{"as_of":"2026-08-10T01:18:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d18f9e02a50c83938e0cb639c1fb8069bca08fbddc1fff95117b530cb302901a","coverage":[{"denominator":24,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":24,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T10:12:03.269851Z","state":"measured"},{"denominator":24,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":24,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2607.20326/citation-record","integrity":"/paper/2607.20326/integrity","json":"/paper/2607.20326/citation-record.json","paper":"/paper/2607.20326"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T10:12:01.200997Z","title":"Dcanet: Differential convolution attention network for rgb-d semantic segmentation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:01.200997Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:bcadd63e26d18e1a64efbd12fbcbce8c57add9519cf62d1952856ad70f9b6024","observation_id":"af647eed-eefb-4003-92f7-99b70cceea4f","resolution":{"observed_at":"2026-08-01T10:12:01.200997Z","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":"2026-08-01T10:12:01.326490Z","title":"Esenet-d: Efficient semantic segmentation for rgb-depth food images,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:01.326490Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:30d4d612419619c220e8f370460b17e68a6b9d485a6b786f2ca2e6f624ffaf14","observation_id":"28aaa90c-5ba0-42e5-91ed-f876bbcecdbf","resolution":{"observed_at":"2026-08-01T10:12:01.326490Z","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":"2026-08-01T10:12:01.445784Z","title":"Asymformer: Asymmetrical cross-modal representation learning for mobile platform real-time rgb-d semantic segmentation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:01.445784Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:953110845ae65af2d3c579cd3288615588deb2fa79cc3efd72aecb843c483b3c","observation_id":"61eeb62e-85a3-4cdb-ae4b-6e3dfd9fa647","resolution":{"observed_at":"2026-08-01T10:12:01.445784Z","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":"2026-08-01T10:12:01.569122Z","title":"Non-local aggregation for rgb-d semantic segmentation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:01.569122Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:db9de8f9ea8968ed87d338973840d9c45208482d0a0fc0ebb74c546075499bdd","observation_id":"c2b10c52-679f-4fc7-b6b9-0e3fab6e3130","resolution":{"observed_at":"2026-08-01T10:12:01.569122Z","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":"2026-08-01T10:12:01.695419Z","title":"Acnet: Attention based network to exploit complementary features for rgbd semantic seg- mentation,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:01.695419Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:5d91700b0e88d510cca16615ae57143cea68a10234476b6830f164463052bf7f","observation_id":"9636d6ff-9f31-400c-a4db-5fbb918a5784","resolution":{"observed_at":"2026-08-01T10:12:01.695419Z","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":"2026-08-01T10:12:01.805895Z","title":"A brief survey on rgb-d semantic segmentation using deep learning,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:01.805895Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:3fcaca850e26c568790d5e32c502aa55b1bc644463ea814dd446b09554d43925","observation_id":"eb102586-ead6-434e-b382-6bf681017311","resolution":{"observed_at":"2026-08-01T10:12:01.805895Z","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":"2026-08-01T10:12:01.926845Z","title":"Depth-aware cnn for rgb-d segmentation,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:01.926845Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:27f2928f11a60ac9d0432d14b3f082067e241230fdb2bdad53dfd5b251c1617b","observation_id":"22237cb4-84c0-4509-b85b-8ffb54b59ce5","resolution":{"observed_at":"2026-08-01T10:12:01.926845Z","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":"2026-08-01T10:12:02.103275Z","title":"Learning rich features from rgb-d images for object detection and segmentation,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:02.103275Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:50e2c0276de763073f5d6a923d99faaf84b192a877b29214940b5070717d8843","observation_id":"cf8443c4-ed96-4330-ba64-8bac2e3a061f","resolution":{"observed_at":"2026-08-01T10:12:02.103275Z","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":"2026-08-01T10:12:02.147568Z","title":"Spcformer: spatial perception correction transformer for semantic segmentation of scene parsing: F. lu et al.,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:02.147568Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:1e11b54b9d5583a25b9ceae6992804bce2a8b6c190492a1ff3e953f1bcbaa166","observation_id":"58912301-efe1-497a-90e8-ccec4692afd0","resolution":{"observed_at":"2026-08-01T10:12:02.147568Z","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":"2026-08-01T10:12:02.316148Z","title":"Fully convolu- tional networks for semantic segmentation,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:02.316148Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:d9b7f05230dec957fbfdc5480419e10bab193099b0b2b71d5737c7c278304724","observation_id":"e06f066a-25ca-43bd-ab96-b33ad8c92538","resolution":{"observed_at":"2026-08-01T10:12:02.316148Z","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":"2026-08-01T10:12:02.458486Z","title":"U-net: Convo- lutional networks for biomedical image segmentation,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:02.458486Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:4ecbb67128dcf524ae64b12ef6d1d1582cddd03c8a5a1237314e79e0903e453d","observation_id":"6b3ccb3d-ba95-46e6-84df-4f9750c12040","resolution":{"observed_at":"2026-08-01T10:12:02.458486Z","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":"2026-08-01T10:12:02.670099Z","title":"Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:02.670099Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:ac4cd0da51323ba99ade5173d14d74c42756962eb93e5061933fccd1b6f2e48c","observation_id":"4ad92f00-daf7-4498-9957-45a492eee752","resolution":{"observed_at":"2026-08-01T10:12:02.670099Z","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":"2026-08-01T10:12:02.878927Z","title":"Benchmarking multi-modal semantic segmentation under sensor fail- ures: Missing and noisy modality