{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RRMPMTB4S5IJCEFYPRMDGUITP7","short_pith_number":"pith:RRMPMTB4","schema_version":"1.0","canonical_sha256":"8c58f64c3c97509110b87c583351137fdaaa3b58889cc3dc6c80cb5bcd004cad","source":{"kind":"arxiv","id":"2607.20326","version":1},"attestation_state":"computed","paper":{"title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fang Ren, Guanxiang Mao, Jiwei Jiang, Shuang Hao, Xuchen Zhu, Yajuan Wei","submitted_at":"2026-07-22T16:12:27Z","abstract_excerpt":"RGB-D semantic segmentation has achieved remarkable progress, yet most models assume that RGB and depth are always available. In practice, failures or occlusions of surveillance sensors often remove one modality. Although RGB or depth alone can contain sufficient cues, models trained only on full-modality inputs fail to exploit the remaining modality once one is missing, causing severe degradation. We tackle this issue with a simple continued-training paradigm, \\emph{Condition Dropout (ConD)}, which mitigates degradation while preserving full-modality accuracy. Starting from a pretrained RGB-D"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.20326","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-22T16:12:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6d0c0de133a6e3d978ec9f6b5b6f9462fa6571e781f5822d080eacf0223ccaa7","abstract_canon_sha256":"2ccc603840c3f7432457e648c3753a4642e41b1a9a179b69146a93f53dd2b7e2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T01:25:14.553943Z","signature_b64":"ThDM/HTePQ3rFo2X/jy811NPN0XbfhQ2M/eYgxujIP1i1y8dxZk756f8i8V+vMEmKBZPxKmOUDpP+Uu4eTRpAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c58f64c3c97509110b87c583351137fdaaa3b58889cc3dc6c80cb5bcd004cad","last_reissued_at":"2026-07-23T01:25:14.553124Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T01:25:14.553124Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Reliable RGB-D Semantic Segmentation: Handling Missing Modalities via Condition Dropout","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Fang Ren, Guanxiang Mao, Jiwei Jiang, Shuang Hao, Xuchen Zhu, Yajuan Wei","submitted_at":"2026-07-22T16:12:27Z","abstract_excerpt":"RGB-D semantic segmentation has achieved remarkable progress, yet most models assume that RGB and depth are always available. In practice, failures or occlusions of surveillance sensors often remove one modality. Although RGB or depth alone can contain sufficient cues, models trained only on full-modality inputs fail to exploit the remaining modality once one is missing, causing severe degradation. We tackle this issue with a simple continued-training paradigm, \\emph{Condition Dropout (ConD)}, which mitigates degradation while preserving full-modality accuracy. Starting from a pretrained RGB-D"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20326","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2607.20326/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.20326","created_at":"2026-07-23T01:25:14.553554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.20326v1","created_at":"2026-07-23T01:25:14.553554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20326","created_at":"2026-07-23T01:25:14.553554+00:00"},{"alias_kind":"pith_short_12","alias_value":"RRMPMTB4S5IJ","created_at":"2026-07-23T01:25:14.553554+00:00"},{"alias_kind":"pith_short_16","alias_value":"RRMPMTB4S5IJCEFY","created_at":"2026-07-23T01:25:14.553554+00:00"},{"alias_kind":"pith_short_8","alias_value":"RRMPMTB4","created_at":"2026-07-23T01:25:14.553554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RRMPMTB4S5IJCEFYPRMDGUITP7","json":"https://pith.science/pith/RRMPMTB4S5IJCEFYPRMDGUITP7.json","graph_json":"https://pith.science/api/pith-number/RRMPMTB4S5IJCEFYPRMDGUITP7/graph.json","events_json":"https://pith.science/api/pith-number/RRMPMTB4S5IJCEFYPRMDGUITP7/events.json","paper":"https://pith.science/paper/RRMPMTB4"},"agent_actions":{"view_html":"https://pith.science/pith/RRMPMTB4S5IJCEFYPRMDGUITP7","download_json":"https://pith.science/pith/RRMPMTB4S5IJCEFYPRMDGUITP7.json","view_paper":"https://pith.science/paper/RRMPMTB4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.20326&json=true","fetch_graph":"https://pith.science/api/pith-number/RRMPMTB4S5IJCEFYPRMDGUITP7/graph.json","fetch_events":"https://pith.science/api/pith-number/RRMPMTB4S5IJCEFYPRMDGUITP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RRMPMTB4S5IJCEFYPRMDGUITP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RRMPMTB4S5IJCEFYPRMDGUITP7/action/storage_attestation","attest_author":"https://pith.science/pith/RRMPMTB4S5IJCEFYPRMDGUITP7/action/author_attestation","sign_citation":"https://pith.science/pith/RRMPMTB4S5IJCEFYPRMDGUITP7/action/citation_signature","submit_replication":"https://pith.science/pith/RRMPMTB4S5IJCEFYPRMDGUITP7/action/replication_record"}},"created_at":"2026-07-23T01:25:14.553554+00:00","updated_at":"2026-07-23T01:25:14.553554+00:00"}