{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:4QT3GLV3TNB3UHZRCJE73QPULS","short_pith_number":"pith:4QT3GLV3","schema_version":"1.0","canonical_sha256":"e427b32ebb9b43ba1f311249fdc1f45c875f10d5e14155138fda584f4bc0fa73","source":{"kind":"arxiv","id":"2506.20841","version":1},"attestation_state":"computed","paper":{"title":"FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ha Min Son, Shahbaz Rezaei, Xin Liu","submitted_at":"2025-06-25T21:25:05Z","abstract_excerpt":"Semi-supervised domain generalization (SSDG) aims to solve the problem of generalizing to out-of-distribution data when only a few labels are available. Due to label scarcity, applying domain generalization methods often underperform. Consequently, existing SSDG methods combine semi-supervised learning methods with various regularization terms. However, these methods do not explicitly regularize to learn domains invariant representations across all domains, which is a key goal for domain generalization. To address this, we introduce FixCLR. Inspired by success in self-supervised learning, we c"},"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":"2506.20841","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-25T21:25:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7363a1aa0261ce5490453a83502dee1caec01dd7f198005ea8c03350f976bbe1","abstract_canon_sha256":"bc90d4bdd6a32a4cbd81ff6534d424d58bae5b25e84b6eaeb37ede28f85d0baf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:34.963661Z","signature_b64":"xjp/kqTMutszqfNbxPn147Vu7VPrGgrab3ulLmEqpkko2at9AiIk8wzSs/JXB2xH8r9GWwzFyCsvf+6q98A5CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e427b32ebb9b43ba1f311249fdc1f45c875f10d5e14155138fda584f4bc0fa73","last_reissued_at":"2026-07-05T11:27:34.963155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:34.963155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FixCLR: Negative-Class Contrastive Learning for Semi-Supervised Domain Generalization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Ha Min Son, Shahbaz Rezaei, Xin Liu","submitted_at":"2025-06-25T21:25:05Z","abstract_excerpt":"Semi-supervised domain generalization (SSDG) aims to solve the problem of generalizing to out-of-distribution data when only a few labels are available. Due to label scarcity, applying domain generalization methods often underperform. Consequently, existing SSDG methods combine semi-supervised learning methods with various regularization terms. However, these methods do not explicitly regularize to learn domains invariant representations across all domains, which is a key goal for domain generalization. To address this, we introduce FixCLR. Inspired by success in self-supervised learning, we c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20841","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/2506.20841/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":"2506.20841","created_at":"2026-07-05T11:27:34.963209+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20841v1","created_at":"2026-07-05T11:27:34.963209+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20841","created_at":"2026-07-05T11:27:34.963209+00:00"},{"alias_kind":"pith_short_12","alias_value":"4QT3GLV3TNB3","created_at":"2026-07-05T11:27:34.963209+00:00"},{"alias_kind":"pith_short_16","alias_value":"4QT3GLV3TNB3UHZR","created_at":"2026-07-05T11:27:34.963209+00:00"},{"alias_kind":"pith_short_8","alias_value":"4QT3GLV3","created_at":"2026-07-05T11:27:34.963209+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/4QT3GLV3TNB3UHZRCJE73QPULS","json":"https://pith.science/pith/4QT3GLV3TNB3UHZRCJE73QPULS.json","graph_json":"https://pith.science/api/pith-number/4QT3GLV3TNB3UHZRCJE73QPULS/graph.json","events_json":"https://pith.science/api/pith-number/4QT3GLV3TNB3UHZRCJE73QPULS/events.json","paper":"https://pith.science/paper/4QT3GLV3"},"agent_actions":{"view_html":"https://pith.science/pith/4QT3GLV3TNB3UHZRCJE73QPULS","download_json":"https://pith.science/pith/4QT3GLV3TNB3UHZRCJE73QPULS.json","view_paper":"https://pith.science/paper/4QT3GLV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20841&json=true","fetch_graph":"https://pith.science/api/pith-number/4QT3GLV3TNB3UHZRCJE73QPULS/graph.json","fetch_events":"https://pith.science/api/pith-number/4QT3GLV3TNB3UHZRCJE73QPULS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4QT3GLV3TNB3UHZRCJE73QPULS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4QT3GLV3TNB3UHZRCJE73QPULS/action/storage_attestation","attest_author":"https://pith.science/pith/4QT3GLV3TNB3UHZRCJE73QPULS/action/author_attestation","sign_citation":"https://pith.science/pith/4QT3GLV3TNB3UHZRCJE73QPULS/action/citation_signature","submit_replication":"https://pith.science/pith/4QT3GLV3TNB3UHZRCJE73QPULS/action/replication_record"}},"created_at":"2026-07-05T11:27:34.963209+00:00","updated_at":"2026-07-05T11:27:34.963209+00:00"}