{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4CP7T3PPMSP5N4VWPOBPVYTZDD","short_pith_number":"pith:4CP7T3PP","schema_version":"1.0","canonical_sha256":"e09ff9edef649fd6f2b67b82fae27918ef16edc47054417785e01e008f5fed69","source":{"kind":"arxiv","id":"1908.03884","version":3},"attestation_state":"computed","paper":{"title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jogendra Nath Kundu, Nishank Lakkakula, R. Venkatesh Babu","submitted_at":"2019-08-11T10:52:07Z","abstract_excerpt":"Aiming towards human-level generalization, there is a need to explore adaptable representation learning methods with greater transferability. Most existing approaches independently address task-transferability and cross-domain adaptation, resulting in limited generalization. In this paper, we propose UM-Adapt - a unified framework to effectively perform unsupervised domain adaptation for spatially-structured prediction tasks, simultaneously maintaining a balanced performance across individual tasks in a multi-task setting. To realize this, we propose two novel regularization strategies; a) Con"},"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":"1908.03884","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-08-11T10:52:07Z","cross_cats_sorted":[],"title_canon_sha256":"666ab006b997375af751ac1aa238dfa1209dc1765b35b21a44f7e31b66d4bb8d","abstract_canon_sha256":"2d50b002bb746135d0e38d321c6254074308504827acf6937bd967aebafa6074"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:04:43.854033Z","signature_b64":"J7o0/tYDRNyBPv6OWLl0pAGVx9zMv0Q2Vn3wdCKDnusgRfDP7eB/2/RRXca/8Y2YSFgTPIYilEZaaLKem+JBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e09ff9edef649fd6f2b67b82fae27918ef16edc47054417785e01e008f5fed69","last_reissued_at":"2026-07-05T00:04:43.853621Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:04:43.853621Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UM-Adapt: Unsupervised Multi-Task Adaptation Using Adversarial Cross-Task Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jogendra Nath Kundu, Nishank Lakkakula, R. Venkatesh Babu","submitted_at":"2019-08-11T10:52:07Z","abstract_excerpt":"Aiming towards human-level generalization, there is a need to explore adaptable representation learning methods with greater transferability. Most existing approaches independently address task-transferability and cross-domain adaptation, resulting in limited generalization. In this paper, we propose UM-Adapt - a unified framework to effectively perform unsupervised domain adaptation for spatially-structured prediction tasks, simultaneously maintaining a balanced performance across individual tasks in a multi-task setting. To realize this, we propose two novel regularization strategies; a) Con"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.03884","kind":"arxiv","version":3},"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/1908.03884/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":"1908.03884","created_at":"2026-07-05T00:04:43.853676+00:00"},{"alias_kind":"arxiv_version","alias_value":"1908.03884v3","created_at":"2026-07-05T00:04:43.853676+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.03884","created_at":"2026-07-05T00:04:43.853676+00:00"},{"alias_kind":"pith_short_12","alias_value":"4CP7T3PPMSP5","created_at":"2026-07-05T00:04:43.853676+00:00"},{"alias_kind":"pith_short_16","alias_value":"4CP7T3PPMSP5N4VW","created_at":"2026-07-05T00:04:43.853676+00:00"},{"alias_kind":"pith_short_8","alias_value":"4CP7T3PP","created_at":"2026-07-05T00:04:43.853676+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/4CP7T3PPMSP5N4VWPOBPVYTZDD","json":"https://pith.science/pith/4CP7T3PPMSP5N4VWPOBPVYTZDD.json","graph_json":"https://pith.science/api/pith-number/4CP7T3PPMSP5N4VWPOBPVYTZDD/graph.json","events_json":"https://pith.science/api/pith-number/4CP7T3PPMSP5N4VWPOBPVYTZDD/events.json","paper":"https://pith.science/paper/4CP7T3PP"},"agent_actions":{"view_html":"https://pith.science/pith/4CP7T3PPMSP5N4VWPOBPVYTZDD","download_json":"https://pith.science/pith/4CP7T3PPMSP5N4VWPOBPVYTZDD.json","view_paper":"https://pith.science/paper/4CP7T3PP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1908.03884&json=true","fetch_graph":"https://pith.science/api/pith-number/4CP7T3PPMSP5N4VWPOBPVYTZDD/graph.json","fetch_events":"https://pith.science/api/pith-number/4CP7T3PPMSP5N4VWPOBPVYTZDD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4CP7T3PPMSP5N4VWPOBPVYTZDD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4CP7T3PPMSP5N4VWPOBPVYTZDD/action/storage_attestation","attest_author":"https://pith.science/pith/4CP7T3PPMSP5N4VWPOBPVYTZDD/action/author_attestation","sign_citation":"https://pith.science/pith/4CP7T3PPMSP5N4VWPOBPVYTZDD/action/citation_signature","submit_replication":"https://pith.science/pith/4CP7T3PPMSP5N4VWPOBPVYTZDD/action/replication_record"}},"created_at":"2026-07-05T00:04:43.853676+00:00","updated_at":"2026-07-05T00:04:43.853676+00:00"}