{"as_of":"2026-08-16T15:45:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:5195d15a26e0256793efa025d311b1f11a9a99577a7bb04c0ff8823e30eb3931","coverage":[{"denominator":36,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":36,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-14T14:10:44.341115Z","state":"measured"},{"denominator":36,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":36,"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/1908.03675/citation-record","integrity":"/paper/1908.03675/integrity","json":"/paper/1908.03675/citation-record.json","paper":"/paper/1908.03675"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:44.699375Z","title":"Learning attribute representations with local- ization for flexible fashion search","venue":null,"work_id":"a2f58cac-ff2c-46ed-ba88-6f5e474bffd8","year":2018},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.226734Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:af57ca572e3c14295ad5344c0f3d2a2f0fe116e259c08d5836bb56a71f54901c","observation_id":"f5164b9c-103a-4c59-88bc-bc9d7c890ee9","resolution":{"observed_at":"2026-08-14T14:10:44.702829Z","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":"1807.07560","last_updated":"2019-03-28T17:04:47Z","snapshot_observed_at":"2026-08-14T18:49:52.415746Z","submitted_at":"2018-07-19T17:57:16Z","title":"Compositional GAN: Learning Image-Conditional Binary Composition","version":3},"cited_work":{"arxiv_id":"1807.07560","doi":null,"metadata_source":"pith","pith_arxiv_id":"1807.07560","snapshot_observed_at":"2026-08-14T14:10:44.411922Z","title":"Compositional GAN: Learning Image-Conditional Binary Composition","venue":"cs.CV","work_id":"675587e2-ab24-4855-be79-83c9acac185d","year":2018},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.230970Z"},"links":{"cited_paper":"/paper/1807.07560","citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:17d299015caf7221176836c4ef6d5814a7505db10bbfe70c10ebba75dd70d902","observation_id":"15992426-955e-4737-b8fb-8c97dc1bef4f","resolution":{"observed_at":"2026-08-14T14:10:44.415800Z","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:44.690458Z","title":"Spatial context in recogni- tion","venue":null,"work_id":"462789fe-6edf-440d-abc6-e4afa594642d","year":1996},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.234881Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:e32731603797572207156cbac1fe97f19c73e8aa532172d5eaa286187e17dba1","observation_id":"edd7c0db-5b0f-4ee3-a464-0580580761ea","resolution":{"observed_at":"2026-08-14T14:10:44.693451Z","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":"2026-08-14T14:10:44.682154Z","title":"PatchMatch: A randomized correspon- dence algorithm for structural image editing","venue":null,"work_id":"ca536fd6-c769-47b3-9245-db89a2ad72e2","year":2009},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.238424Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:8536c61f8c39e3efdb75bb875051d75ab1631b8c9abbfe5b1dee9527acf7cd54","observation_id":"5a8f42a7-ec7e-4fdf-a708-8d8b10b69700","resolution":{"observed_at":"2026-08-14T14:10:44.685330Z","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":"2026-08-14T14:10:44.672549Z","title":"Inside-outside net: Detecting objects in context with skip pooling and recurrent neural networks","venue":null,"work_id":"d6b08db0-9dfe-463c-93d9-35f8a3335086","year":2016},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.242046Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:c91b325d6a9d91f9ca002897639e1d5dda3c81484b921f0a10bf3967911bd60d","observation_id":"5a4dcf9a-7dd1-4ada-8774-3eea48eea136","resolution":{"observed_at":"2026-08-14T14:10:44.676082Z","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":"2026-08-14T14:10:44.661366Z","title":"An empirical study of context in object detection","venue":null,"work_id":"6047c513-09c6-42d4-9bba-2d6f7ed9be9f","year":2009},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.245392Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:3fd175882fb59cae709ba6939e1ab2b67ddbf8ac550cfddeb65c26d399f23886","observation_id":"79f2d525-0d43-4c64-b4c9-1be8e4a97542","resolution":{"observed_at":"2026-08-14T14:10:44.665388Z","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":"2026-08-14T14:10:44.651969Z","title":"Scene