{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AZSRTZI7MRV6QIJ62E6PJXT7JC","short_pith_number":"pith:AZSRTZI7","schema_version":"1.0","canonical_sha256":"066519e51f646be8213ed13cf4de7f48bcf6a841dcf76ec8417db807d17f0b7e","source":{"kind":"arxiv","id":"2503.12780","version":1},"attestation_state":"computed","paper":{"title":"LangDA: Building Context-Awareness via Language for Domain Adaptive Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexander Wong, Bavesh Balaji, Chang Liu, C Thomas, Kwei-Herng Lai, Raviteja Vemulapalli, Saad Hossain, Sirisha Rambhatla","submitted_at":"2025-03-17T03:33:28Z","abstract_excerpt":"Unsupervised domain adaptation for semantic segmentation (DASS) aims to transfer knowledge from a label-rich source domain to a target domain with no labels. Two key approaches in DASS are (1) vision-only approaches using masking or multi-resolution crops, and (2) language-based approaches that use generic class-wise prompts informed by target domain (e.g. \"a {snowy} photo of a {class}\"). However, the former is susceptible to noisy pseudo-labels that are biased to the source domain. The latter does not fully capture the intricate spatial relationships of objects -- key for dense prediction tas"},"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":"2503.12780","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T03:33:28Z","cross_cats_sorted":["cs.AI","cs.LG","eess.IV","stat.ML"],"title_canon_sha256":"6294b2d2bc2bc4560c84b37912f60a86ac6b686dccc8c4db227b4ffd28ee3284","abstract_canon_sha256":"48f59960625ddbe429dc66f1a96289dd5339e544ae46b3c8976d755f8ed77df1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:32:46.000391Z","signature_b64":"MZwqekTuKAuzzrens7CK/lTDZ5YDXMu+3r4kDqFCEspGW2DO3WFDGGNjTrPk063T1mhO0d8mo52Bo1CGdnFfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"066519e51f646be8213ed13cf4de7f48bcf6a841dcf76ec8417db807d17f0b7e","last_reissued_at":"2026-07-05T10:32:45.999603Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:32:45.999603Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LangDA: Building Context-Awareness via Language for Domain Adaptive Semantic Segmentation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.IV","stat.ML"],"primary_cat":"cs.CV","authors_text":"Alexander Wong, Bavesh Balaji, Chang Liu, C Thomas, Kwei-Herng Lai, Raviteja Vemulapalli, Saad Hossain, Sirisha Rambhatla","submitted_at":"2025-03-17T03:33:28Z","abstract_excerpt":"Unsupervised domain adaptation for semantic segmentation (DASS) aims to transfer knowledge from a label-rich source domain to a target domain with no labels. Two key approaches in DASS are (1) vision-only approaches using masking or multi-resolution crops, and (2) language-based approaches that use generic class-wise prompts informed by target domain (e.g. \"a {snowy} photo of a {class}\"). However, the former is susceptible to noisy pseudo-labels that are biased to the source domain. The latter does not fully capture the intricate spatial relationships of objects -- key for dense prediction tas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12780","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/2503.12780/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":"2503.12780","created_at":"2026-07-05T10:32:45.999689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.12780v1","created_at":"2026-07-05T10:32:45.999689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12780","created_at":"2026-07-05T10:32:45.999689+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZSRTZI7MRV6","created_at":"2026-07-05T10:32:45.999689+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZSRTZI7MRV6QIJ6","created_at":"2026-07-05T10:32:45.999689+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZSRTZI7","created_at":"2026-07-05T10:32:45.999689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03365","citing_title":"Dual-Foundation Models for Unsupervised Domain Adaptation","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZSRTZI7MRV6QIJ62E6PJXT7JC","json":"https://pith.science/pith/AZSRTZI7MRV6QIJ62E6PJXT7JC.json","graph_json":"https://pith.science/api/pith-number/AZSRTZI7MRV6QIJ62E6PJXT7JC/graph.json","events_json":"https://pith.science/api/pith-number/AZSRTZI7MRV6QIJ62E6PJXT7JC/events.json","paper":"https://pith.science/paper/AZSRTZI7"},"agent_actions":{"view_html":"https://pith.science/pith/AZSRTZI7MRV6QIJ62E6PJXT7JC","download_json":"https://pith.science/pith/AZSRTZI7MRV6QIJ62E6PJXT7JC.json","view_paper":"https://pith.science/paper/AZSRTZI7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.12780&json=true","fetch_graph":"https://pith.science/api/pith-number/AZSRTZI7MRV6QIJ62E6PJXT7JC/graph.json","fetch_events":"https://pith.science/api/pith-number/AZSRTZI7MRV6QIJ62E6PJXT7JC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZSRTZI7MRV6QIJ62E6PJXT7JC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZSRTZI7MRV6QIJ62E6PJXT7JC/action/storage_attestation","attest_author":"https://pith.science/pith/AZSRTZI7MRV6QIJ62E6PJXT7JC/action/author_attestation","sign_citation":"https://pith.science/pith/AZSRTZI7MRV6QIJ62E6PJXT7JC/action/citation_signature","submit_replication":"https://pith.science/pith/AZSRTZI7MRV6QIJ62E6PJXT7JC/action/replication_record"}},"created_at":"2026-07-05T10:32:45.999689+00:00","updated_at":"2026-07-05T10:32:45.999689+00:00"}