:59.855747Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:01f6acfe460c59cba28bb3465e8a881217510fe0940ec193244a463880b055dd","observation_id":"fd4dcce7-d4d3-4156-a47f-fd083a76945f","resolution":{"observed_at":"2026-08-03T15:15:59.855747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:15:59.977880Z","title":"ProMIPL: A probabilistic generative model for multi-instance partial-label learning,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-03T15:15:59.977880Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:ed91334ac7235f72651561f7447227c14a3c001c59b8b7b96b1c4d23bdc451fc","observation_id":"9107d511-e344-42a1-b30d-e008bfdb0487","resolution":{"observed_at":"2026-08-03T15:15:59.977880Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:00.134761Z","title":"Fast multi-instance partial- label learning,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:00.134761Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:cc09a7a6e36ad47bf8fd575d5c84311a941fb336e092aeea28f27b5b0a92c0db","observation_id":"cb7224d1-b4fe-48d7-bfa8-6902a6bbb926","resolution":{"observed_at":"2026-08-03T15:16:00.134761Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:00.236467Z","title":"On learning latent models with multi-instance weak supervision,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:00.236467Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:e9e2986459cf0b78d6751856cf33d23e17e7e442fd5e60e13fff5117f3ae3db5","observation_id":"101ebbe5-529b-41e4-9dfd-0fcc3e5c5f2e","resolution":{"observed_at":"2026-08-03T15:16:00.236467Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:00.333350Z","title":"On calibration of modern neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:00.333350Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:0dfddff9c373fbbb8e31229c70b2cfb6df20afb3e4134e5ec63d05db22a062bc","observation_id":"57b87ea2-922a-49c6-b3c6-99fd5c6726e6","resolution":{"observed_at":"2026-08-03T15:16:00.333350Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:00.456258Z","title":"When does label smoothing help?","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:00.456258Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:9f53aec7608e551c130ac39214e8a21115ccbccbbf8fc652947f0d18e84946a1","observation_id":"9b40c762-050e-4aba-a1fa-d9af5a51e518","resolution":{"observed_at":"2026-08-03T15:16:00.456258Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:00.494425Z","title":"Rethinking calibration of deep neural networks: Do not be afraid of overconfidence,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:00.494425Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:d487758db85c064f2a0cffac61d63f7532ae887db1e85f7d7a431fad9328dec3","observation_id":"c0b502ef-595b-4fa4-a151-a7265e050ed1","resolution":{"observed_at":"2026-08-03T15:16:00.494425Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:00.572652Z","title":"On mixup training: Improved calibration and predictive uncertainty for deep neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:00.572652Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:2ddd20ea1d60f35dd9871dad23a4b01e50d820b723bbe7f604fb8b9414603392","observation_id":"6ec2fd45-6d13-493a-a5b5-1492f226ffb6","resolution":{"observed_at":"2026-08-03T15:16:00.572652Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:00.628459Z","title":"When and how mixup improves calibration,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:00.628459Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:71207c895c991134f7a4f0af1f9d4f3a3e6b9235ec89733662eb0885ba0eca30","observation_id":"fa45a71f-bb5e-4824-80df-ad99247ef2e5","resolution":{"observed_at":"2026-08-03T15:16:00.628459Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:00.790578Z","title":"Calibrating deep neural networks using focal loss,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:00.790578Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:71be90b594de730f37554cd17e38a603465a7e45a8efb355b5b520541373d96b","observation_id":"e801244e-dc6a-4a01-8cd7-2a4090547fd3","resolution":{"observed_at":"2026-08-03T15:16:00.790578Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:00.914321Z","title":"Dual focal loss for calibration,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:00.914321Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:3354ead979435b55a564c7ef6234e4ff77a80f4253a4b51304561183973fb2b2","observation_id":"732551fa-5c77-4845-b8f3-da155649d393","resolution":{"observed_at":"2026-08-03T15:16:00.914321Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:01.032878Z","title":"Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods,","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:01.032878Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:0add7405fe89d301dec5ac7941cf1c6fc1025407bf5a2e9d65923d5229ecaf35","observation_id":"c4279ab6-cc9b-4c08-bef9-714e9e9bf548","resolution":{"observed_at":"2026-08-03T15:16:01.032878Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:01.199494Z","title":"Post-hoc uncertainty calibration for domain drift scenarios,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:01.199494Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:8c87c0c86fb4fb68c979047dad3d5afe5395aae9bc42f1edf315ffa85fb267db","observation_id":"bd17843b-7307-4ef5-9b71-055b049105e6","resolution":{"observed_at":"2026-08-03T15:16:01.199494Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:01.263117Z","title":"On the pitfall of mixup for uncertainty calibration,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:01.263117Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:118f2681475f124391e4e055f22fb3358ff8ef21a1423dad33f28d686d35b3a1","observation_id":"cdf086e0-1267-468f-ac6a-500f12a09276","resolution":{"observed_at":"2026-08-03T15:16:01.263117Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:01.323869Z","title":"Calibration bottleneck: Over- compressed representations are less calibratable,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:01.323869Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:3ef33dbec65f7cb35b8b8b3805dd8cc084a136880eb346fd0c4219e67328b6b8","observation_id":"739d38c0-1225-4a01-a58f-2fa0a6faf1f1","resolution":{"observed_at":"2026-08-03T15:16:01.323869Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:01.376488Z","title":"Focal loss for dense object detection,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:01.376488Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:92d994d062d2a88dea04b1515222b7b5769803daaf0b515899c8528fec05a16f","observation_id":"8967de49-bb9e-4123-84d8-62876f4bb080","resolution":{"observed_at":"2026-08-03T15:16:01.376488Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:01.451114Z","title":"Gradient-based learning applied to document recognition,","venue":null,"work_id":null,"year":1998},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:01.451114Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:f608103e1a8f8441946da4239b7c8769d50c8f0e716a1c92d683c39117c46b3b","observation_id":"dea9aaee-5bb0-4baa-bf27-32336062a4c6","resolution":{"observed_at":"2026-08-03T15:16:01.451114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1708.07747","last_updated":"2017-09-15T21:29:49Z","snapshot_observed_at":"2026-07-06T05:56:41.814255Z","submitted_at":"2017-08-25T14:01:29Z","title":"Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1708.07747","snapshot_observed_at":"2026-08-03T15:16:01.536345Z","title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:01.536345Z"},"links":{"cited_paper":"/paper/1708.07747","citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:081f4746655ac569f2b6ab74356ef1979c0676ab48684f7d7a9b35949f82aefd","observation_id":"8a53ba8b-0503-4189-ab18-4b727de707e1","resolution":{"observed_at":"2026-08-03T15:16:01.536345Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-03T15:16:01.640866Z","title":"Multiple-instance active learn- ing,","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning","version":2},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-03T15:16:01.640866Z"},"links":{"citing_paper":"/paper/2512.17788"},"observation_digest":"sha256:70da874a025bfcc07aa97f917c626e293793f50ad29df17396dc44012e8278de","observation_id":"4f919f61-e4f7-4be9-ba09-02a38f446714","resolution":{"observed_at":"2026-08-03T15:16:01.640866Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2512.17788","last_updated":"2026-07-14T13:00:08Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-06T16:21:16.398611Z","submitted_at":"2025-12-19T16:58:31Z","title":"Calibratable Disambiguation Loss for Multi-Instance Partial-Label Learning"},"reference_resolution":{"displayed":60,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":60,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":60},"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 60 of 60 outbound references and 0 inbound Pith citation observations for arXiv:2512.17788."}