{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:GSECCUCZ2H75PJPOKIXYWBBHMU","short_pith_number":"pith:GSECCUCZ","schema_version":"1.0","canonical_sha256":"3488215059d1ffd7a5ee522f8b04276509c1222c1c183eda7c6514bdda775178","source":{"kind":"arxiv","id":"2112.12989","version":3},"attestation_state":"computed","paper":{"title":"Domain-Aware Continual Zero-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kai Yi, Mohamed Elhoseiny, Paul Janson, Wenxuan Zhang","submitted_at":"2021-12-24T08:17:18Z","abstract_excerpt":"Modern visual systems have a wide range of potential applications in vision tasks for natural science research, such as aiding in species discovery, monitoring animals in the wild, and so on. However, real-world vision tasks may experience changes in environmental conditions, leading to shifts in how captured images are presented. To address this issue, we introduce Domain-Aware Continual Zero-Shot Learning (DACZSL), a task to recognize images of unseen categories in continuously changing domains. Accordingly, we propose a Domain-Invariant Network (DIN) to learn factorized features for shiftin"},"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":"2112.12989","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-12-24T08:17:18Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"2456a293fd970d71a9406bad8998857c04a378b2df0ece37a10a085bfd127bdf","abstract_canon_sha256":"58f3c08d9e08ba940a9edf078edd9c74f814f0ab17dd9136b9565c5d20951396"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:46.441398Z","signature_b64":"sjzCXpoYL03BSvF0mfs/ChFSiZ92ni28MKz1u/mqSM5kGjexbXSZQVvuF6y0YrzeQcxr6xcgpPjS+R8VdBdfCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3488215059d1ffd7a5ee522f8b04276509c1222c1c183eda7c6514bdda775178","last_reissued_at":"2026-07-05T07:54:46.440998Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:46.440998Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Domain-Aware Continual Zero-Shot Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Kai Yi, Mohamed Elhoseiny, Paul Janson, Wenxuan Zhang","submitted_at":"2021-12-24T08:17:18Z","abstract_excerpt":"Modern visual systems have a wide range of potential applications in vision tasks for natural science research, such as aiding in species discovery, monitoring animals in the wild, and so on. However, real-world vision tasks may experience changes in environmental conditions, leading to shifts in how captured images are presented. To address this issue, we introduce Domain-Aware Continual Zero-Shot Learning (DACZSL), a task to recognize images of unseen categories in continuously changing domains. Accordingly, we propose a Domain-Invariant Network (DIN) to learn factorized features for shiftin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.12989","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/2112.12989/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":"2112.12989","created_at":"2026-07-05T07:54:46.441055+00:00"},{"alias_kind":"arxiv_version","alias_value":"2112.12989v3","created_at":"2026-07-05T07:54:46.441055+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.12989","created_at":"2026-07-05T07:54:46.441055+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSECCUCZ2H75","created_at":"2026-07-05T07:54:46.441055+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSECCUCZ2H75PJPO","created_at":"2026-07-05T07:54:46.441055+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSECCUCZ","created_at":"2026-07-05T07:54:46.441055+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.08233","citing_title":"Strategies for Improving Communication Efficiency in Distributed and Federated Learning: Compression, Local Training, and Personalization","ref_index":229,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSECCUCZ2H75PJPOKIXYWBBHMU","json":"https://pith.science/pith/GSECCUCZ2H75PJPOKIXYWBBHMU.json","graph_json":"https://pith.science/api/pith-number/GSECCUCZ2H75PJPOKIXYWBBHMU/graph.json","events_json":"https://pith.science/api/pith-number/GSECCUCZ2H75PJPOKIXYWBBHMU/events.json","paper":"https://pith.science/paper/GSECCUCZ"},"agent_actions":{"view_html":"https://pith.science/pith/GSECCUCZ2H75PJPOKIXYWBBHMU","download_json":"https://pith.science/pith/GSECCUCZ2H75PJPOKIXYWBBHMU.json","view_paper":"https://pith.science/paper/GSECCUCZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2112.12989&json=true","fetch_graph":"https://pith.science/api/pith-number/GSECCUCZ2H75PJPOKIXYWBBHMU/graph.json","fetch_events":"https://pith.science/api/pith-number/GSECCUCZ2H75PJPOKIXYWBBHMU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSECCUCZ2H75PJPOKIXYWBBHMU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSECCUCZ2H75PJPOKIXYWBBHMU/action/storage_attestation","attest_author":"https://pith.science/pith/GSECCUCZ2H75PJPOKIXYWBBHMU/action/author_attestation","sign_citation":"https://pith.science/pith/GSECCUCZ2H75PJPOKIXYWBBHMU/action/citation_signature","submit_replication":"https://pith.science/pith/GSECCUCZ2H75PJPOKIXYWBBHMU/action/replication_record"}},"created_at":"2026-07-05T07:54:46.441055+00:00","updated_at":"2026-07-05T07:54:46.441055+00:00"}