robustness,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:02.878927Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:663f97becf4b1b60107af3fac17b0e3f7e0431e2c74a775ad218c6be9c648e30","observation_id":"d49c23a5-5ea9-4026-93f6-a76010b781b0","resolution":{"observed_at":"2026-08-01T10:12:02.878927Z","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":"2026-08-01T10:12:02.938117Z","title":"Missing modality robustness in semi-supervised multi-modal semantic segmentation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:02.938117Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:7851f8901d1333690243f39e9c570c7ab425f892dc92d34079c4e00e9b1b8926","observation_id":"819528b1-5906-4b15-bd53-b322372d1d6c","resolution":{"observed_at":"2026-08-01T10:12:02.938117Z","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":"2026-08-01T10:12:03.008485Z","title":"Mask- mentor: Unlocking the potential of masked self-teaching for missing modality rgb-d semantic segmentation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.008485Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:dcde5c4414f0e35be44ab412c8cfaed8a8a6cc05a34b0fd33c5f22656197fe40","observation_id":"abf907e2-0c01-4c3c-8207-c230a9a41157","resolution":{"observed_at":"2026-08-01T10:12:03.008485Z","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":"2026-08-01T10:12:03.092642Z","title":"Mmpl-seg: Prompt learning with missing modalities for medical segmentation,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.092642Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:adf49af8fb521a3fde9f0c19e30162cc48aba3d936ce8070a382df3e4b1468cb","observation_id":"212125e2-ccfb-45a6-9254-c61ba310c426","resolution":{"observed_at":"2026-08-01T10:12:03.092642Z","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":"2026-08-01T10:12:03.139809Z","title":"Towards robust multimodal sentiment analysis under uncertain signal missing,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.139809Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:8e819ec5794e8bdc4f4add5253fbbb54db06d4409217ca6cd202017c1ec2e69d","observation_id":"4d890958-81e6-44a4-b2ce-67cc98507de0","resolution":{"observed_at":"2026-08-01T10:12:03.139809Z","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":"2026-08-01T10:12:03.169044Z","title":"Mitigating modality discrepancies for rgb-t semantic segmentation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.169044Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:677beb12ef8b9b9392fa68b152af9d0b0cc38901f54f3d9c2711518a1f34f549","observation_id":"f9e1a2cd-1efd-42d9-a0fe-2a46f41f5322","resolution":{"observed_at":"2026-08-01T10:12:03.169044Z","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":"2026-08-01T10:12:03.181709Z","title":"Cola: Conditional dropout and language-driven robust dual-modal salient object detection,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.181709Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:e11ca3ad49b7a104de38ea7f872045babc329bdf6a28a90c0b0bec09d751d6c2","observation_id":"b8ff11fb-8034-4531-ab01-4f999d284df1","resolution":{"observed_at":"2026-08-01T10:12:03.181709Z","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":"2026-08-01T10:12:03.232313Z","title":"Adding conditional control to text-to-image diffusion models,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.232313Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:ade10cd72cc875d1da3a9db0407c5cd78132126646c765e2d46c24e798f40422","observation_id":"ca51251e-a332-4b6a-b682-3094021bd265","resolution":{"observed_at":"2026-08-01T10:12:03.232313Z","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":"2026-08-01T10:12:03.255339Z","title":"Indoor segmentation and support inference from rgbd images,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.255339Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:fc99f89ceb98b9887115c881b27c286bd491e58d250ad1aad019334d3a0912b2","observation_id":"4d790484-a4ac-449d-9b3d-620fad219e58","resolution":{"observed_at":"2026-08-01T10:12:03.255339Z","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":"2026-08-01T10:12:03.260114Z","title":"Sun rgb-d: A rgb-d scene understanding benchmark suite,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.260114Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:ed4076ebe423d35675446bccdcf2f4e756d3804f9b8ebec42e8f944557f93747","observation_id":"217e4c19-3fc9-4b8c-aa0d-aafeee331d3c","resolution":{"observed_at":"2026-08-01T10:12:03.260114Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.09668","last_updated":"2024-02-07T11:07:29Z","snapshot_observed_at":"2026-07-06T16:19:53.325354Z","submitted_at":"2023-09-18T11:09:11Z","title":"DFormer: Rethinking RGBD Representation Learning for Semantic Segmentation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.09668","snapshot_observed_at":"2026-08-01T10:12:03.265043Z","title":"Dformer: Rethinking rgbd representation learning for semantic segmentation,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.265043Z"},"links":{"cited_paper":"/paper/2309.09668","citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:a7638a51ad95fabc8a73302d6f31e98096c057af5dfae0fc38d97874e30ab692","observation_id":"1e62da8a-dd83-4759-8b69-4507ec00af44","resolution":{"observed_at":"2026-08-01T10:12:03.265043Z","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":"2026-08-01T10:12:03.269851Z","title":"Sigma: Siamese mamba network for multi-modal semantic segmentation,","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T10:12:03.269851Z"},"links":{"citing_paper":"/paper/2607.20326"},"observation_digest":"sha256:58f6de320478f8f9dddb8273e9046ca18c0114a70d6e5fe089cbea0aa1248def","observation_id":"24ad7f13-ea78-4737-93c9-c16e16c1b885","resolution":{"observed_at":"2026-08-01T10:12:03.269851Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.20326","last_updated":"2026-07-22T16:12:27Z","latest_version":1,"primary_category":"cs.CV","snapshot_observed_at":"2026-08-01T10:12:00.861506Z","submitted_at":"2026-07-22T16:12:27Z","title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout"},"reference_resolution":{"displayed":24,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":24,"verified_exact":0,"verified_fuzzy":0},"total_outbound_references":24},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 24 of 24 outbound references and 0 inbound Pith citation observations for arXiv:2607.20326."}