completion using millions of photographs","venue":null,"work_id":"15a62c00-166d-455e-a09b-ee0a7a6e89e2","year":2007},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.249010Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:e9363a1d35d4e8d2af225f6759d8fadd02bf7fa471181f975573265a534bb72f","observation_id":"c0eb7549-d9b5-4b2b-8aa0-fbc804ab074a","resolution":{"observed_at":"2026-08-14T14:10:44.655577Z","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":"2026-08-14T14:10:44.641751Z","title":"Globally and locally consistent image completion","venue":null,"work_id":"e3bad21e-82c8-4d7d-b253-b5736a6b0cee","year":2017},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.251682Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:cefd72bca9c81df9e717b7e8f3fdbfc7ff6943c0c7c2ffcea84dcf0737255f45","observation_id":"1a2fd3a7-8ebb-48f0-9566-0ff58d721ee3","resolution":{"observed_at":"2026-08-14T14:10:44.645756Z","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":"1702.08734","last_updated":"2017-02-28T10:42:31Z","snapshot_observed_at":"2026-08-14T21:14:23.253253Z","submitted_at":"2017-02-28T10:42:31Z","title":"Billion-scale similarity search with GPUs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1702.08734","snapshot_observed_at":"2026-08-14T14:10:44.254396Z","title":"Billion- scale similarity search with gpus","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.254396Z"},"links":{"cited_paper":"/paper/1702.08734","citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:42d55f33af82994b13bd2356731227f4e7fbd3d47d0c1ad731cbd9791a89a82e","observation_id":"9e81dada-6978-4f3a-ad0f-52f543d7857a","resolution":{"observed_at":"2026-08-14T14:10:44.254396Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1412.6980","last_updated":"2017-01-30T01:27:54Z","snapshot_observed_at":"2026-08-14T18:51:16.666127Z","submitted_at":"2014-12-22T13:54:29Z","title":"Adam: A Method for Stochastic Optimization","version":9},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1412.6980","snapshot_observed_at":"2026-08-14T14:10:44.257124Z","title":"Adam: A method for stochastic optimization","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.257124Z"},"links":{"cited_paper":"/paper/1412.6980","citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:d92cad32da0edbf0183bf48f58a21bf0e868d775211e513e9d57b0e978ca3647","observation_id":"f6e0e8b6-bdba-4896-8bc8-a8ff62dd88bb","resolution":{"observed_at":"2026-08-14T14:10:44.257124Z","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":"2026-08-14T14:10:44.631723Z","title":"Photo clip art","venue":null,"work_id":"77478023-cab5-42f5-97e6-0ecd7adf1cf4","year":2007},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.259908Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:075cb65552c56f9ecb2e352c268edf6bb31eaf66eb886ef3b8f25b2323c843a0","observation_id":"8d85d089-4cf1-4c27-9904-c996881c51e7","resolution":{"observed_at":"2026-08-14T14:10:44.635303Z","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":"2026-08-14T14:10:44.620921Z","title":"St-gan: Spatial transformer generative adversarial networks for image compositing","venue":null,"work_id":"b4f28adc-446c-4ff7-9cb8-c2b39ade0140","year":null},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.262404Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:dbc6a0e7525e32853f92cf4fa564704a0e266cee13fe27e8c6bf6e6176ec5c14","observation_id":"076faae5-6af6-4af3-8ca9-75889a238392","resolution":{"observed_at":"2026-08-14T14:10:44.624889Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:44.264962Z","title":"Microsoft coco: Common objects in context","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.264962Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:c5ce9bbdbad95e125d23181306b10b88de757a6c5b9d40589b7f00e8543f9d19","observation_id":"5b018e18-02cc-4cec-a0ed-7e8e89c7ace2","resolution":{"observed_at":"2026-08-14T14:10:44.264962Z","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":"2026-08-14T14:10:44.268089Z","title":"Automatic differentiation in