{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MKS7EZY3MZQ7O5S3LRMURMNPT4","short_pith_number":"pith:MKS7EZY3","schema_version":"1.0","canonical_sha256":"62a5f2671b6661f7765b5c5948b1af9f356368daf6cade439c562f72d7f2074c","source":{"kind":"arxiv","id":"2605.16393","version":1},"attestation_state":"computed","paper":{"title":"Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Joel Valdivia Ortega, Marion Jasnin, Tingying Peng","submitted_at":"2026-05-12T11:56:46Z","abstract_excerpt":"Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap remains for Vision Transformers (ViTs) in the field, particularly for sparse, fine-structured, and low signal-to-noise targets. We attribute this challenge in part to the lightweight pixel decoders commonly used in promptable ViT models, who may lack the local inductive bias needed for high-precision biomedical masks. We bridge this gap by introducing ViTC-UNet, which conditions a UNet on frozen pre-trained ViT representations through learnable tokens and a two-way attention decod"},"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":"2605.16393","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-12T11:56:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1d1108c35b80d5498891593be3d14d974dd55bc1419790dc3827878d9ac76c6c","abstract_canon_sha256":"59a1aa3cef83f11d5de617469fee2a34b241789085dfcec16e9cedac6667e29e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:20.065663Z","signature_b64":"2stikFpqSwjDbsYa9qU3rjfv8dZZLCy7ToOIAPDqzQKKivyilvpnfYcRCKuR2o/YT+HnMuYn2mxzWmwdmmbnAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62a5f2671b6661f7765b5c5948b1af9f356368daf6cade439c562f72d7f2074c","last_reissued_at":"2026-05-20T00:02:20.065034Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:20.065034Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision Transformer-Conditioned UNet for Domain-Adaptive Semantic Segmentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Joel Valdivia Ortega, Marion Jasnin, Tingying Peng","submitted_at":"2026-05-12T11:56:46Z","abstract_excerpt":"Semantic segmentation is essential for analysing anatomical features in biomedical research, yet a performance gap remains for Vision Transformers (ViTs) in the field, particularly for sparse, fine-structured, and low signal-to-noise targets. We attribute this challenge in part to the lightweight pixel decoders commonly used in promptable ViT models, who may lack the local inductive bias needed for high-precision biomedical masks. We bridge this gap by introducing ViTC-UNet, which conditions a UNet on frozen pre-trained ViT representations through learnable tokens and a two-way attention decod"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16393","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/2605.16393/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.607015Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"14ed8113848b57e19078415cfc399a4e1a57fd8792f467b420503da5d172ecb7"},"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":"2605.16393","created_at":"2026-05-20T00:02:20.065115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16393v1","created_at":"2026-05-20T00:02:20.065115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16393","created_at":"2026-05-20T00:02:20.065115+00:00"},{"alias_kind":"pith_short_12","alias_value":"MKS7EZY3MZQ7","created_at":"2026-05-20T00:02:20.065115+00:00"},{"alias_kind":"pith_short_16","alias_value":"MKS7EZY3MZQ7O5S3","created_at":"2026-05-20T00:02:20.065115+00:00"},{"alias_kind":"pith_short_8","alias_value":"MKS7EZY3","created_at":"2026-05-20T00:02:20.065115+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/MKS7EZY3MZQ7O5S3LRMURMNPT4","json":"https://pith.science/pith/MKS7EZY3MZQ7O5S3LRMURMNPT4.json","graph_json":"https://pith.science/api/pith-number/MKS7EZY3MZQ7O5S3LRMURMNPT4/graph.json","events_json":"https://pith.science/api/pith-number/MKS7EZY3MZQ7O5S3LRMURMNPT4/events.json","paper":"https://pith.science/paper/MKS7EZY3"},"agent_actions":{"view_html":"https://pith.science/pith/MKS7EZY3MZQ7O5S3LRMURMNPT4","download_json":"https://pith.science/pith/MKS7EZY3MZQ7O5S3LRMURMNPT4.json","view_paper":"https://pith.science/paper/MKS7EZY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16393&json=true","fetch_graph":"https://pith.science/api/pith-number/MKS7EZY3MZQ7O5S3LRMURMNPT4/graph.json","fetch_events":"https://pith.science/api/pith-number/MKS7EZY3MZQ7O5S3LRMURMNPT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MKS7EZY3MZQ7O5S3LRMURMNPT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MKS7EZY3MZQ7O5S3LRMURMNPT4/action/storage_attestation","attest_author":"https://pith.science/pith/MKS7EZY3MZQ7O5S3LRMURMNPT4/action/author_attestation","sign_citation":"https://pith.science/pith/MKS7EZY3MZQ7O5S3LRMURMNPT4/action/citation_signature","submit_replication":"https://pith.science/pith/MKS7EZY3MZQ7O5S3LRMURMNPT4/action/replication_record"}},"created_at":"2026-05-20T00:02:20.065115+00:00","updated_at":"2026-05-20T00:02:20.065115+00:00"}