{"as_of":"2026-08-16T08:56:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:23bcaf12ac273a74bca1630f4cfd82eca3a9bcd559ae4a3c6e2966c78a754339","coverage":[{"denominator":29,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":29,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:57:57.559749Z","state":"measured"},{"denominator":29,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":29,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+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/1908.02095/citation-record","integrity":"/paper/1908.02095/integrity","json":"/paper/1908.02095/citation-record.json","paper":"/paper/1908.02095"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:57:57.889023Z","title":"Visualizing and understanding convolu- tional networks,","venue":null,"work_id":"fe4bb657-479d-4770-a52e-b0d83054a1ce","year":2014},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.456081Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:aa575b061dea485fdaf04a5825c694c70400ebc260ac89fb92773747b5810964","observation_id":"d2b92e62-0a8a-4017-85fc-853f41472077","resolution":{"observed_at":"2026-08-14T14:57:57.892628Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.879076Z","title":"ImageNet classification with deep convolutional neural networks,","venue":null,"work_id":"e0c43aa3-6ffc-4dbd-aaba-b54646832d68","year":2012},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.460165Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:a4eb6a11ac00359d491377529369178a4f9b57b00d073b96015afae813f8d660","observation_id":"41efe5da-9afc-41a8-899a-529bdea66771","resolution":{"observed_at":"2026-08-14T14:57:57.882909Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1409.1556","last_updated":"2015-04-10T16:25:04Z","snapshot_observed_at":"2026-08-14T23:20:42.336514Z","submitted_at":"2014-09-04T19:48:04Z","title":"Very Deep Convolutional Networks for Large-Scale Image Recognition","version":6},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1409.1556","snapshot_observed_at":"2026-08-14T14:57:57.463960Z","title":"Very deep convolutional networks for large-scale image recognition,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.463960Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:5465d2ab218dea66fe843664744b4137f9560634949916a20440dc085189a119","observation_id":"b14139ff-8cf8-48e4-8b46-03feaed95e6a","resolution":{"observed_at":"2026-08-14T14:57:57.463960Z","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":"2026-08-14T14:57:57.869247Z","title":"Going deeper with convolutions,","venue":null,"work_id":"8cedbfc3-9cf4-451c-a90b-d9f6df5df088","year":2015},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.467707Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:bcb9174a28367a773cd881047841db787754955fc2d411cd217c1eb43cf001d2","observation_id":"9c010776-fef1-40a2-a424-14ed5200a44f","resolution":{"observed_at":"2026-08-14T14:57:57.872621Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.858754Z","title":"Rich feature hierarchies for accurate object detection and semantic segmentation,","venue":null,"work_id":"362b768d-ca19-4c78-8e6e-a2f820df2bf0","year":2014},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.471892Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:554ddba42c7d4dfb79c9d44a530659b96a38a19677f608da689a578ffc9494e2","observation_id":"16379bab-0cdb-4e23-a486-60055c41ad20","resolution":{"observed_at":"2026-08-14T14:57:57.862916Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.847906Z","title":"Fully convolutional networks for semantic segmentation,","venue":null,"work_id":"90b92f60-2e83-47bb-8792-343d68b1a054","year":2015},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.475804Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:fc4c113452b50d1eed22d2026de01b6b424e357cf8f72c07c418489356bae1e7","observation_id":"c8fab4e0-3c33-4595-bf5f-81d7ac2f23d3","resolution":{"observed_at":"2026-08-14T14:57:57.851631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.837851Z","title":"A survey on deep learning in medical image analysis,","venue":null,"work_id":"9a6af2a6-abe3-4ef8-be93-569538569a50","year":2017},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.479962Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:58eb87e9dd8c7285d2cbae4209d6c666aae73f822ea44609194c8fc5b79e191a","observation_id":"22b464b4-9345-4971-be3f-e1993c9a71d7","resolution":{"observed_at":"2026-08-14T14:57:57.841631Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.827586Z","title":"U-net: