{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:FHWHZML6FV7RRY5W26MPAWXB52","short_pith_number":"pith:FHWHZML6","schema_version":"1.0","canonical_sha256":"29ec7cb17e2d7f18e3b6d798f05ae1eeb407eb8ef040d9b723378d5275e82028","source":{"kind":"arxiv","id":"2605.14626","version":1},"attestation_state":"computed","paper":{"title":"UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Ding, Fei Zhou, Haoyu Wang, Lei Zhang, Mengmeng Zheng, Ping Zhou, Wei Wei","submitted_at":"2026-05-14T09:39:53Z","abstract_excerpt":"RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmentation methods usually adopt cascaded generation paradigms, decomposing joint triplet generation into local conditional processes. As a result, consistency among VIS, IR, and Label in spatial structure, semantic content, and cross-modal details cannot be reliably maintained. To address this issue, we propose UniTriGen, a unified triplet generation framework that directly generates spatially aligned, semantically cons"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.14626","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-14T09:39:53Z","cross_cats_sorted":[],"title_canon_sha256":"ebafd982cd26bee767dc5be0b95b2e45ab935b1bbd0b7a960eb10d1d2ee37ca6","abstract_canon_sha256":"6237492e6b519623a95c253ad308914b6a7e7f91d2b5bfc1c25d46347b1a437f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:04.016282Z","signature_b64":"FkoDXjDIvQvnjPZNQ7xBB1ppxnPZuBlLQWmOVzoIX5C4XWq/LPsufy8rOg8XZmMrGKUVgot7+N0bXOATpR1oDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29ec7cb17e2d7f18e3b6d798f05ae1eeb407eb8ef040d9b723378d5275e82028","last_reissued_at":"2026-05-17T23:39:04.015768Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:04.015768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniTriGen: Unified Triplet Generation of Aligned Visible-Infrared-Label for Few-Shot RGB-T Semantic Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Ding, Fei Zhou, Haoyu Wang, Lei Zhang, Mengmeng Zheng, Ping Zhou, Wei Wei","submitted_at":"2026-05-14T09:39:53Z","abstract_excerpt":"RGB-T semantic segmentation requires strictly aligned VIS-IR-Label triplets; however, such aligned triplet data are often scarce in real-world scenarios. Existing generative augmentation methods usually adopt cascaded generation paradigms, decomposing joint triplet generation into local conditional processes. As a result, consistency among VIS, IR, and Label in spatial structure, semantic content, and cross-modal details cannot be reliably maintained. To address this issue, we propose UniTriGen, a unified triplet generation framework that directly generates spatially aligned, semantically cons"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"UniTriGen generates high-quality aligned triplets from limited real paired data, thereby achieving consistent performance improvements across various RGB-T semantic segmentation models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That jointly encoding VIS, IR, and Label into a shared latent space and modeling them with a single diffusion process will reliably enforce global cross-modal consistency in spatial structure and semantics without introducing artifacts or biases.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"UniTriGen uses unified diffusion in a shared latent space plus lightweight adapters and scene-balanced sampling to produce high-quality aligned VIS-IR-Label triplets from limited paired data, improving few-shot RGB-T semantic segmentation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"4e517537d8938a00cc87bf6cea41b9a19a121b1d1e455ac11684427deb6299a1"},"source":{"id":"2605.14626","kind":"arxiv","version":1},"verdict":{"id":"12c7f69d-df97-4026-8a7f-6b958af13a7e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T05:48:18.792752Z","strongest_claim":"UniTriGen generates high-quality aligned triplets from limited real paired data, thereby achieving consistent performance improvements across various RGB-T semantic segmentation models.","one_line_summary":"UniTriGen uses unified diffusion in a shared latent space plus lightweight adapters and scene-balanced sampling to produce high-quality aligned VIS-IR-Label triplets from limited paired data, improving few-shot RGB-T semantic segmentation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That jointly encoding VIS, IR, and Label into a shared latent space and modeling them with a single diffusion process will reliably enforce global cross-modal consistency in spatial structure and semantics without introducing artifacts or biases.","pith_extraction_headline":"A single diffusion process in shared latent space generates aligned visible-infrared-label triplets from limited real pairs."},"references":{"count":41,"sample":[{"doi":"","year":2025,"title":"Textssr: diffusion-based data synthesis for scene text recognition","work_id":"de692509-a80e-4288-ad60-f9e89cda767d","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Text2earth: Unlocking text-driven remote sensing image generation with a global-scale dataset and a foundation model.IEEE Geoscience and Remote Sensing Magazine, 2025","work_id":"2c950442-15ce-4a7e-9547-c6f9d501133a","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Datasetdm: Synthesizing data with perception annotations using diffusion models","work_id":"dc70158c-0417-4ab1-ab20-51d2e8a692dc","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Dataset diffusion: Diffusion-based synthetic data generation for pixel-level semantic segmentation.Advances in Neural Information Processing Systems, 36: 76872–76892, 2023","work_id":"6759a602-891f-4a74-9230-805709de97dd","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"Pseudo-sd: pseudo controlled stable diffusion for semi-supervised and cross-domain semantic segmentation","work_id":"3f0a6b02-fe47-4e83-9d37-a87d58217680","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":41,"snapshot_sha256":"c2499e326175543b92985379b7b1a1a7d237b9d128ffb66b40fa5ce9d0b50181","internal_anchors":4},"formal_canon":{"evidence_count":2,"snapshot_sha256":"ee08563d8c4a3bde856216414d8683a8bc8ebc302843fc4e9427bb59d00ad500"},"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":"2605.14626","created_at":"2026-05-17T23:39:04.015861+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.14626v1","created_at":"2026-05-17T23:39:04.015861+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14626","created_at":"2026-05-17T23:39:04.015861+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHWHZML6FV7R","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHWHZML6FV7RRY5W","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHWHZML6","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52","json":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52.json","graph_json":"https://pith.science/api/pith-number/FHWHZML6FV7RRY5W26MPAWXB52/graph.json","events_json":"https://pith.science/api/pith-number/FHWHZML6FV7RRY5W26MPAWXB52/events.json","paper":"https://pith.science/paper/FHWHZML6"},"agent_actions":{"view_html":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52","download_json":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52.json","view_paper":"https://pith.science/paper/FHWHZML6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.14626&json=true","fetch_graph":"https://pith.science/api/pith-number/FHWHZML6FV7RRY5W26MPAWXB52/graph.json","fetch_events":"https://pith.science/api/pith-number/FHWHZML6FV7RRY5W26MPAWXB52/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52/action/storage_attestation","attest_author":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52/action/author_attestation","sign_citation":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52/action/citation_signature","submit_replication":"https://pith.science/pith/FHWHZML6FV7RRY5W26MPAWXB52/action/replication_record"}},"created_at":"2026-05-17T23:39:04.015861+00:00","updated_at":"2026-05-17T23:39:04.015861+00:00"}