{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:2IXQFFQ6KCXXI6ALJBOSI62XSX","short_pith_number":"pith:2IXQFFQ6","schema_version":"1.0","canonical_sha256":"d22f02961e50af74780b485d247b5795ef4bd8444c70c8308475a0961755676d","source":{"kind":"arxiv","id":"2602.01179","version":2},"attestation_state":"computed","paper":{"title":"Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fangyikang Wang, Hao Wang, Haoxuan Li, Tianqiao Liu, Yunfei Teng, Zhan Zhuang, Zhengnan Li, Zhichao Chen, Zhouchen Lin","submitted_at":"2026-02-01T12:07:54Z","abstract_excerpt":"Gradual domain adaptation (GDA) aims to mitigate domain shift by progressively adapting models from the source domain to the target domain via intermediate domains. However, real intermediate domains are often unavailable or ineffective, necessitating the synthesis of intermediate samples. Flow-based models have recently been used for this purpose by interpolating between source and target distributions. Notably, their training typically relies on sample-based log-likelihood estimation, which can discard useful information and thus degrade GDA performance. The key to addressing this limitation"},"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":"2602.01179","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-01T12:07:54Z","cross_cats_sorted":[],"title_canon_sha256":"e023b4f79a4d2f1bef346dc42abfa3ceafd3ba9e0b8fed64676e9b147974d978","abstract_canon_sha256":"870d57bc6bf9620ebe4507a44e7461d0941051f033e3185d57cb2df4da898aea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:54.358668Z","signature_b64":"IqpplB5d1cG5z7287RSzOxfrD8rJD6Ou1BZwlOWtn4J/6OY5zMPIahlGGb3+a7Udq64SmsKEINuZIajWuLJ5Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d22f02961e50af74780b485d247b5795ef4bd8444c70c8308475a0961755676d","last_reissued_at":"2026-06-10T01:09:54.357513Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:54.357513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking the Flow-Based Gradual Domain Adaptation: A Semi-Dual Optimal Transport Perspective","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Fangyikang Wang, Hao Wang, Haoxuan Li, Tianqiao Liu, Yunfei Teng, Zhan Zhuang, Zhengnan Li, Zhichao Chen, Zhouchen Lin","submitted_at":"2026-02-01T12:07:54Z","abstract_excerpt":"Gradual domain adaptation (GDA) aims to mitigate domain shift by progressively adapting models from the source domain to the target domain via intermediate domains. However, real intermediate domains are often unavailable or ineffective, necessitating the synthesis of intermediate samples. Flow-based models have recently been used for this purpose by interpolating between source and target distributions. Notably, their training typically relies on sample-based log-likelihood estimation, which can discard useful information and thus degrade GDA performance. The key to addressing this limitation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.01179","kind":"arxiv","version":2},"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/2602.01179/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":"2602.01179","created_at":"2026-06-10T01:09:54.357677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.01179v2","created_at":"2026-06-10T01:09:54.357677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.01179","created_at":"2026-06-10T01:09:54.357677+00:00"},{"alias_kind":"pith_short_12","alias_value":"2IXQFFQ6KCXX","created_at":"2026-06-10T01:09:54.357677+00:00"},{"alias_kind":"pith_short_16","alias_value":"2IXQFFQ6KCXXI6AL","created_at":"2026-06-10T01:09:54.357677+00:00"},{"alias_kind":"pith_short_8","alias_value":"2IXQFFQ6","created_at":"2026-06-10T01:09:54.357677+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/2IXQFFQ6KCXXI6ALJBOSI62XSX","json":"https://pith.science/pith/2IXQFFQ6KCXXI6ALJBOSI62XSX.json","graph_json":"https://pith.science/api/pith-number/2IXQFFQ6KCXXI6ALJBOSI62XSX/graph.json","events_json":"https://pith.science/api/pith-number/2IXQFFQ6KCXXI6ALJBOSI62XSX/events.json","paper":"https://pith.science/paper/2IXQFFQ6"},"agent_actions":{"view_html":"https://pith.science/pith/2IXQFFQ6KCXXI6ALJBOSI62XSX","download_json":"https://pith.science/pith/2IXQFFQ6KCXXI6ALJBOSI62XSX.json","view_paper":"https://pith.science/paper/2IXQFFQ6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.01179&json=true","fetch_graph":"https://pith.science/api/pith-number/2IXQFFQ6KCXXI6ALJBOSI62XSX/graph.json","fetch_events":"https://pith.science/api/pith-number/2IXQFFQ6KCXXI6ALJBOSI62XSX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2IXQFFQ6KCXXI6ALJBOSI62XSX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2IXQFFQ6KCXXI6ALJBOSI62XSX/action/storage_attestation","attest_author":"https://pith.science/pith/2IXQFFQ6KCXXI6ALJBOSI62XSX/action/author_attestation","sign_citation":"https://pith.science/pith/2IXQFFQ6KCXXI6ALJBOSI62XSX/action/citation_signature","submit_replication":"https://pith.science/pith/2IXQFFQ6KCXXI6ALJBOSI62XSX/action/replication_record"}},"created_at":"2026-06-10T01:09:54.357677+00:00","updated_at":"2026-06-10T01:09:54.357677+00:00"}