Convolutional networks for biomedical image segmentation,","venue":null,"work_id":"c59f79d8-1692-42be-93bd-17a1b7168911","year":2015},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.483689Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:92c9831258a330ac6c9c2e70b6e650a3c1e39e1dadb455f3302c5a3527b9fc9b","observation_id":"a4e277ba-1d55-4b98-b7fc-da8f45e98df2","resolution":{"observed_at":"2026-08-14T14:57:57.831220Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.816925Z","title":"DCAN: Deep contour-aware networks for object instance segmentation from histology images,","venue":null,"work_id":"2879f57a-0cfe-41cd-b47a-3a9772673003","year":2017},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.487226Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:d7be7c6c559fff5a8215ad07fed4c51485d9664b9c8e0bb870261fb09e9fa3fc","observation_id":"d29bee55-e4cb-4810-91c2-4b96c3b91238","resolution":{"observed_at":"2026-08-14T14:57:57.820777Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.806231Z","title":"Gland instance segmentation by deep multichannel side supervision,","venue":null,"work_id":"7afe8b62-a88f-4294-9ed7-cba08d980783","year":2016},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.490801Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:34c3da09d6a414d5f71cab62f858b0f76a81f273f6714efc092295fd2f8eab47","observation_id":"a7a668ad-2007-46a0-8ea6-46277056f860","resolution":{"observed_at":"2026-08-14T14:57:57.810201Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.795676Z","title":"Gland instance segmentation using deep multichannel neural networks,","venue":null,"work_id":"446019cc-bca4-4daa-8cef-837851bad3dc","year":2017},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.494288Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:fa72f27230ae9c04db5d2f32c5e0b929f8405188021ac3c51074fc365de8714f","observation_id":"1aa3dbeb-b82c-4934-bb56-1220bbf0a94a","resolution":{"observed_at":"2026-08-14T14:57:57.799739Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.785453Z","title":"A decision-theoretic generalization of on-line learning and an application to boosting,","venue":null,"work_id":"a6e40a8b-646c-4fbe-9588-1505fe47afdd","year":1997},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.497587Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:4f760b6290a929b085c27e606b831ccfac61f1db4eb4198f5ad44e89edabeae3","observation_id":"a010fcb3-6365-4419-8788-dc62f5cc4e41","resolution":{"observed_at":"2026-08-14T14:57:57.789109Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.775122Z","title":"Auto-context and its application to high-level vision tasks and 3D brain image segmentation,","venue":null,"work_id":"de50e57f-ba09-4f21-9d5b-983cc6f54c49","year":2010},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.501370Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:93b399529b3fb369eac7386c5f1bca1932b52ac4681edb79bc8b8e0a3368ff41","observation_id":"2b63850b-470f-4545-a4f4-08952491745f","resolution":{"observed_at":"2026-08-14T14:57:57.778834Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.764765Z","title":"Iterative instance segmentation,","venue":null,"work_id":"4f597e79-9060-4663-ab8f-793054e944aa","year":2016},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.505000Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:38fd93e7b3fe0f56b968ee5e9de776115d6dfab13fa04c1d7387d80155f9d1f6","observation_id":"f49798fc-f8a9-4546-a5f8-a22aff279659","resolution":{"observed_at":"2026-08-14T14:57:57.768245Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.754454Z","title":"Boundary-aware fully convolutional network for brain tumor segmentation,","venue":null,"work_id":"b94db62c-a9a8-466b-b209-1b0d71efb1fb","year":2017},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.508359Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:ae4b53e385ed6ea675b66fff2abdbdc0380f65b73dc6b3ad56005a4b8c1749da","observation_id":"167a57b8-ac77-4964-9f4b-234569481cfb","resolution":{"observed_at":"2026-08-14T14:57:57.758273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.743708Z","title":"Detect, replace, refine: Deep structured prediction for pixel