{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:6EH3CGMO3TIUWF2ZIODOPLZWS3","short_pith_number":"pith:6EH3CGMO","schema_version":"1.0","canonical_sha256":"f10fb1198edcd14b17594386e7af3696d46b70d7952fd653589e464844171595","source":{"kind":"arxiv","id":"2004.00999","version":3},"attestation_state":"computed","paper":{"title":"Pruned Wasserstein Index Generation Model and wigpy Package","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","econ.GN","q-fin.EC"],"primary_cat":"cs.LG","authors_text":"Fangzhou Xie","submitted_at":"2020-03-30T18:26:24Z","abstract_excerpt":"Recent proposal of Wasserstein Index Generation model (WIG) has shown a new direction for automatically generating indices. However, it is challenging in practice to fit large datasets for two reasons. First, the Sinkhorn distance is notoriously expensive to compute and suffers from dimensionality severely. Second, it requires to compute a full $N\\times N$ matrix to be fit into memory, where $N$ is the dimension of vocabulary. When the dimensionality is too large, it is even impossible to compute at all. I hereby propose a Lasso-based shrinkage method to reduce dimensionality for the vocabular"},"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":"2004.00999","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T18:26:24Z","cross_cats_sorted":["cs.CL","econ.GN","q-fin.EC"],"title_canon_sha256":"1d563d90916b74aa1677ae366d6c7316f52bf553cf5977776500b7e5fa2fdecb","abstract_canon_sha256":"67556e3ab666e6c251e598a6db2d376ec2c95732589938722895cbcd7b275ec9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:15:27.327183Z","signature_b64":"tHO9kVtDU6ivGpwO1VuDQyKNn9+ecT7dT1KEUMK+8kmitWdPiGmhOirnAhzjZJpXD0JkxCYHTr8dRgXmrjqDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f10fb1198edcd14b17594386e7af3696d46b70d7952fd653589e464844171595","last_reissued_at":"2026-07-05T03:15:27.326683Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:15:27.326683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Pruned Wasserstein Index Generation Model and wigpy Package","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","econ.GN","q-fin.EC"],"primary_cat":"cs.LG","authors_text":"Fangzhou Xie","submitted_at":"2020-03-30T18:26:24Z","abstract_excerpt":"Recent proposal of Wasserstein Index Generation model (WIG) has shown a new direction for automatically generating indices. However, it is challenging in practice to fit large datasets for two reasons. First, the Sinkhorn distance is notoriously expensive to compute and suffers from dimensionality severely. Second, it requires to compute a full $N\\times N$ matrix to be fit into memory, where $N$ is the dimension of vocabulary. When the dimensionality is too large, it is even impossible to compute at all. I hereby propose a Lasso-based shrinkage method to reduce dimensionality for the vocabular"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00999","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/2004.00999/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":"2004.00999","created_at":"2026-07-05T03:15:27.326740+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.00999v3","created_at":"2026-07-05T03:15:27.326740+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00999","created_at":"2026-07-05T03:15:27.326740+00:00"},{"alias_kind":"pith_short_12","alias_value":"6EH3CGMO3TIU","created_at":"2026-07-05T03:15:27.326740+00:00"},{"alias_kind":"pith_short_16","alias_value":"6EH3CGMO3TIUWF2Z","created_at":"2026-07-05T03:15:27.326740+00:00"},{"alias_kind":"pith_short_8","alias_value":"6EH3CGMO","created_at":"2026-07-05T03:15:27.326740+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/6EH3CGMO3TIUWF2ZIODOPLZWS3","json":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3.json","graph_json":"https://pith.science/api/pith-number/6EH3CGMO3TIUWF2ZIODOPLZWS3/graph.json","events_json":"https://pith.science/api/pith-number/6EH3CGMO3TIUWF2ZIODOPLZWS3/events.json","paper":"https://pith.science/paper/6EH3CGMO"},"agent_actions":{"view_html":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3","download_json":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3.json","view_paper":"https://pith.science/paper/6EH3CGMO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.00999&json=true","fetch_graph":"https://pith.science/api/pith-number/6EH3CGMO3TIUWF2ZIODOPLZWS3/graph.json","fetch_events":"https://pith.science/api/pith-number/6EH3CGMO3TIUWF2ZIODOPLZWS3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/action/storage_attestation","attest_author":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/action/author_attestation","sign_citation":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/action/citation_signature","submit_replication":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/action/replication_record"}},"created_at":"2026-07-05T03:15:27.326740+00:00","updated_at":"2026-07-05T03:15:27.326740+00:00"}