{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:6EH3CGMO3TIUWF2ZIODOPLZWS3","short_pith_number":"pith:6EH3CGMO","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"},"canonical_sha256":"f10fb1198edcd14b17594386e7af3696d46b70d7952fd653589e464844171595","source":{"kind":"arxiv","id":"2004.00999","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.00999","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.00999v3","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00999","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"6EH3CGMO3TIU","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"6EH3CGMO3TIUWF2Z","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"6EH3CGMO","created_at":"2026-07-05T03:15:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:6EH3CGMO3TIUWF2ZIODOPLZWS3","target":"record","payload":{"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"},"canonical_sha256":"f10fb1198edcd14b17594386e7af3696d46b70d7952fd653589e464844171595","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"},"source_kind":"arxiv","source_id":"2004.00999","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/4BzyVP9xkEaWSinEWWPCLABdhIbtnvmmHP6gDvMAJucc5uOBTZqxtmoOZf/yg3MWE3DfHpplTeEkVJJDuFyDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:02:36.924044Z"},"content_sha256":"1f310ab32ff0ffdab8b3b42c090873095d095889b308c46715cfdead5eecd17b","schema_version":"1.0","event_id":"sha256:1f310ab32ff0ffdab8b3b42c090873095d095889b308c46715cfdead5eecd17b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:6EH3CGMO3TIUWF2ZIODOPLZWS3","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:15:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z00nVaD+B50hT+4xYDJBRvbzQD/e/kaxFNh6X4zcDyGw4wbX4RXCZapE8fLhVQOP9r7fdkc0brtmaoR2p4exDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T06:02:36.924952Z"},"content_sha256":"7071a8ddcc21a441adb9dd5b3b91ce07b271f9a41bb1ef2b7180855885c1db75","schema_version":"1.0","event_id":"sha256:7071a8ddcc21a441adb9dd5b3b91ce07b271f9a41bb1ef2b7180855885c1db75"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/bundle.json","state_url":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-18T06:02:36Z","links":{"resolver":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3","bundle":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/bundle.json","state":"https://pith.science/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EH3CGMO3TIUWF2ZIODOPLZWS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:6EH3CGMO3TIUWF2ZIODOPLZWS3","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"67556e3ab666e6c251e598a6db2d376ec2c95732589938722895cbcd7b275ec9","cross_cats_sorted":["cs.CL","econ.GN","q-fin.EC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T18:26:24Z","title_canon_sha256":"1d563d90916b74aa1677ae366d6c7316f52bf553cf5977776500b7e5fa2fdecb"},"schema_version":"1.0","source":{"id":"2004.00999","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.00999","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"arxiv_version","alias_value":"2004.00999v3","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.00999","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"pith_short_12","alias_value":"6EH3CGMO3TIU","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"pith_short_16","alias_value":"6EH3CGMO3TIUWF2Z","created_at":"2026-07-05T03:15:27Z"},{"alias_kind":"pith_short_8","alias_value":"6EH3CGMO","created_at":"2026-07-05T03:15:27Z"}],"graph_snapshots":[{"event_id":"sha256:7071a8ddcc21a441adb9dd5b3b91ce07b271f9a41bb1ef2b7180855885c1db75","target":"graph","created_at":"2026-07-05T03:15:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2004.00999/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fangzhou Xie","cross_cats":["cs.CL","econ.GN","q-fin.EC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T18:26:24Z","title":"Pruned Wasserstein Index Generation Model and wigpy Package"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.00999","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1f310ab32ff0ffdab8b3b42c090873095d095889b308c46715cfdead5eecd17b","target":"record","created_at":"2026-07-05T03:15:27Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"67556e3ab666e6c251e598a6db2d376ec2c95732589938722895cbcd7b275ec9","cross_cats_sorted":["cs.CL","econ.GN","q-fin.EC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-03-30T18:26:24Z","title_canon_sha256":"1d563d90916b74aa1677ae366d6c7316f52bf553cf5977776500b7e5fa2fdecb"},"schema_version":"1.0","source":{"id":"2004.00999","kind":"arxiv","version":3}},"canonical_sha256":"f10fb1198edcd14b17594386e7af3696d46b70d7952fd653589e464844171595","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f10fb1198edcd14b17594386e7af3696d46b70d7952fd653589e464844171595","first_computed_at":"2026-07-05T03:15:27.326683Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:15:27.326683Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tHO9kVtDU6ivGpwO1VuDQyKNn9+ecT7dT1KEUMK+8kmitWdPiGmhOirnAhzjZJpXD0JkxCYHTr8dRgXmrjqDDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:15:27.327183Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.00999","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1f310ab32ff0ffdab8b3b42c090873095d095889b308c46715cfdead5eecd17b","sha256:7071a8ddcc21a441adb9dd5b3b91ce07b271f9a41bb1ef2b7180855885c1db75"],"state_sha256":"65e3783599f2704bd78772a99dd153f4f1ddc5ecbc7ce093bddd0833e977c193"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pI3XASnqWNEAJHEahmw50qXwrVjoZT39mN4pmXCAGuW7El85ElQpABMtzZbmkuBeKaglsJ4R1wn4xCcl46kvDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T06:02:36.936221Z","bundle_sha256":"8ebb982dd0917e4a255ad1122d6eb02c8b4caf928eb3c86c3ccbb927f9ca9e57"}}