{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KZUYRZEMH56PQJHO5D3BUG6Q6Q","short_pith_number":"pith:KZUYRZEM","schema_version":"1.0","canonical_sha256":"566988e48c3f7cf824eee8f61a1bd0f42f0b4954c898ec95b31769e6c79f8405","source":{"kind":"arxiv","id":"2505.12861","version":2},"attestation_state":"computed","paper":{"title":"RMMSS: Towards Advanced Robust Multi-Modal Semantic Segmentation with Hybrid Prototype Distillation and Feature Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Tan, Xu Zheng, Yang Liu","submitted_at":"2025-05-19T08:46:03Z","abstract_excerpt":"Multi-modal semantic segmentation (MMSS) faces significant challenges in real-world applications due to incomplete, degraded, or missing sensor data. While current MMSS methods typically use self-distillation with modality dropout to improve robustness, they largely overlook inter-modal correlations and thus suffer significant performance degradation when no modalities are missing. To this end, we present RMMSS, a two-stage framework designed to progressively enhance model robustness under missing-modality conditions, while maintaining strong performance in full-modality scenarios. It comprise"},"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":"2505.12861","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-19T08:46:03Z","cross_cats_sorted":[],"title_canon_sha256":"96ff3d14faa3347a9d79ef0a4931eeebdd3a97ca4179394577a3f84c92638b9f","abstract_canon_sha256":"1d0a72d7854cf74bf91c4d15acbfbd3b5e567e0d520363065ee63d6983d13cc7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:55:19.377848Z","signature_b64":"5skoABoU6vlhfngLEhZNRllQEIycy/tAUuK90DsEzKkGJedTpTIDKH5Fz994CzmskoP+lwNX4WPvQKDlFFTQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"566988e48c3f7cf824eee8f61a1bd0f42f0b4954c898ec95b31769e6c79f8405","last_reissued_at":"2026-07-05T11:55:19.377435Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:55:19.377435Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RMMSS: Towards Advanced Robust Multi-Modal Semantic Segmentation with Hybrid Prototype Distillation and Feature Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiaqi Tan, Xu Zheng, Yang Liu","submitted_at":"2025-05-19T08:46:03Z","abstract_excerpt":"Multi-modal semantic segmentation (MMSS) faces significant challenges in real-world applications due to incomplete, degraded, or missing sensor data. While current MMSS methods typically use self-distillation with modality dropout to improve robustness, they largely overlook inter-modal correlations and thus suffer significant performance degradation when no modalities are missing. To this end, we present RMMSS, a two-stage framework designed to progressively enhance model robustness under missing-modality conditions, while maintaining strong performance in full-modality scenarios. It comprise"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12861","kind":"arxiv","version":2},"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/2505.12861/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":"2505.12861","created_at":"2026-07-05T11:55:19.377489+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.12861v2","created_at":"2026-07-05T11:55:19.377489+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12861","created_at":"2026-07-05T11:55:19.377489+00:00"},{"alias_kind":"pith_short_12","alias_value":"KZUYRZEMH56P","created_at":"2026-07-05T11:55:19.377489+00:00"},{"alias_kind":"pith_short_16","alias_value":"KZUYRZEMH56PQJHO","created_at":"2026-07-05T11:55:19.377489+00:00"},{"alias_kind":"pith_short_8","alias_value":"KZUYRZEM","created_at":"2026-07-05T11:55:19.377489+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/KZUYRZEMH56PQJHO5D3BUG6Q6Q","json":"https://pith.science/pith/KZUYRZEMH56PQJHO5D3BUG6Q6Q.json","graph_json":"https://pith.science/api/pith-number/KZUYRZEMH56PQJHO5D3BUG6Q6Q/graph.json","events_json":"https://pith.science/api/pith-number/KZUYRZEMH56PQJHO5D3BUG6Q6Q/events.json","paper":"https://pith.science/paper/KZUYRZEM"},"agent_actions":{"view_html":"https://pith.science/pith/KZUYRZEMH56PQJHO5D3BUG6Q6Q","download_json":"https://pith.science/pith/KZUYRZEMH56PQJHO5D3BUG6Q6Q.json","view_paper":"https://pith.science/paper/KZUYRZEM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.12861&json=true","fetch_graph":"https://pith.science/api/pith-number/KZUYRZEMH56PQJHO5D3BUG6Q6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/KZUYRZEMH56PQJHO5D3BUG6Q6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KZUYRZEMH56PQJHO5D3BUG6Q6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KZUYRZEMH56PQJHO5D3BUG6Q6Q/action/storage_attestation","attest_author":"https://pith.science/pith/KZUYRZEMH56PQJHO5D3BUG6Q6Q/action/author_attestation","sign_citation":"https://pith.science/pith/KZUYRZEMH56PQJHO5D3BUG6Q6Q/action/citation_signature","submit_replication":"https://pith.science/pith/KZUYRZEMH56PQJHO5D3BUG6Q6Q/action/replication_record"}},"created_at":"2026-07-05T11:55:19.377489+00:00","updated_at":"2026-07-05T11:55:19.377489+00:00"}