{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LIFERR4PRVCCDWOCZAX25D3YXH","short_pith_number":"pith:LIFERR4P","schema_version":"1.0","canonical_sha256":"5a0a48c78f8d4421d9c2c82fae8f78b9c09e4c1014ae93b7566f6efb68aeb49d","source":{"kind":"arxiv","id":"2408.04591","version":2},"attestation_state":"computed","paper":{"title":"HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongjun Wang, Kai Han, Sagar Vaze","submitted_at":"2024-08-08T17:04:06Z","abstract_excerpt":"Generalized Category Discovery (GCD) is a challenging task in which, given a partially labelled dataset, models must categorize all unlabelled instances, regardless of whether they come from labelled categories or from new ones. In this paper, we challenge a remaining assumption in this task: that all images share the same domain. Specifically, we introduce a new task and method to handle GCD when the unlabelled data also contains images from different domains to the labelled set. Our proposed `HiLo' networks extract High-level semantic and Low-level domain features, before minimizing the mutu"},"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":"2408.04591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-08T17:04:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e38ae122109328ed896e49591b7cc5dc405feaeebbc29bd73a19894e47e91402","abstract_canon_sha256":"763948e293acc268d8c1f6b2c890d814f80429e78c06abe910e7de01076567c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:22:48.950460Z","signature_b64":"W92XKFJNtzvcO5+wZ4iEtKxj28UDAIcXKjJ8sIrg7NTPBH0rOwJc9qwy3MEUm4bwq0q9xz5gVxbSW9w+iLETCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5a0a48c78f8d4421d9c2c82fae8f78b9c09e4c1014ae93b7566f6efb68aeb49d","last_reissued_at":"2026-07-05T10:22:48.949936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:22:48.949936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiLo: A Learning Framework for Generalized Category Discovery Robust to Domain Shifts","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Hongjun Wang, Kai Han, Sagar Vaze","submitted_at":"2024-08-08T17:04:06Z","abstract_excerpt":"Generalized Category Discovery (GCD) is a challenging task in which, given a partially labelled dataset, models must categorize all unlabelled instances, regardless of whether they come from labelled categories or from new ones. In this paper, we challenge a remaining assumption in this task: that all images share the same domain. Specifically, we introduce a new task and method to handle GCD when the unlabelled data also contains images from different domains to the labelled set. Our proposed `HiLo' networks extract High-level semantic and Low-level domain features, before minimizing the mutu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.04591","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/2408.04591/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":"2408.04591","created_at":"2026-07-05T10:22:48.949993+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.04591v2","created_at":"2026-07-05T10:22:48.949993+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.04591","created_at":"2026-07-05T10:22:48.949993+00:00"},{"alias_kind":"pith_short_12","alias_value":"LIFERR4PRVCC","created_at":"2026-07-05T10:22:48.949993+00:00"},{"alias_kind":"pith_short_16","alias_value":"LIFERR4PRVCCDWOC","created_at":"2026-07-05T10:22:48.949993+00:00"},{"alias_kind":"pith_short_8","alias_value":"LIFERR4P","created_at":"2026-07-05T10:22:48.949993+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08183","citing_title":"Sparsity Hurts: Simple Linear Adapter Can Boost Generalized Category Discovery","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11484","citing_title":"PACO: Proxy-Task Alignment and Online Calibration for On-the-Fly Category Discovery","ref_index":57,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LIFERR4PRVCCDWOCZAX25D3YXH","json":"https://pith.science/pith/LIFERR4PRVCCDWOCZAX25D3YXH.json","graph_json":"https://pith.science/api/pith-number/LIFERR4PRVCCDWOCZAX25D3YXH/graph.json","events_json":"https://pith.science/api/pith-number/LIFERR4PRVCCDWOCZAX25D3YXH/events.json","paper":"https://pith.science/paper/LIFERR4P"},"agent_actions":{"view_html":"https://pith.science/pith/LIFERR4PRVCCDWOCZAX25D3YXH","download_json":"https://pith.science/pith/LIFERR4PRVCCDWOCZAX25D3YXH.json","view_paper":"https://pith.science/paper/LIFERR4P","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.04591&json=true","fetch_graph":"https://pith.science/api/pith-number/LIFERR4PRVCCDWOCZAX25D3YXH/graph.json","fetch_events":"https://pith.science/api/pith-number/LIFERR4PRVCCDWOCZAX25D3YXH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LIFERR4PRVCCDWOCZAX25D3YXH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LIFERR4PRVCCDWOCZAX25D3YXH/action/storage_attestation","attest_author":"https://pith.science/pith/LIFERR4PRVCCDWOCZAX25D3YXH/action/author_attestation","sign_citation":"https://pith.science/pith/LIFERR4PRVCCDWOCZAX25D3YXH/action/citation_signature","submit_replication":"https://pith.science/pith/LIFERR4PRVCCDWOCZAX25D3YXH/action/replication_record"}},"created_at":"2026-07-05T10:22:48.949993+00:00","updated_at":"2026-07-05T10:22:48.949993+00:00"}