{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:DRIFLCK6EW2YWKDL5MOD64EUYH","short_pith_number":"pith:DRIFLCK6","schema_version":"1.0","canonical_sha256":"1c5055895e25b58b286beb1c3f7094c1cd4b63e5270c5d97e7fed1dc0c8501b2","source":{"kind":"arxiv","id":"2310.10143","version":2},"attestation_state":"computed","paper":{"title":"An Empirical Study of Self-supervised Learning with Wasserstein Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Deborah Sulem, Guillaume Houry, Han Zhao, Kira Michaela Dusterwald, Makoto Yamada, Yao-Hung Hubert Tsai, Yuki Takezawa","submitted_at":"2023-10-16T07:31:30Z","abstract_excerpt":"In this study, we delve into the problem of self-supervised learning (SSL) utilizing the 1-Wasserstein distance on a tree structure (a.k.a., Tree-Wasserstein distance (TWD)), where TWD is defined as the L1 distance between two tree-embedded vectors. In SSL methods, the cosine similarity is often utilized as an objective function; however, it has not been well studied when utilizing the Wasserstein distance. Training the Wasserstein distance is numerically challenging. Thus, this study empirically investigates a strategy for optimizing the SSL with the Wasserstein distance and finds a stable tr"},"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":"2310.10143","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-10-16T07:31:30Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a315644c15d1d1a0489e50147c98453ec4cabfd772c9b79fbb4710c8d0b352ba","abstract_canon_sha256":"12a2d8175edeca92f120354db1aa3676ab88ff379ffce0fa73b273488c79f26b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:41:43.773517Z","signature_b64":"6X2L4CFNlp1CNQ6UIdxVUqZTrU9kMZA0rxxukaV5iEbc8zeuSOPK4vxoJwA5gwxC10guw3l6voGeQFikmMcSAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c5055895e25b58b286beb1c3f7094c1cd4b63e5270c5d97e7fed1dc0c8501b2","last_reissued_at":"2026-07-05T07:41:43.773018Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:41:43.773018Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"An Empirical Study of Self-supervised Learning with Wasserstein Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Deborah Sulem, Guillaume Houry, Han Zhao, Kira Michaela Dusterwald, Makoto Yamada, Yao-Hung Hubert Tsai, Yuki Takezawa","submitted_at":"2023-10-16T07:31:30Z","abstract_excerpt":"In this study, we delve into the problem of self-supervised learning (SSL) utilizing the 1-Wasserstein distance on a tree structure (a.k.a., Tree-Wasserstein distance (TWD)), where TWD is defined as the L1 distance between two tree-embedded vectors. In SSL methods, the cosine similarity is often utilized as an objective function; however, it has not been well studied when utilizing the Wasserstein distance. Training the Wasserstein distance is numerically challenging. Thus, this study empirically investigates a strategy for optimizing the SSL with the Wasserstein distance and finds a stable tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.10143","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/2310.10143/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":"2310.10143","created_at":"2026-07-05T07:41:43.773075+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.10143v2","created_at":"2026-07-05T07:41:43.773075+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.10143","created_at":"2026-07-05T07:41:43.773075+00:00"},{"alias_kind":"pith_short_12","alias_value":"DRIFLCK6EW2Y","created_at":"2026-07-05T07:41:43.773075+00:00"},{"alias_kind":"pith_short_16","alias_value":"DRIFLCK6EW2YWKDL","created_at":"2026-07-05T07:41:43.773075+00:00"},{"alias_kind":"pith_short_8","alias_value":"DRIFLCK6","created_at":"2026-07-05T07:41:43.773075+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/DRIFLCK6EW2YWKDL5MOD64EUYH","json":"https://pith.science/pith/DRIFLCK6EW2YWKDL5MOD64EUYH.json","graph_json":"https://pith.science/api/pith-number/DRIFLCK6EW2YWKDL5MOD64EUYH/graph.json","events_json":"https://pith.science/api/pith-number/DRIFLCK6EW2YWKDL5MOD64EUYH/events.json","paper":"https://pith.science/paper/DRIFLCK6"},"agent_actions":{"view_html":"https://pith.science/pith/DRIFLCK6EW2YWKDL5MOD64EUYH","download_json":"https://pith.science/pith/DRIFLCK6EW2YWKDL5MOD64EUYH.json","view_paper":"https://pith.science/paper/DRIFLCK6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.10143&json=true","fetch_graph":"https://pith.science/api/pith-number/DRIFLCK6EW2YWKDL5MOD64EUYH/graph.json","fetch_events":"https://pith.science/api/pith-number/DRIFLCK6EW2YWKDL5MOD64EUYH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DRIFLCK6EW2YWKDL5MOD64EUYH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DRIFLCK6EW2YWKDL5MOD64EUYH/action/storage_attestation","attest_author":"https://pith.science/pith/DRIFLCK6EW2YWKDL5MOD64EUYH/action/author_attestation","sign_citation":"https://pith.science/pith/DRIFLCK6EW2YWKDL5MOD64EUYH/action/citation_signature","submit_replication":"https://pith.science/pith/DRIFLCK6EW2YWKDL5MOD64EUYH/action/replication_record"}},"created_at":"2026-07-05T07:41:43.773075+00:00","updated_at":"2026-07-05T07:41:43.773075+00:00"}