{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NW5SQEBAGP6M6WY67PEP5BYZX6","short_pith_number":"pith:NW5SQEBA","schema_version":"1.0","canonical_sha256":"6dbb28102033fccf5b1efbc8fe8719bf8cb3fccd9671a6a9cccf892b10ff15e9","source":{"kind":"arxiv","id":"2502.06525","version":2},"attestation_state":"computed","paper":{"title":"Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anna Korba, Christophe Vauthier, Quentin M\\'erigot","submitted_at":"2025-02-10T14:49:22Z","abstract_excerpt":"In this paper, we investigate the properties of the Sliced Wasserstein Distance (SW) when employed as an objective functional. The SW metric has gained significant interest in the optimal transport and machine learning literature, due to its ability to capture intricate geometric properties of probability distributions while remaining computationally tractable, making it a valuable tool for various applications, including generative modeling and domain adaptation. Our study aims to provide a rigorous analysis of the critical points arising from the optimization of the SW objective. By computin"},"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":"2502.06525","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-02-10T14:49:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"36240c052d8badb199b01357c70484c5a4a3a752f4405b4a5cc069e9e34481f9","abstract_canon_sha256":"fee92bc10f8eca69d44fcc842601dc82160f734fbd8137cec92f9cf84054d009"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:56:43.493890Z","signature_b64":"HMH+NV01BBxJKCb/+NaA+5H2HEmyJJD5oOU6BTyZbjUA2YN0mQTZT2u47rclBurzGFuMts3bHOpArsvwvTsOCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6dbb28102033fccf5b1efbc8fe8719bf8cb3fccd9671a6a9cccf892b10ff15e9","last_reissued_at":"2026-07-05T11:56:43.493400Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:56:43.493400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Understanding Gradient Dynamics of the Sliced-Wasserstein Distance via Critical Point Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Anna Korba, Christophe Vauthier, Quentin M\\'erigot","submitted_at":"2025-02-10T14:49:22Z","abstract_excerpt":"In this paper, we investigate the properties of the Sliced Wasserstein Distance (SW) when employed as an objective functional. The SW metric has gained significant interest in the optimal transport and machine learning literature, due to its ability to capture intricate geometric properties of probability distributions while remaining computationally tractable, making it a valuable tool for various applications, including generative modeling and domain adaptation. Our study aims to provide a rigorous analysis of the critical points arising from the optimization of the SW objective. By computin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.06525","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/2502.06525/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":"2502.06525","created_at":"2026-07-05T11:56:43.493463+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.06525v2","created_at":"2026-07-05T11:56:43.493463+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.06525","created_at":"2026-07-05T11:56:43.493463+00:00"},{"alias_kind":"pith_short_12","alias_value":"NW5SQEBAGP6M","created_at":"2026-07-05T11:56:43.493463+00:00"},{"alias_kind":"pith_short_16","alias_value":"NW5SQEBAGP6M6WY6","created_at":"2026-07-05T11:56:43.493463+00:00"},{"alias_kind":"pith_short_8","alias_value":"NW5SQEBA","created_at":"2026-07-05T11:56:43.493463+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.28134","citing_title":"Convergence of empirical subgradients for optimal transport-based objectives","ref_index":67,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NW5SQEBAGP6M6WY67PEP5BYZX6","json":"https://pith.science/pith/NW5SQEBAGP6M6WY67PEP5BYZX6.json","graph_json":"https://pith.science/api/pith-number/NW5SQEBAGP6M6WY67PEP5BYZX6/graph.json","events_json":"https://pith.science/api/pith-number/NW5SQEBAGP6M6WY67PEP5BYZX6/events.json","paper":"https://pith.science/paper/NW5SQEBA"},"agent_actions":{"view_html":"https://pith.science/pith/NW5SQEBAGP6M6WY67PEP5BYZX6","download_json":"https://pith.science/pith/NW5SQEBAGP6M6WY67PEP5BYZX6.json","view_paper":"https://pith.science/paper/NW5SQEBA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.06525&json=true","fetch_graph":"https://pith.science/api/pith-number/NW5SQEBAGP6M6WY67PEP5BYZX6/graph.json","fetch_events":"https://pith.science/api/pith-number/NW5SQEBAGP6M6WY67PEP5BYZX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NW5SQEBAGP6M6WY67PEP5BYZX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NW5SQEBAGP6M6WY67PEP5BYZX6/action/storage_attestation","attest_author":"https://pith.science/pith/NW5SQEBAGP6M6WY67PEP5BYZX6/action/author_attestation","sign_citation":"https://pith.science/pith/NW5SQEBAGP6M6WY67PEP5BYZX6/action/citation_signature","submit_replication":"https://pith.science/pith/NW5SQEBAGP6M6WY67PEP5BYZX6/action/replication_record"}},"created_at":"2026-07-05T11:56:43.493463+00:00","updated_at":"2026-07-05T11:56:43.493463+00:00"}