wise labeling,","venue":null,"work_id":"3d705fd6-8956-415e-9015-ce9d096b2ca5","year":2017},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.511974Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:8b7a1a969b938bbc7fc9a275408298c86cccaf61cce4420a827d507fd6ced92c","observation_id":"08cc9284-d3d1-48b4-a7e8-b0480a6da02e","resolution":{"observed_at":"2026-08-14T14:57:57.747527Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1705.07450","last_updated":"2017-08-18T22:22:28Z","snapshot_observed_at":"2026-08-14T20:59:16.931661Z","submitted_at":"2017-05-21T13:56:03Z","title":"Image Segmentation by Iterative Inference from Conditional Score Estimation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1705.07450","snapshot_observed_at":"2026-08-14T14:57:57.515262Z","title":"Image segmentation by iterative inference from conditional score estimation,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.515262Z"},"links":{"cited_paper":"/paper/1705.07450","citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:559f388e70a7e3cb5673e28dcba18b4532aa7629f9f0053cceb887a0c5ee5e23","observation_id":"2956e144-cb21-470a-8d43-5d71a64a0ecb","resolution":{"observed_at":"2026-08-14T14:57:57.515262Z","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":"2026-08-14T14:57:57.732961Z","title":"Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture,","venue":null,"work_id":"c630b5af-17fc-465c-8160-825cdb018bf1","year":2015},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.520057Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:45f5092597c101e7999f7fe332909762527191ce727814f9d2eed222f53976a1","observation_id":"61a7efde-d957-4aff-8de5-37c67c5f8cad","resolution":{"observed_at":"2026-08-14T14:57:57.736854Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.722193Z","title":"SegNet: A deep convolutional encoder-decoder architecture for image segmentation,","venue":null,"work_id":"59ed16e5-d908-4159-a7ef-3ae908ecd15e","year":2017},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.523511Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:4c31632471ed491d79bd10961d0dba46fd189ec8ec86ba6231f6dad59a8681ec","observation_id":"e8eec99b-ef7f-40d5-9d94-c21fa5ea6402","resolution":{"observed_at":"2026-08-14T14:57:57.726085Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.711390Z","title":"Generalised dice overlap as a deep learning loss function for highly unbalanced segmentations,","venue":null,"work_id":"474ec702-daad-4778-b7d4-fca74b86fd7d","year":2017},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.526892Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:f19e6291066ee7b2f95ccbc52c68da28ea8f135858178526b75b148fa045234a","observation_id":"e065d8ba-78fd-4c47-8b2f-bccbcfc0f05d","resolution":{"observed_at":"2026-08-14T14:57:57.715184Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.700675Z","title":"Focal loss for dense object detection,","venue":null,"work_id":"9af35954-72eb-476c-ade1-bc1f0fbef738","year":2017},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.530426Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:af0968f19761620696aa25a2ceab21960ee10f8c4fd3046be44653883704687c","observation_id":"1da35a51-55f6-4926-ae07-4747d6a1f081","resolution":{"observed_at":"2026-08-14T14:57:57.704659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.689320Z","title":"Boosting neural networks,","venue":null,"work_id":"26b8e81e-3007-4567-ac4e-102115e405cf","year":2000},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.533952Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:2380285ef66b26360da0dd6a1fcfd66a7b81effab7d2b97c04eb1d72ee06cd8c","observation_id":"dbf294d1-440c-408e-8952-2c3f9d6e2acc","resolution":{"observed_at":"2026-08-14T14:57:57.693266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.677610Z","title":"Incremental learning of convolutional neural networks,","venue":null,"work_id":"73b803be-f648-403e-a87f-43872d0ad1e4","year":2009},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.537330Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:824eefc2dab52b407b61653ac0075f9f7a261711b680cf6a287cf801adfc2ef3","observation_id":"210fd121-9b0f-46d1-ac93-0cf0a5a45fac","resolution":{"observed_at":"2026-08-14T14:57:57.681551Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.666820Z","title":"Convolutional neural network