{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WS4Z5CO7GK4NOLMBZJ3CZTCV6C","short_pith_number":"pith:WS4Z5CO7","schema_version":"1.0","canonical_sha256":"b4b99e89df32b8d72d81ca762ccc55f0bdf8da2587f304b89ff8ebccbc286444","source":{"kind":"arxiv","id":"2411.18823","version":2},"attestation_state":"computed","paper":{"title":"Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Hanrong Ye, Jingdong Zhang, Wenping Wang, Xin Li","submitted_at":"2024-11-27T23:53:27Z","abstract_excerpt":"In recent years, simultaneous learning of multiple dense prediction tasks with partially annotated label data has emerged as an important research area. Previous works primarily focus on leveraging cross-task relations or conducting adversarial training for extra regularization, which achieve promising performance improvements, while still suffering from the lack of direct pixel-wise supervision and extra training of heavy mapping networks. To effectively tackle this challenge, we propose a novel approach to optimize a set of compact learnable hierarchical task tokens, including global and fin"},"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":"2411.18823","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-27T23:53:27Z","cross_cats_sorted":[],"title_canon_sha256":"9edc5ed35178bced4cc2bccfa3565c5bf378506be5ae6051cc64a827b16c6e46","abstract_canon_sha256":"7c26660c8fb59e7e9fed9a7b965c54207eac246419f96fc480675c35cff23065"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:54.569177Z","signature_b64":"Iw+U9z1+zroEd/gn57yIN2FCVWrv1Vf+8kiNnSUV2L+q5RjaJPKgtVCRr825LxnvJ8MQo1Wrvvxhy/b3cj5UBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b4b99e89df32b8d72d81ca762ccc55f0bdf8da2587f304b89ff8ebccbc286444","last_reissued_at":"2026-07-05T11:45:54.568657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:54.568657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-Task Label Discovery via Hierarchical Task Tokens for Partially Annotated Dense Predictions","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dan Xu, Hanrong Ye, Jingdong Zhang, Wenping Wang, Xin Li","submitted_at":"2024-11-27T23:53:27Z","abstract_excerpt":"In recent years, simultaneous learning of multiple dense prediction tasks with partially annotated label data has emerged as an important research area. Previous works primarily focus on leveraging cross-task relations or conducting adversarial training for extra regularization, which achieve promising performance improvements, while still suffering from the lack of direct pixel-wise supervision and extra training of heavy mapping networks. To effectively tackle this challenge, we propose a novel approach to optimize a set of compact learnable hierarchical task tokens, including global and fin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18823","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/2411.18823/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":"2411.18823","created_at":"2026-07-05T11:45:54.568735+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18823v2","created_at":"2026-07-05T11:45:54.568735+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18823","created_at":"2026-07-05T11:45:54.568735+00:00"},{"alias_kind":"pith_short_12","alias_value":"WS4Z5CO7GK4N","created_at":"2026-07-05T11:45:54.568735+00:00"},{"alias_kind":"pith_short_16","alias_value":"WS4Z5CO7GK4NOLMB","created_at":"2026-07-05T11:45:54.568735+00:00"},{"alias_kind":"pith_short_8","alias_value":"WS4Z5CO7","created_at":"2026-07-05T11:45:54.568735+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/WS4Z5CO7GK4NOLMBZJ3CZTCV6C","json":"https://pith.science/pith/WS4Z5CO7GK4NOLMBZJ3CZTCV6C.json","graph_json":"https://pith.science/api/pith-number/WS4Z5CO7GK4NOLMBZJ3CZTCV6C/graph.json","events_json":"https://pith.science/api/pith-number/WS4Z5CO7GK4NOLMBZJ3CZTCV6C/events.json","paper":"https://pith.science/paper/WS4Z5CO7"},"agent_actions":{"view_html":"https://pith.science/pith/WS4Z5CO7GK4NOLMBZJ3CZTCV6C","download_json":"https://pith.science/pith/WS4Z5CO7GK4NOLMBZJ3CZTCV6C.json","view_paper":"https://pith.science/paper/WS4Z5CO7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18823&json=true","fetch_graph":"https://pith.science/api/pith-number/WS4Z5CO7GK4NOLMBZJ3CZTCV6C/graph.json","fetch_events":"https://pith.science/api/pith-number/WS4Z5CO7GK4NOLMBZJ3CZTCV6C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WS4Z5CO7GK4NOLMBZJ3CZTCV6C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WS4Z5CO7GK4NOLMBZJ3CZTCV6C/action/storage_attestation","attest_author":"https://pith.science/pith/WS4Z5CO7GK4NOLMBZJ3CZTCV6C/action/author_attestation","sign_citation":"https://pith.science/pith/WS4Z5CO7GK4NOLMBZJ3CZTCV6C/action/citation_signature","submit_replication":"https://pith.science/pith/WS4Z5CO7GK4NOLMBZJ3CZTCV6C/action/replication_record"}},"created_at":"2026-07-05T11:45:54.568735+00:00","updated_at":"2026-07-05T11:45:54.568735+00:00"}