pytorch","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.268089Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:bcb2724cf244e82df7b3d9c0c9e1492a1b5a341b82af3ff9fc0bf2a5ca9b7511","observation_id":"7502c8af-21dd-4fbb-95c7-94c0484ba8f2","resolution":{"observed_at":"2026-08-14T14:10:44.268089Z","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":"2026-08-14T14:10:44.602310Z","title":"Context encoders: Feature learning by inpainting","venue":null,"work_id":"636e75e7-66ff-478d-85a5-db038b998466","year":2016},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.270934Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:0dd405f21e4fea90b9fb895837ada1c0d5af48afaaea92238233788dec0e97a4","observation_id":"dd976cac-0ed8-4385-81f7-8f70c397681e","resolution":{"observed_at":"2026-08-14T14:10:44.605178Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:44.274072Z","title":"Pois- son image editing","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.274072Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:ed460487274eb5a898f919a804d43ac85db8b315d5596cbbff51b45a76638e03","observation_id":"481452b9-bede-4bd6-a48d-c3512bf5abaf","resolution":{"observed_at":"2026-08-14T14:10:44.274072Z","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":"2026-08-14T14:10:44.588657Z","title":"Data-driven detection of prominent objects","venue":null,"work_id":"6deba4e7-10ee-4d8f-ba4a-516f85d5b741","year":1969},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.277530Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:440dfcdff5cc04d6b99c3ade12926947f650472adb5b51cd73e90b5bbba30f3e","observation_id":"42810cf1-1569-43bc-bd27-b669caeb85af","resolution":{"observed_at":"2026-08-14T14:10:44.591533Z","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:44.281361Z","title":"Imagenet large scale visual recognition challenge","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.281361Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:b822f4b13d9c364f0fb6662f7174934492ff59b356d526bcd5bf60ba9f65d732","observation_id":"db249bd1-a614-4c03-bb4a-118b4e271a8b","resolution":{"observed_at":"2026-08-14T14:10:44.281361Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"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":"2026-08-14T14:10:44.284371Z","title":"Very deep convo- lutional networks for large-scale image recognition","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.284371Z"},"links":{"cited_paper":"/paper/1409.1556","citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:bef14c1177c2f046493d57d29da4559c8708960e1ab615fe63a8e649f3cb6a53","observation_id":"2d8817fa-3791-4504-8ef3-cef62f31c1d7","resolution":{"observed_at":"2026-08-14T14:10:44.284371Z","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":"2026-08-14T14:10:44.573789Z","title":"Context-based vi- sion: recognizing objects using information from both 2 d and 3 d imagery","venue":null,"work_id":"b84ec0b3-c097-49c8-ac69-95bcdd362276","year":1991},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.287486Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:cd1b243de18776c2aafa7e8f4a4c4eb0eaf0b1c82e7cd2767d10e48ba4185ed5","observation_id":"216da993-fa24-4c7f-aa74-c18a49a3d28e","resolution":{"observed_at":"2026-08-14T14:10:44.577106Z","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":"2026-08-14T14:10:44.564785Z","title":"Seeing what is not there: Learning context to determine where objects are missing","venue":null,"work_id":"26c19d7b-569e-4c40-9f3a-d283a9923b8c","year":2017},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.291536Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:4264c590f53b82efae60833e44018e9841f19109ea3db36d877741c5bc556e0a","observation_id":"50dd66f7-0e97-4bcd-96cc-ebc09ed8ecb7","resolution":{"observed_at":"2026-08-14T14:10:44.568284Z","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":"2026-08-14T14:10:44.555373Z","title":"Multi-scale image harmonization","venue":null,"work_id":"62bc357a-a8aa-4cf0-a6b0-8aae283c3256","year":null},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.294744Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:bf39a3692cfa9ed1830a5d1f0bd1cdb0462d5daef312f8e97158232e4a484de8","observation_id":"39eae385-9415-483d-8aae-fe8652ff6152","resolution":{"observed_at":"2026-08-14T14:10:44.558943Z","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":"2026-08-14T14:10:44.545604Z","title":"Where