{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:JMGM5ZXQ2EYGF3MNPEXWIHVLRK","short_pith_number":"pith:JMGM5ZXQ","canonical_record":{"source":{"id":"1805.04437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-11T15:01:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"679345c8e32424896af6be48dfd65b71d3284d28496016f615b2ac486a5101bb","abstract_canon_sha256":"693816d909707df7ca79c9fe21683277ea282c43589e42952308b5505c1af57a"},"schema_version":"1.0"},"canonical_sha256":"4b0ccee6f0d13062ed8d792f641eab8a803bbc8239a2ce1e414f3823bc5d78dc","source":{"kind":"arxiv","id":"1805.04437","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04437","created_at":"2026-05-18T00:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04437v1","created_at":"2026-05-18T00:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04437","created_at":"2026-05-18T00:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"JMGM5ZXQ2EYG","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JMGM5ZXQ2EYGF3MN","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JMGM5ZXQ","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:JMGM5ZXQ2EYGF3MNPEXWIHVLRK","target":"record","payload":{"canonical_record":{"source":{"id":"1805.04437","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-11T15:01:00Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"679345c8e32424896af6be48dfd65b71d3284d28496016f615b2ac486a5101bb","abstract_canon_sha256":"693816d909707df7ca79c9fe21683277ea282c43589e42952308b5505c1af57a"},"schema_version":"1.0"},"canonical_sha256":"4b0ccee6f0d13062ed8d792f641eab8a803bbc8239a2ce1e414f3823bc5d78dc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:10.338640Z","signature_b64":"KVQjJ+pN9lN6eCIc8mF9yxPXgeI0VVtVunnlISE2rNx/9WfmRlpSLSgoVI9sWXUwCgjk1rKKITbLzvRpkxIWDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b0ccee6f0d13062ed8d792f641eab8a803bbc8239a2ce1e414f3823bc5d78dc","last_reissued_at":"2026-05-18T00:16:10.338052Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:10.338052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.04437","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TX7pSWwUtp8xcPsEonpk9Ml0B0ICPY2u0EHv16EaKjMGTHVuuKmrdWLbiiwpjqk6M7qdEZd9dLhGbnVpkXY1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T17:34:26.820971Z"},"content_sha256":"8d27eba148a3ac03633937952c537b8c5c6614c47e5539827e384db550a0051e","schema_version":"1.0","event_id":"sha256:8d27eba148a3ac03633937952c537b8c5c6614c47e5539827e384db550a0051e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:JMGM5ZXQ2EYGF3MNPEXWIHVLRK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-lingual Document Retrieval using Regularized Wasserstein Distance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Charlotte Laclau, Georgios Balikas, Ievgen Redko, Massih-Reza Amini","submitted_at":"2018-05-11T15:01:00Z","abstract_excerpt":"Many information retrieval algorithms rely on the notion of a good distance that allows to efficiently compare objects of different nature. Recently, a new promising metric called Word Mover's Distance was proposed to measure the divergence between text passages. In this paper, we demonstrate that this metric can be extended to incorporate term-weighting schemes and provide more accurate and computationally efficient matching between documents using entropic regularization. We evaluate the benefits of both extensions in the task of cross-lingual document retrieval (CLDR). Our experimental resu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04437","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":""},"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":"2026-05-18T00:16:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+xirEzqt0jCVxmjbJOidDXz9tVVAFHISCH5hqsi+gWZU3NX4lvXtMO9sXxjfq3SWEED0LAbGFzEm7beZDmniAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T17:34:26.821714Z"},"content_sha256":"99ba4e1ec6d4e6eb16366126ceacf11a827069088c4197c29309cd81c915dd4a","schema_version":"1.0","event_id":"sha256:99ba4e1ec6d4e6eb16366126ceacf11a827069088c4197c29309cd81c915dd4a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/bundle.json","state_url":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/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":"2026-05-28T17:34:26Z","links":{"resolver":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK","bundle":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/bundle.json","state":"https://pith.science/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JMGM5ZXQ2EYGF3MNPEXWIHVLRK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:JMGM5ZXQ2EYGF3MNPEXWIHVLRK","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":"693816d909707df7ca79c9fe21683277ea282c43589e42952308b5505c1af57a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-11T15:01:00Z","title_canon_sha256":"679345c8e32424896af6be48dfd65b71d3284d28496016f615b2ac486a5101bb"},"schema_version":"1.0","source":{"id":"1805.04437","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.04437","created_at":"2026-05-18T00:16:10Z"},{"alias_kind":"arxiv_version","alias_value":"1805.04437v1","created_at":"2026-05-18T00:16:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.04437","created_at":"2026-05-18T00:16:10Z"},{"alias_kind":"pith_short_12","alias_value":"JMGM5ZXQ2EYG","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"JMGM5ZXQ2EYGF3MN","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"JMGM5ZXQ","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:99ba4e1ec6d4e6eb16366126ceacf11a827069088c4197c29309cd81c915dd4a","target":"graph","created_at":"2026-05-18T00:16:10Z","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"},"paper":{"abstract_excerpt":"Many information retrieval algorithms rely on the notion of a good distance that allows to efficiently compare objects of different nature. Recently, a new promising metric called Word Mover's Distance was proposed to measure the divergence between text passages. In this paper, we demonstrate that this metric can be extended to incorporate term-weighting schemes and provide more accurate and computationally efficient matching between documents using entropic regularization. We evaluate the benefits of both extensions in the task of cross-lingual document retrieval (CLDR). Our experimental resu","authors_text":"Charlotte Laclau, Georgios Balikas, Ievgen Redko, Massih-Reza Amini","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-11T15:01:00Z","title":"Cross-lingual Document Retrieval using Regularized Wasserstein Distance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.04437","kind":"arxiv","version":1},"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":"sha256:8d27eba148a3ac03633937952c537b8c5c6614c47e5539827e384db550a0051e","target":"record","created_at":"2026-05-18T00:16:10Z","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":"693816d909707df7ca79c9fe21683277ea282c43589e42952308b5505c1af57a","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-11T15:01:00Z","title_canon_sha256":"679345c8e32424896af6be48dfd65b71d3284d28496016f615b2ac486a5101bb"},"schema_version":"1.0","source":{"id":"1805.04437","kind":"arxiv","version":1}},"canonical_sha256":"4b0ccee6f0d13062ed8d792f641eab8a803bbc8239a2ce1e414f3823bc5d78dc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4b0ccee6f0d13062ed8d792f641eab8a803bbc8239a2ce1e414f3823bc5d78dc","first_computed_at":"2026-05-18T00:16:10.338052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:10.338052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KVQjJ+pN9lN6eCIc8mF9yxPXgeI0VVtVunnlISE2rNx/9WfmRlpSLSgoVI9sWXUwCgjk1rKKITbLzvRpkxIWDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:10.338640Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.04437","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8d27eba148a3ac03633937952c537b8c5c6614c47e5539827e384db550a0051e","sha256:99ba4e1ec6d4e6eb16366126ceacf11a827069088c4197c29309cd81c915dd4a"],"state_sha256":"eb3f989e84748fffb45682adf37c500112c2b059604d3596a87c5acedb255a9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"x3yRaptPmj7tbpd0TpLTmbEnpJqe0lKCpkU3J2fX7jb7/dZRoZMdidgdkp5bLUQqt6kbV9Wc5fnv0jZpX6DACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T17:34:26.826019Z","bundle_sha256":"425c928e9a94a41e74e6244a4487b33af74b2920503b9f01bf5d2a4acc4279c0"}}