{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:FHO3VRPLCRKUYO35LLZ2EL4I25","short_pith_number":"pith:FHO3VRPL","schema_version":"1.0","canonical_sha256":"29ddbac5eb14554c3b7d5af3a22f88d749a8e9228a9e82e421f7c89b37324142","source":{"kind":"arxiv","id":"2311.18531","version":3},"attestation_state":"computed","paper":{"title":"Dataset Distillation via the Wasserstein Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Haohan Wang, Haoyang Liu, Jingrui He, Luwei Li, Peiran Wang, Tiancheng Xing, Vibhu Dalal, Yijiang Li","submitted_at":"2023-11-30T13:15:28Z","abstract_excerpt":"Dataset Distillation (DD) aims to generate a compact synthetic dataset that enables models to achieve performance comparable to training on the full large dataset, significantly reducing computational costs. Drawing from optimal transport theory, we introduce WMDD (Wasserstein Metric-based Dataset Distillation), a straightforward yet powerful method that employs the Wasserstein metric to enhance distribution matching.\n  We compute the Wasserstein barycenter of features from a pretrained classifier to capture essential characteristics of the original data distribution. By optimizing synthetic d"},"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":"2311.18531","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-30T13:15:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6b0e444ecc269e2d71679cb54cff65f54dcf922a2c68c219166e261ab7911556","abstract_canon_sha256":"c8b0a39ac29e249aa5efbc431d1a7b360d20971da61ff95ade90ff4537403201"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:30:35.194068Z","signature_b64":"t0YpYnVNNIoYpV4r5Iq2A1P7/ob1+8QKTgbjKHVQdpjmmIkMNOl1m5XolQPeJiWb28e/vre7oxdUKO5v52ubCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"29ddbac5eb14554c3b7d5af3a22f88d749a8e9228a9e82e421f7c89b37324142","last_reissued_at":"2026-07-05T11:30:35.193526Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:30:35.193526Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset Distillation via the Wasserstein Metric","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Haohan Wang, Haoyang Liu, Jingrui He, Luwei Li, Peiran Wang, Tiancheng Xing, Vibhu Dalal, Yijiang Li","submitted_at":"2023-11-30T13:15:28Z","abstract_excerpt":"Dataset Distillation (DD) aims to generate a compact synthetic dataset that enables models to achieve performance comparable to training on the full large dataset, significantly reducing computational costs. Drawing from optimal transport theory, we introduce WMDD (Wasserstein Metric-based Dataset Distillation), a straightforward yet powerful method that employs the Wasserstein metric to enhance distribution matching.\n  We compute the Wasserstein barycenter of features from a pretrained classifier to capture essential characteristics of the original data distribution. By optimizing synthetic d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.18531","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/2311.18531/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":"2311.18531","created_at":"2026-07-05T11:30:35.193583+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.18531v3","created_at":"2026-07-05T11:30:35.193583+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.18531","created_at":"2026-07-05T11:30:35.193583+00:00"},{"alias_kind":"pith_short_12","alias_value":"FHO3VRPLCRKU","created_at":"2026-07-05T11:30:35.193583+00:00"},{"alias_kind":"pith_short_16","alias_value":"FHO3VRPLCRKUYO35","created_at":"2026-07-05T11:30:35.193583+00:00"},{"alias_kind":"pith_short_8","alias_value":"FHO3VRPL","created_at":"2026-07-05T11:30:35.193583+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21705","citing_title":"Structural Assessment for Understanding and Guiding Dataset Distillation in Discrete Token Space","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00916","citing_title":"Condensing Large-Scale Datasets Directly with Minimal Information Loss","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20196","citing_title":"Distill Once, Adapt Life-Long: Exploring Dataset Distillation for Continual Test-Time Adaptation","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03877","citing_title":"DMGD: Train-Free Dataset Distillation with Semantic-Distribution Matching in Diffusion Models","ref_index":35,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FHO3VRPLCRKUYO35LLZ2EL4I25","json":"https://pith.science/pith/FHO3VRPLCRKUYO35LLZ2EL4I25.json","graph_json":"https://pith.science/api/pith-number/FHO3VRPLCRKUYO35LLZ2EL4I25/graph.json","events_json":"https://pith.science/api/pith-number/FHO3VRPLCRKUYO35LLZ2EL4I25/events.json","paper":"https://pith.science/paper/FHO3VRPL"},"agent_actions":{"view_html":"https://pith.science/pith/FHO3VRPLCRKUYO35LLZ2EL4I25","download_json":"https://pith.science/pith/FHO3VRPLCRKUYO35LLZ2EL4I25.json","view_paper":"https://pith.science/paper/FHO3VRPL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.18531&json=true","fetch_graph":"https://pith.science/api/pith-number/FHO3VRPLCRKUYO35LLZ2EL4I25/graph.json","fetch_events":"https://pith.science/api/pith-number/FHO3VRPLCRKUYO35LLZ2EL4I25/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FHO3VRPLCRKUYO35LLZ2EL4I25/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FHO3VRPLCRKUYO35LLZ2EL4I25/action/storage_attestation","attest_author":"https://pith.science/pith/FHO3VRPLCRKUYO35LLZ2EL4I25/action/author_attestation","sign_citation":"https://pith.science/pith/FHO3VRPLCRKUYO35LLZ2EL4I25/action/citation_signature","submit_replication":"https://pith.science/pith/FHO3VRPLCRKUYO35LLZ2EL4I25/action/replication_record"}},"created_at":"2026-07-05T11:30:35.193583+00:00","updated_at":"2026-07-05T11:30:35.193583+00:00"}