{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:PYFXKIN4EDL3CTKTLW7CKUUZAX","short_pith_number":"pith:PYFXKIN4","schema_version":"1.0","canonical_sha256":"7e0b7521bc20d7b14d535dbe25529905da34c8f7a9f14b52e72ae3dfa7545cd0","source":{"kind":"arxiv","id":"2602.19423","version":4},"attestation_state":"computed","paper":{"title":"Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Prefer-DAS adapts electron microscopy segmentation across domains by aligning local human preferences with sparse prompts.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiabao Chen, Jialin Peng, Shan Xiong","submitted_at":"2026-02-23T01:39:03Z","abstract_excerpt":"Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive annotated data in each domain. However, the prevalent unsupervised domain adaptation (UDA) strategies often demonstrate limited and biased performance, which hinders their practical applications. In this study, we explore sparse points and local human preferences as weak labels in the target domain, thereby presenting a more realistic yet annotation-efficient setting. Specifically, we develop Prefer-DAS, which pioneers"},"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":true},"canonical_record":{"source":{"id":"2602.19423","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-23T01:39:03Z","cross_cats_sorted":[],"title_canon_sha256":"72409e91d49227d8bc856e3a1e3a1f47d842fafa2c6e6bbffe39c7e8f8654ea5","abstract_canon_sha256":"3d93c7ed408c0f5f5e65d98c3a2675e3c19d7d31ffad5000b0deb409a77a85bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:39.735271Z","signature_b64":"TNVc/KT8yv4wEwA/mima9b+VfY1BesSh79GawZOq3nn1mdHcDcEhErb+ndHcjucIFUcy5SSiwwOg/vk9lwFcBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7e0b7521bc20d7b14d535dbe25529905da34c8f7a9f14b52e72ae3dfa7545cd0","last_reissued_at":"2026-05-20T00:01:39.734590Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:39.734590Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Prefer-DAS: Learning from Local Preferences and Sparse Prompts for Domain Adaptive Segmentation of Electron Microscopy","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"Prefer-DAS adapts electron microscopy segmentation across domains by aligning local human preferences with sparse prompts.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jiabao Chen, Jialin Peng, Shan Xiong","submitted_at":"2026-02-23T01:39:03Z","abstract_excerpt":"Domain adaptive segmentation (DAS) is a promising paradigm for delineating intracellular structures from various large-scale electron microscopy (EM) without incurring extensive annotated data in each domain. However, the prevalent unsupervised domain adaptation (UDA) strategies often demonstrate limited and biased performance, which hinders their practical applications. In this study, we explore sparse points and local human preferences as weak labels in the target domain, thereby presenting a more realistic yet annotation-efficient setting. Specifically, we develop Prefer-DAS, which pioneers"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"the Prefer-DAS model can effectively perform both weakly-supervised and unsupervised DAS, depending on the availability of points and human preferences. Comprehensive experiments on four challenging DAS tasks demonstrate that our model outperforms SAM-like methods as well as unsupervised and weakly-supervised DAS methods in both automatic and interactive segmentation modes, highlighting strong generalizability and flexibility. Additionally, the performance of our model is very close to or even exceeds that of supervised models.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Local human preferences provide reliable, spatially consistent signals that can be aligned via LPO/SLPO without introducing bias or noise that degrades segmentation accuracy, and that UPO can safely substitute when feedback is missing.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Prefer-DAS integrates sparse promptable learning with local direct preference optimization and unsupervised variants to achieve strong domain adaptive segmentation performance in electron microscopy, outperforming prior unsupervised and weakly-supervised methods while approaching supervised results.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Prefer-DAS adapts electron microscopy segmentation across domains by aligning local human preferences with sparse prompts.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"edc65242801451b5fc9d141aed9a3d832bc3b7d83779235d44c1e98e2f319ef3"},"source":{"id":"2602.19423","kind":"arxiv","version":4},"verdict":{"id":"ad557e63-239f-4d4f-afc4-e1dd920c3b01","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T21:04:33.611759Z","strongest_claim":"the Prefer-DAS model can effectively perform both weakly-supervised and unsupervised DAS, depending on the availability of points and human preferences. Comprehensive experiments on four challenging DAS tasks demonstrate that our model outperforms SAM-like methods as well as unsupervised and weakly-supervised DAS methods in both automatic and interactive segmentation modes, highlighting strong generalizability and flexibility. Additionally, the performance of our model is very close to or even exceeds that of supervised models.","one_line_summary":"Prefer-DAS integrates sparse promptable learning with local direct preference optimization and unsupervised variants to achieve strong domain adaptive segmentation performance in electron microscopy, outperforming prior unsupervised and weakly-supervised methods while approaching supervised results.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Local human preferences provide reliable, spatially consistent signals that can be aligned via LPO/SLPO without introducing bias or noise that degrades segmentation accuracy, and that UPO can safely substitute when feedback is missing.","pith_extraction_headline":"Prefer-DAS adapts electron microscopy segmentation across domains by aligning local human preferences with sparse prompts."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2602.19423/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":1,"snapshot_sha256":"233729160be4396e7c128c33a56dadb53398e9044c1185a8534436becbf44617"},"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":"2602.19423","created_at":"2026-05-20T00:01:39.734700+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.19423v4","created_at":"2026-05-20T00:01:39.734700+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.19423","created_at":"2026-05-20T00:01:39.734700+00:00"},{"alias_kind":"pith_short_12","alias_value":"PYFXKIN4EDL3","created_at":"2026-05-20T00:01:39.734700+00:00"},{"alias_kind":"pith_short_16","alias_value":"PYFXKIN4EDL3CTKT","created_at":"2026-05-20T00:01:39.734700+00:00"},{"alias_kind":"pith_short_8","alias_value":"PYFXKIN4","created_at":"2026-05-20T00:01:39.734700+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PYFXKIN4EDL3CTKTLW7CKUUZAX","json":"https://pith.science/pith/PYFXKIN4EDL3CTKTLW7CKUUZAX.json","graph_json":"https://pith.science/api/pith-number/PYFXKIN4EDL3CTKTLW7CKUUZAX/graph.json","events_json":"https://pith.science/api/pith-number/PYFXKIN4EDL3CTKTLW7CKUUZAX/events.json","paper":"https://pith.science/paper/PYFXKIN4"},"agent_actions":{"view_html":"https://pith.science/pith/PYFXKIN4EDL3CTKTLW7CKUUZAX","download_json":"https://pith.science/pith/PYFXKIN4EDL3CTKTLW7CKUUZAX.json","view_paper":"https://pith.science/paper/PYFXKIN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.19423&json=true","fetch_graph":"https://pith.science/api/pith-number/PYFXKIN4EDL3CTKTLW7CKUUZAX/graph.json","fetch_events":"https://pith.science/api/pith-number/PYFXKIN4EDL3CTKTLW7CKUUZAX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PYFXKIN4EDL3CTKTLW7CKUUZAX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PYFXKIN4EDL3CTKTLW7CKUUZAX/action/storage_attestation","attest_author":"https://pith.science/pith/PYFXKIN4EDL3CTKTLW7CKUUZAX/action/author_attestation","sign_citation":"https://pith.science/pith/PYFXKIN4EDL3CTKTLW7CKUUZAX/action/citation_signature","submit_replication":"https://pith.science/pith/PYFXKIN4EDL3CTKTLW7CKUUZAX/action/replication_record"}},"created_at":"2026-05-20T00:01:39.734700+00:00","updated_at":"2026-05-20T00:01:39.734700+00:00"}