{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZS3NSQL3MHFANTA6LIRBWU5ENO","short_pith_number":"pith:ZS3NSQL3","schema_version":"1.0","canonical_sha256":"ccb6d9417b61ca06cc1e5a221b53a46ba5d94bab0ee1c5783aac25306873b399","source":{"kind":"arxiv","id":"2502.05027","version":1},"attestation_state":"computed","paper":{"title":"Trust-Aware Diversion for Data-Effective Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiaofeng Cao, Xin Shen, Xin Yu, Yanbin Liu, Zhuojie Wu","submitted_at":"2025-02-07T15:57:39Z","abstract_excerpt":"Dataset distillation compresses a large dataset into a small synthetic subset that retains essential information. Existing methods assume that all samples are perfectly labeled, limiting their real-world applications where incorrect labels are ubiquitous. These mislabeled samples introduce untrustworthy information into the dataset, which misleads model optimization in dataset distillation. To tackle this issue, we propose a Trust-Aware Diversion (TAD) dataset distillation method. Our proposed TAD introduces an iterative dual-loop optimization framework for data-effective distillation. Specifi"},"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":"2502.05027","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T15:57:39Z","cross_cats_sorted":[],"title_canon_sha256":"cc505cf53bdb126f066cce4680c97d651711e0d176b34ba86d6d571b6f168dab","abstract_canon_sha256":"e19bbb377769ed1a11b1ff77e23cd4e676ea9dca5801599d7cf903498a54734b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:01.881756Z","signature_b64":"YmOSfGi/gB/hyWpNWWk1ahV3gCQcQFHmvgq9d7pVdAkXf4ZIt2WC4g3nJgjst3UI6TKD6gaFWOSZqa+MRJrqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccb6d9417b61ca06cc1e5a221b53a46ba5d94bab0ee1c5783aac25306873b399","last_reissued_at":"2026-07-05T10:11:01.881262Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:01.881262Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trust-Aware Diversion for Data-Effective Distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Xiaofeng Cao, Xin Shen, Xin Yu, Yanbin Liu, Zhuojie Wu","submitted_at":"2025-02-07T15:57:39Z","abstract_excerpt":"Dataset distillation compresses a large dataset into a small synthetic subset that retains essential information. Existing methods assume that all samples are perfectly labeled, limiting their real-world applications where incorrect labels are ubiquitous. These mislabeled samples introduce untrustworthy information into the dataset, which misleads model optimization in dataset distillation. To tackle this issue, we propose a Trust-Aware Diversion (TAD) dataset distillation method. Our proposed TAD introduces an iterative dual-loop optimization framework for data-effective distillation. Specifi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05027","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/2502.05027/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":"2502.05027","created_at":"2026-07-05T10:11:01.881334+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05027v1","created_at":"2026-07-05T10:11:01.881334+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05027","created_at":"2026-07-05T10:11:01.881334+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZS3NSQL3MHFA","created_at":"2026-07-05T10:11:01.881334+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZS3NSQL3MHFANTA6","created_at":"2026-07-05T10:11:01.881334+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZS3NSQL3","created_at":"2026-07-05T10:11:01.881334+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.05673","citing_title":"The Evolution of Dataset Distillation: Toward Scalable and Generalizable Solutions","ref_index":198,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZS3NSQL3MHFANTA6LIRBWU5ENO","json":"https://pith.science/pith/ZS3NSQL3MHFANTA6LIRBWU5ENO.json","graph_json":"https://pith.science/api/pith-number/ZS3NSQL3MHFANTA6LIRBWU5ENO/graph.json","events_json":"https://pith.science/api/pith-number/ZS3NSQL3MHFANTA6LIRBWU5ENO/events.json","paper":"https://pith.science/paper/ZS3NSQL3"},"agent_actions":{"view_html":"https://pith.science/pith/ZS3NSQL3MHFANTA6LIRBWU5ENO","download_json":"https://pith.science/pith/ZS3NSQL3MHFANTA6LIRBWU5ENO.json","view_paper":"https://pith.science/paper/ZS3NSQL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05027&json=true","fetch_graph":"https://pith.science/api/pith-number/ZS3NSQL3MHFANTA6LIRBWU5ENO/graph.json","fetch_events":"https://pith.science/api/pith-number/ZS3NSQL3MHFANTA6LIRBWU5ENO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZS3NSQL3MHFANTA6LIRBWU5ENO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZS3NSQL3MHFANTA6LIRBWU5ENO/action/storage_attestation","attest_author":"https://pith.science/pith/ZS3NSQL3MHFANTA6LIRBWU5ENO/action/author_attestation","sign_citation":"https://pith.science/pith/ZS3NSQL3MHFANTA6LIRBWU5ENO/action/citation_signature","submit_replication":"https://pith.science/pith/ZS3NSQL3MHFANTA6LIRBWU5ENO/action/replication_record"}},"created_at":"2026-07-05T10:11:01.881334+00:00","updated_at":"2026-07-05T10:11:01.881334+00:00"}