based sentiment analysis using adaboost combination,","venue":null,"work_id":"826bd631-f6e6-4cea-8eb7-26325acb83da","year":2016},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.540693Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:f7dfd671ef60f152b33df0c972ff9c979249809a538f0981062472be43e1fd5c","observation_id":"5b3a1939-97f4-4e5d-ba09-e2e4eb2f2a1a","resolution":{"observed_at":"2026-08-14T14:57:57.670861Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.656028Z","title":"Robust object rep- resentation by boosting-like deep learning architecture,","venue":null,"work_id":"21160bca-bc70-4e4c-9526-572f75615f62","year":2016},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.544135Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:adab654d2c5fe53220c4636c0d10690fcf6598a62acb56e7de81eb5d4a1b5f6a","observation_id":"0477e34a-c4e6-4331-8fee-c18272696fbc","resolution":{"observed_at":"2026-08-14T14:57:57.659860Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.645186Z","title":"Incremental boosting convolutional neural network for facial action unit recognition,","venue":null,"work_id":"ced196d0-4120-4572-96d2-08f06f6eb3aa","year":2016},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.548287Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:8747d3712fb97b9628081f87ec37dff0adccfc72e33e5d3543ca2374d520a40e","observation_id":"a03e0b7b-1689-44a9-b292-e712f2522a68","resolution":{"observed_at":"2026-08-14T14:57:57.649002Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-14T14:57:57.633831Z","title":"Dropout: a simple way to prevent neural networks from overfit- ting,","venue":null,"work_id":"b2e8aa12-1cd2-4bef-b506-78ab26164499","year":1929},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.551876Z"},"links":{"citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:50d882be2bb3b8bb640d49742523d89579d0e2ebcd15f5fe1ae1cfe815d4ac68","observation_id":"370c5551-314b-45df-abd7-497ec9be2b36","resolution":{"observed_at":"2026-08-14T14:57:57.637911Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1212.5701","last_updated":"2012-12-22T15:46:49Z","snapshot_observed_at":"2026-08-15T00:34:41.793608Z","submitted_at":"2012-12-22T15:46:49Z","title":"ADADELTA: An Adaptive Learning Rate Method","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1212.5701","snapshot_observed_at":"2026-08-14T14:57:57.555489Z","title":"Adadelta: an adaptive learning rate method,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.555489Z"},"links":{"cited_paper":"/paper/1212.5701","citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:7545c95e25a40356e3ef98f9228a5060354c04e2f2d3a2a11a3eb262efc22af6","observation_id":"85b20977-a1fa-4e71-abaa-a87f22907ac9","resolution":{"observed_at":"2026-08-14T14:57:57.555489Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1603.00275","last_updated":"2016-09-01T14:18:51Z","snapshot_observed_at":"2026-08-15T19:50:27.556684Z","submitted_at":"2016-03-01T13:53:48Z","title":"Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest","version":2},"cited_work":{"arxiv_id":"1603.00275","doi":null,"metadata_source":"pith","pith_arxiv_id":"1603.00275","snapshot_observed_at":"2026-08-14T14:57:57.589184Z","title":"Gland Segmentation in Colon Histology Images: The GlaS Challenge Contest","venue":"cs.CV","work_id":"7382d57f-c4e4-4796-a1df-47f4a2cf65b4","year":2016},"citing_paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:57:57.559749Z"},"links":{"cited_paper":"/paper/1603.00275","citing_paper":"/paper/1908.02095"},"observation_digest":"sha256:df7c6d0328919bee69e1606ed2a2b41f147203d277ff2d1b6a58e62b59e2247e","observation_id":"cd81ecf8-2836-4d04-9be3-d25619dcd937","resolution":{"observed_at":"2026-08-14T14:57:57.595147Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"1908.02095","last_updated":"2019-08-06T12:06:12Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T03:36:37.717930Z","submitted_at":"2019-08-06T12:06:12Z","title":"AttentionBoost: Learning What to Attend by Boosting Fully Convolutional Networks"},"reference_resolution":{"displayed":29,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":3,"verified_exact":1,"verified_fuzzy":25},"total_outbound_references":29},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 29 of 29 outbound references and 0 inbound Pith citation observations for arXiv:1908.02095."}