and who? automatic semantic-aware person composition","venue":null,"work_id":"a991915f-b800-4908-bbf9-c080244099c8","year":2018},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.298403Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:980d99392efcfc1eed6d2b8e07f035505edab88534d147221b25fe487eb9202c","observation_id":"76cf773d-ce5f-45b6-918e-edcdfc79631f","resolution":{"observed_at":"2026-08-14T14:10:44.549067Z","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":"2026-08-14T14:10:44.536040Z","title":"Error- tolerant image compositing","venue":null,"work_id":"be08c1ac-b77a-406d-903f-2c1867ccb569","year":2010},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.302154Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:9bb3e799aaba6cbffc5c223c9e7140a4735415a2c8bd22e240c41bf1651aabaf","observation_id":"544c2883-ba20-4836-963a-37fc44047aee","resolution":{"observed_at":"2026-08-14T14:10:44.539561Z","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":"2026-08-14T14:10:44.525077Z","title":"Contextual priming for object detection","venue":null,"work_id":"38f9d6fd-755b-40c0-850b-7f287f8958c6","year":2003},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.305505Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:f6d80ebdd1e5a186824340b42e78e572f1cc7a9ecb04c31d55c550d7fbe458eb","observation_id":"782ce5a7-6072-4a10-a69b-4360e33991d9","resolution":{"observed_at":"2026-08-14T14:10:44.529257Z","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":"2026-08-14T14:10:44.513739Z","title":"80 million tiny images: A large data set for nonparametric ob- ject and scene recognition","venue":null,"work_id":"9d3aea17-5f96-41ba-ab23-d1b4e7abd5d8","year":1958},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.308730Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:808bf248e4573bb84e50ef1043e41ea78459204f769593ef40fa137669deebfb","observation_id":"a043f257-4e57-43c4-940f-4ddda32b116d","resolution":{"observed_at":"2026-08-14T14:10:44.518220Z","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":"2026-08-14T14:10:44.503325Z","title":"Deep image harmonization","venue":null,"work_id":"5f7f4650-737f-4c74-b8ca-81047c802a84","year":2017},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.311929Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:f6d07e65a7b646d88e6810cce72b4cfcd1056b3b32d1fc1c3c2bfc3d01099882","observation_id":"fe801bb6-a04d-48f3-ae06-cd1dbc71ca6b","resolution":{"observed_at":"2026-08-14T14:10:44.507606Z","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":"2026-08-14T14:10:44.493698Z","title":"Unsupervised learning of visual representations using videos","venue":null,"work_id":"4bb1b767-b377-4250-b3e9-11e0a4081f4b","year":2015},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.315088Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:1d6fd37da575aa8a48c6c4f3c72ca669ace281b4147bdf8edd894f28a61cc724","observation_id":"873ec2d1-dd3d-400c-99db-97902f2363f8","resolution":{"observed_at":"2026-08-14T14:10:44.496795Z","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":"2026-08-14T14:10:44.485359Z","title":"Get out of my picture! internet-based inpainting","venue":null,"work_id":"3f2d98ef-485c-4b86-b783-57b091a23d5a","year":2009},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.319329Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:e0a6b8cafa942d28efbee6697a98b7fb30d07f37cc06fb902967321699a0d0eb","observation_id":"c49a36d6-9897-41b6-bb9d-d211cd1f64a9","resolution":{"observed_at":"2026-08-14T14:10:44.488162Z","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":"2026-08-14T14:10:44.477142Z","title":"High-resolution image inpainting using multi- scale neural patch synthesis","venue":null,"work_id":"4ab6b996-e26d-4f9f-95eb-fc3e3c1a32fe","year":2017},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.322296Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:9dc54a40e91264dc0e5f7b95c9cde037ada5aa3b25702d913b82a509eef9861a","observation_id":"479e93f5-76fe-4bc4-8a8f-d4492c972379","resolution":{"observed_at":"2026-08-14T14:10:44.480029Z","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":"2026-08-14T14:10:44.466728Z","title":"Context driven scene parsing with attention to rare