{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:GWLR23D2LRAYGZ66LGDPFH4V3X","short_pith_number":"pith:GWLR23D2","schema_version":"1.0","canonical_sha256":"35971d6c7a5c418367de5986f29f95ddf3e3627930b163b30c7cf8a96696eeb7","source":{"kind":"arxiv","id":"2010.12760","version":2},"attestation_state":"computed","paper":{"title":"Dataset Dynamics via Gradient Flows in Probability Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Alvarez-Melis, Nicol\\`o Fusi","submitted_at":"2020-10-24T03:29:22Z","abstract_excerpt":"Various machine learning tasks, from generative modeling to domain adaptation, revolve around the concept of dataset transformation and manipulation. While various methods exist for transforming unlabeled datasets, principled methods to do so for labeled (e.g., classification) datasets are missing. In this work, we propose a novel framework for dataset transformation, which we cast as optimization over data-generating joint probability distributions. We approach this class of problems through Wasserstein gradient flows in probability space, and derive practical and efficient particle-based met"},"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":"2010.12760","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-24T03:29:22Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"21d7a859460f981a5fc1309a2152ff91568965e60988abe3d16d52f954d53446","abstract_canon_sha256":"e5bc27e47cfb57c693370c92cf3b9648973c08457d125b327500934d1bae00e1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:51.506718Z","signature_b64":"5PCvB7H0DL4SIHeRAYrGpPQ9PLRbpOaoK+++kRiQguDoVZUi54sF5Grurc1+DpOOjZ26jQ86GHdGd/+o9PEoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35971d6c7a5c418367de5986f29f95ddf3e3627930b163b30c7cf8a96696eeb7","last_reissued_at":"2026-07-05T02:49:51.506225Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:51.506225Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dataset Dynamics via Gradient Flows in Probability Space","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"David Alvarez-Melis, Nicol\\`o Fusi","submitted_at":"2020-10-24T03:29:22Z","abstract_excerpt":"Various machine learning tasks, from generative modeling to domain adaptation, revolve around the concept of dataset transformation and manipulation. While various methods exist for transforming unlabeled datasets, principled methods to do so for labeled (e.g., classification) datasets are missing. In this work, we propose a novel framework for dataset transformation, which we cast as optimization over data-generating joint probability distributions. We approach this class of problems through Wasserstein gradient flows in probability space, and derive practical and efficient particle-based met"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12760","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/2010.12760/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":"2010.12760","created_at":"2026-07-05T02:49:51.506282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.12760v2","created_at":"2026-07-05T02:49:51.506282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12760","created_at":"2026-07-05T02:49:51.506282+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWLR23D2LRAY","created_at":"2026-07-05T02:49:51.506282+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWLR23D2LRAYGZ66","created_at":"2026-07-05T02:49:51.506282+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWLR23D2","created_at":"2026-07-05T02:49:51.506282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.10237","citing_title":"Minimalist Genetic Programming","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09471","citing_title":"The Statistical Cost of Adaptation in Multi-Source Transfer Learning","ref_index":158,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWLR23D2LRAYGZ66LGDPFH4V3X","json":"https://pith.science/pith/GWLR23D2LRAYGZ66LGDPFH4V3X.json","graph_json":"https://pith.science/api/pith-number/GWLR23D2LRAYGZ66LGDPFH4V3X/graph.json","events_json":"https://pith.science/api/pith-number/GWLR23D2LRAYGZ66LGDPFH4V3X/events.json","paper":"https://pith.science/paper/GWLR23D2"},"agent_actions":{"view_html":"https://pith.science/pith/GWLR23D2LRAYGZ66LGDPFH4V3X","download_json":"https://pith.science/pith/GWLR23D2LRAYGZ66LGDPFH4V3X.json","view_paper":"https://pith.science/paper/GWLR23D2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.12760&json=true","fetch_graph":"https://pith.science/api/pith-number/GWLR23D2LRAYGZ66LGDPFH4V3X/graph.json","fetch_events":"https://pith.science/api/pith-number/GWLR23D2LRAYGZ66LGDPFH4V3X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWLR23D2LRAYGZ66LGDPFH4V3X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWLR23D2LRAYGZ66LGDPFH4V3X/action/storage_attestation","attest_author":"https://pith.science/pith/GWLR23D2LRAYGZ66LGDPFH4V3X/action/author_attestation","sign_citation":"https://pith.science/pith/GWLR23D2LRAYGZ66LGDPFH4V3X/action/citation_signature","submit_replication":"https://pith.science/pith/GWLR23D2LRAYGZ66LGDPFH4V3X/action/replication_record"}},"created_at":"2026-07-05T02:49:51.506282+00:00","updated_at":"2026-07-05T02:49:51.506282+00:00"}