{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:7DYALYTUA6DL2HSJ2YBRVDWIRE","short_pith_number":"pith:7DYALYTU","schema_version":"1.0","canonical_sha256":"f8f005e2740786bd1e49d6031a8ec889223af260b0b75ef434850ab9ecde2794","source":{"kind":"arxiv","id":"2209.14926","version":1},"attestation_state":"computed","paper":{"title":"Domain-Unified Prompt Representations for Source-Free Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Feng Zhao, Hanting Li, Hongjing Niu","submitted_at":"2022-09-29T16:44:09Z","abstract_excerpt":"Domain generalization (DG), aiming to make models work on unseen domains, is a surefire way toward general artificial intelligence. Limited by the scale and diversity of current DG datasets, it is difficult for existing methods to scale to diverse domains in open-world scenarios (e.g., science fiction and pixelate style). Therefore, the source-free domain generalization (SFDG) task is necessary and challenging. To address this issue, we propose an approach based on large-scale vision-language pretraining models (e.g., CLIP), which exploits the extensive domain information embedded in it. The p"},"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":"2209.14926","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-09-29T16:44:09Z","cross_cats_sorted":[],"title_canon_sha256":"8a12f6987a5415ef0e4d77fd6b84f29bbdf2bae5529985f8248417e19d9dcc8f","abstract_canon_sha256":"0306bc2c2173ac5f744500f44f4a9c81c6ee648c8fb81cf5517b62665bdc732b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:02:07.065413Z","signature_b64":"Ke+UtAJ6hMLMF45NvihlmeBea2q5zjIP/LPW/oLUM+Ra/kYyiE03zpwcgh2Nph9K9fwnRXkdvDe2CrAw/tUqDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8f005e2740786bd1e49d6031a8ec889223af260b0b75ef434850ab9ecde2794","last_reissued_at":"2026-07-05T05:02:07.064944Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:02:07.064944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Unified Prompt Representations for Source-Free Domain Generalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Li, Feng Zhao, Hanting Li, Hongjing Niu","submitted_at":"2022-09-29T16:44:09Z","abstract_excerpt":"Domain generalization (DG), aiming to make models work on unseen domains, is a surefire way toward general artificial intelligence. Limited by the scale and diversity of current DG datasets, it is difficult for existing methods to scale to diverse domains in open-world scenarios (e.g., science fiction and pixelate style). Therefore, the source-free domain generalization (SFDG) task is necessary and challenging. To address this issue, we propose an approach based on large-scale vision-language pretraining models (e.g., CLIP), which exploits the extensive domain information embedded in it. The p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.14926","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/2209.14926/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":"2209.14926","created_at":"2026-07-05T05:02:07.065009+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.14926v1","created_at":"2026-07-05T05:02:07.065009+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.14926","created_at":"2026-07-05T05:02:07.065009+00:00"},{"alias_kind":"pith_short_12","alias_value":"7DYALYTUA6DL","created_at":"2026-07-05T05:02:07.065009+00:00"},{"alias_kind":"pith_short_16","alias_value":"7DYALYTUA6DL2HSJ","created_at":"2026-07-05T05:02:07.065009+00:00"},{"alias_kind":"pith_short_8","alias_value":"7DYALYTU","created_at":"2026-07-05T05:02:07.065009+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08839","citing_title":"Cross-Sample Relational Fusion: Unifying Domain Generalization and Class-Incremental Learning","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7DYALYTUA6DL2HSJ2YBRVDWIRE","json":"https://pith.science/pith/7DYALYTUA6DL2HSJ2YBRVDWIRE.json","graph_json":"https://pith.science/api/pith-number/7DYALYTUA6DL2HSJ2YBRVDWIRE/graph.json","events_json":"https://pith.science/api/pith-number/7DYALYTUA6DL2HSJ2YBRVDWIRE/events.json","paper":"https://pith.science/paper/7DYALYTU"},"agent_actions":{"view_html":"https://pith.science/pith/7DYALYTUA6DL2HSJ2YBRVDWIRE","download_json":"https://pith.science/pith/7DYALYTUA6DL2HSJ2YBRVDWIRE.json","view_paper":"https://pith.science/paper/7DYALYTU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.14926&json=true","fetch_graph":"https://pith.science/api/pith-number/7DYALYTUA6DL2HSJ2YBRVDWIRE/graph.json","fetch_events":"https://pith.science/api/pith-number/7DYALYTUA6DL2HSJ2YBRVDWIRE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7DYALYTUA6DL2HSJ2YBRVDWIRE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7DYALYTUA6DL2HSJ2YBRVDWIRE/action/storage_attestation","attest_author":"https://pith.science/pith/7DYALYTUA6DL2HSJ2YBRVDWIRE/action/author_attestation","sign_citation":"https://pith.science/pith/7DYALYTUA6DL2HSJ2YBRVDWIRE/action/citation_signature","submit_replication":"https://pith.science/pith/7DYALYTUA6DL2HSJ2YBRVDWIRE/action/replication_record"}},"created_at":"2026-07-05T05:02:07.065009+00:00","updated_at":"2026-07-05T05:02:07.065009+00:00"}