{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:Z4EKZ4NTUIALSCRAY2VISA3PPO","short_pith_number":"pith:Z4EKZ4NT","schema_version":"1.0","canonical_sha256":"cf08acf1b3a200b90a20c6aa89036f7bbb0aa7521f9584d7816fcf09286876f8","source":{"kind":"arxiv","id":"2002.02923","version":1},"attestation_state":"computed","paper":{"title":"Geometric Dataset Distances via Optimal Transport","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":"2020-02-07T17:51:26Z","abstract_excerpt":"The notion of task similarity is at the core of various machine learning paradigms, such as domain adaptation and meta-learning. Current methods to quantify it are often heuristic, make strong assumptions on the label sets across the tasks, and many are architecture-dependent, relying on task-specific optimal parameters (e.g., require training a model on each dataset). In this work we propose an alternative notion of distance between datasets that (i) is model-agnostic, (ii) does not involve training, (iii) can compare datasets even if their label sets are completely disjoint and (iv) has soli"},"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":"2002.02923","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-02-07T17:51:26Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a9260048887fc076692041854bb9488d3eb17e20f825796c797e18e15980abd7","abstract_canon_sha256":"4318c8fa777b9d47cbf50547e901998f5e4f14fcbb267359332bd3520b8906a7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:39:06.434570Z","signature_b64":"z5VNf98mz1mMKQwV5mRwxdb38fG+uvpat5UVELnigI7Osr6kavhP8JUA7ul4SDD6PCbm4FsSBA8Vdl+/ZpYnAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf08acf1b3a200b90a20c6aa89036f7bbb0aa7521f9584d7816fcf09286876f8","last_reissued_at":"2026-07-05T00:39:06.434157Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:39:06.434157Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometric Dataset Distances via Optimal Transport","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":"2020-02-07T17:51:26Z","abstract_excerpt":"The notion of task similarity is at the core of various machine learning paradigms, such as domain adaptation and meta-learning. Current methods to quantify it are often heuristic, make strong assumptions on the label sets across the tasks, and many are architecture-dependent, relying on task-specific optimal parameters (e.g., require training a model on each dataset). In this work we propose an alternative notion of distance between datasets that (i) is model-agnostic, (ii) does not involve training, (iii) can compare datasets even if their label sets are completely disjoint and (iv) has soli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.02923","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/2002.02923/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":"2002.02923","created_at":"2026-07-05T00:39:06.434217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2002.02923v1","created_at":"2026-07-05T00:39:06.434217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.02923","created_at":"2026-07-05T00:39:06.434217+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z4EKZ4NTUIAL","created_at":"2026-07-05T00:39:06.434217+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z4EKZ4NTUIALSCRA","created_at":"2026-07-05T00:39:06.434217+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z4EKZ4NT","created_at":"2026-07-05T00:39:06.434217+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/Z4EKZ4NTUIALSCRAY2VISA3PPO","json":"https://pith.science/pith/Z4EKZ4NTUIALSCRAY2VISA3PPO.json","graph_json":"https://pith.science/api/pith-number/Z4EKZ4NTUIALSCRAY2VISA3PPO/graph.json","events_json":"https://pith.science/api/pith-number/Z4EKZ4NTUIALSCRAY2VISA3PPO/events.json","paper":"https://pith.science/paper/Z4EKZ4NT"},"agent_actions":{"view_html":"https://pith.science/pith/Z4EKZ4NTUIALSCRAY2VISA3PPO","download_json":"https://pith.science/pith/Z4EKZ4NTUIALSCRAY2VISA3PPO.json","view_paper":"https://pith.science/paper/Z4EKZ4NT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2002.02923&json=true","fetch_graph":"https://pith.science/api/pith-number/Z4EKZ4NTUIALSCRAY2VISA3PPO/graph.json","fetch_events":"https://pith.science/api/pith-number/Z4EKZ4NTUIALSCRAY2VISA3PPO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z4EKZ4NTUIALSCRAY2VISA3PPO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z4EKZ4NTUIALSCRAY2VISA3PPO/action/storage_attestation","attest_author":"https://pith.science/pith/Z4EKZ4NTUIALSCRAY2VISA3PPO/action/author_attestation","sign_citation":"https://pith.science/pith/Z4EKZ4NTUIALSCRAY2VISA3PPO/action/citation_signature","submit_replication":"https://pith.science/pith/Z4EKZ4NTUIALSCRAY2VISA3PPO/action/replication_record"}},"created_at":"2026-07-05T00:39:06.434217+00:00","updated_at":"2026-07-05T00:39:06.434217+00:00"}