classes","venue":null,"work_id":"7aa863fa-62ea-440b-b4ed-18af4d47b164","year":2014},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.325314Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:a8875c09bdc6b8859bbc4ab64a05f943ea7e0a31b1c6963742a6c105297a0630","observation_id":"45d0b61c-6b97-481e-96fa-747ba24cae02","resolution":{"observed_at":"2026-08-14T14:10:44.470391Z","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":"2026-08-14T14:10:44.456023Z","title":"Generative image inpainting with contex- tual attention","venue":null,"work_id":"3f92e4cd-a040-4b29-8225-8a77090ed400","year":2018},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.328392Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:0987d3ab4246da70788dd5bb9e2b65993f11f69cd9a451c4c3c127505d8e631e","observation_id":"df8c5e85-9f7d-4c79-949f-a4f7c96b00ae","resolution":{"observed_at":"2026-08-14T14:10:44.459742Z","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":"2026-08-14T14:10:44.445283Z","title":"Compositing-aware image search","venue":null,"work_id":"8c4f2258-1cf2-4454-8a72-624f6980bf9f","year":2018},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.331847Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:a42276dbd84b88f71cf97ab8700da9b5e862a403c64421c38c538579b2577591","observation_id":"bf973cb4-5f65-4dce-818d-c166e38af171","resolution":{"observed_at":"2026-08-14T14:10:44.449057Z","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":"1803.08435","last_updated":"2018-03-22T16:20:45Z","snapshot_observed_at":"2026-08-16T05:05:54.845212Z","submitted_at":"2018-03-22T16:20:45Z","title":"Guided Image Inpainting: Replacing an Image Region by Pulling Content from Another Image","version":1},"cited_work":{"arxiv_id":"1803.08435","doi":null,"metadata_source":"pith","pith_arxiv_id":"1803.08435","snapshot_observed_at":"2026-08-14T14:10:44.369469Z","title":"Guided Image Inpainting: Replacing an Image Region by Pulling Content from Another Image","venue":"cs.CV","work_id":"89676d21-157e-48e7-aff7-f962ff0db78b","year":2018},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.335185Z"},"links":{"cited_paper":"/paper/1803.08435","citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:9581a987de0e8f48eaa34f59b54877c57d0fbef24ad13de303537f7caa1ac11f","observation_id":"42d357df-88f9-435e-8b87-f19392f63032","resolution":{"observed_at":"2026-08-14T14:10:44.374648Z","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"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-14T14:10:44.434392Z","title":"Learning a discriminative model for the perception of realism in composite images","venue":null,"work_id":"932ebd08-2f61-4591-b023-7baf492d8174","year":2015},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.338545Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:e60aedb5f10d52dcaca0aee246830e76661a54777c32006642aa62daab26017e","observation_id":"66f65170-e167-4434-be83-f2e01b251cf5","resolution":{"observed_at":"2026-08-14T14:10:44.438194Z","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":"2026-08-14T14:10:44.423514Z","title":"Faithful completion of images of scenic landmarks using internet images","venue":null,"work_id":"117f02ee-971d-4ac4-81e1-1c590bd080a4","year":1945},"citing_paper":{"arxiv_id":"1908.03675","last_updated":"2019-08-10T02:57:04Z","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-14T14:10:44.341115Z"},"links":{"citing_paper":"/paper/1908.03675"},"observation_digest":"sha256:95dce45e496bb7718ec97ffdb5c7bcc41272e48fd7f012adf579772040adaaef","observation_id":"b9e7c48e-3d1e-47c4-b87f-e58cd3eaabea","resolution":{"observed_at":"2026-08-14T14:10:44.427176Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"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":"1908.03675","last_updated":"2019-08-10T02:57:04Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-16T04:45:12.077172Z","submitted_at":"2019-08-10T02:57:04Z","title":"Unconstrained Foreground Object Search"},"reference_resolution":{"displayed":36,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":7,"verified_exact":2,"verified_fuzzy":26},"total_outbound_references":36},"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 36 of 36 outbound references and 0 inbound Pith citation observations for arXiv:1908.03675."}