{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OVRVSE4G2TSTSAAYAO2DUMUD5D","short_pith_number":"pith:OVRVSE4G","schema_version":"1.0","canonical_sha256":"7563591386d4e539001803b43a3283e8c52cda032a2b9c86db36b1f9d6982f51","source":{"kind":"arxiv","id":"2503.22359","version":2},"attestation_state":"computed","paper":{"title":"Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunxia Xiao, Haimin Zhang, Jiahao Xia, Jianguo Zhang, Min Xu, Wenjian Huang","submitted_at":"2025-03-28T11:59:27Z","abstract_excerpt":"Despite the similar structures of human faces, existing face alignment methods cannot learn unified knowledge from multiple datasets with different landmark annotations. The limited training samples in a single dataset commonly result in fragile robustness in this field. To mitigate knowledge discrepancies among different datasets and train a task-agnostic unified face alignment (TUFA) framework, this paper presents a strategy to unify knowledge from multiple datasets. Specifically, we calculate a mean face shape for each dataset. To explicitly align these mean shapes on an interpretable plane"},"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":"2503.22359","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-28T11:59:27Z","cross_cats_sorted":[],"title_canon_sha256":"4e2ff4434d2eaa61b30c0ab85a70c81f122ee159ac5567f2419cf53648668ec2","abstract_canon_sha256":"7698b8f345e121c9ae3807844165036f9b9c088d65018b63a4507316cd9718c6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:09.886370Z","signature_b64":"fMNtbnctLXIxEMomtC4Z7gWWStNMZ5wjxDhz1FTxlafK8212I6yvZL5D2LZ3PTEHZ2jN7jC0mVeNeFm/NRSoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7563591386d4e539001803b43a3283e8c52cda032a2b9c86db36b1f9d6982f51","last_reissued_at":"2026-07-05T11:29:09.885840Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:09.885840Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mitigating Knowledge Discrepancies among Multiple Datasets for Task-agnostic Unified Face Alignment","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chunxia Xiao, Haimin Zhang, Jiahao Xia, Jianguo Zhang, Min Xu, Wenjian Huang","submitted_at":"2025-03-28T11:59:27Z","abstract_excerpt":"Despite the similar structures of human faces, existing face alignment methods cannot learn unified knowledge from multiple datasets with different landmark annotations. The limited training samples in a single dataset commonly result in fragile robustness in this field. To mitigate knowledge discrepancies among different datasets and train a task-agnostic unified face alignment (TUFA) framework, this paper presents a strategy to unify knowledge from multiple datasets. Specifically, we calculate a mean face shape for each dataset. To explicitly align these mean shapes on an interpretable plane"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.22359","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/2503.22359/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":"2503.22359","created_at":"2026-07-05T11:29:09.885906+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.22359v2","created_at":"2026-07-05T11:29:09.885906+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.22359","created_at":"2026-07-05T11:29:09.885906+00:00"},{"alias_kind":"pith_short_12","alias_value":"OVRVSE4G2TST","created_at":"2026-07-05T11:29:09.885906+00:00"},{"alias_kind":"pith_short_16","alias_value":"OVRVSE4G2TSTSAAY","created_at":"2026-07-05T11:29:09.885906+00:00"},{"alias_kind":"pith_short_8","alias_value":"OVRVSE4G","created_at":"2026-07-05T11:29:09.885906+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/OVRVSE4G2TSTSAAYAO2DUMUD5D","json":"https://pith.science/pith/OVRVSE4G2TSTSAAYAO2DUMUD5D.json","graph_json":"https://pith.science/api/pith-number/OVRVSE4G2TSTSAAYAO2DUMUD5D/graph.json","events_json":"https://pith.science/api/pith-number/OVRVSE4G2TSTSAAYAO2DUMUD5D/events.json","paper":"https://pith.science/paper/OVRVSE4G"},"agent_actions":{"view_html":"https://pith.science/pith/OVRVSE4G2TSTSAAYAO2DUMUD5D","download_json":"https://pith.science/pith/OVRVSE4G2TSTSAAYAO2DUMUD5D.json","view_paper":"https://pith.science/paper/OVRVSE4G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.22359&json=true","fetch_graph":"https://pith.science/api/pith-number/OVRVSE4G2TSTSAAYAO2DUMUD5D/graph.json","fetch_events":"https://pith.science/api/pith-number/OVRVSE4G2TSTSAAYAO2DUMUD5D/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OVRVSE4G2TSTSAAYAO2DUMUD5D/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OVRVSE4G2TSTSAAYAO2DUMUD5D/action/storage_attestation","attest_author":"https://pith.science/pith/OVRVSE4G2TSTSAAYAO2DUMUD5D/action/author_attestation","sign_citation":"https://pith.science/pith/OVRVSE4G2TSTSAAYAO2DUMUD5D/action/citation_signature","submit_replication":"https://pith.science/pith/OVRVSE4G2TSTSAAYAO2DUMUD5D/action/replication_record"}},"created_at":"2026-07-05T11:29:09.885906+00:00","updated_at":"2026-07-05T11:29:09.885906+00:00"}