{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7GV23MFBPYYL6K67BIKYGRTNP5","short_pith_number":"pith:7GV23MFB","canonical_record":{"source":{"id":"1808.07016","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-21T16:59:39Z","cross_cats_sorted":[],"title_canon_sha256":"188f2e419d18d5974495fd1c88843b64b6f972ed4998cc9920c2c209a8e3452b","abstract_canon_sha256":"d436268c2750f5e1f9682964570130c605a70a7473c6cdca28f663ffd2ab6b33"},"schema_version":"1.0"},"canonical_sha256":"f9abadb0a17e30bf2bdf0a1583466d7f51e0a6a7727f94f2b8ab7e2cae85cdbc","source":{"kind":"arxiv","id":"1808.07016","version":7},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07016","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07016v7","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07016","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"7GV23MFBPYYL","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7GV23MFBPYYL6K67","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7GV23MFB","created_at":"2026-05-18T12:32:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7GV23MFBPYYL6K67BIKYGRTNP5","target":"record","payload":{"canonical_record":{"source":{"id":"1808.07016","kind":"arxiv","version":7},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-21T16:59:39Z","cross_cats_sorted":[],"title_canon_sha256":"188f2e419d18d5974495fd1c88843b64b6f972ed4998cc9920c2c209a8e3452b","abstract_canon_sha256":"d436268c2750f5e1f9682964570130c605a70a7473c6cdca28f663ffd2ab6b33"},"schema_version":"1.0"},"canonical_sha256":"f9abadb0a17e30bf2bdf0a1583466d7f51e0a6a7727f94f2b8ab7e2cae85cdbc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:06:36.913228Z","signature_b64":"piZ8QhVRmTRIMjzLKr8noc86pkB70jd/chlRgT8t5ParYMGuRUw4/JCtohR5vmEc4CqCtgXWnYHWZsBDywT8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9abadb0a17e30bf2bdf0a1583466d7f51e0a6a7727f94f2b8ab7e2cae85cdbc","last_reissued_at":"2026-05-18T00:06:36.912861Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:06:36.912861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.07016","source_version":7,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AglwPv7AQVOCCieCUVcXSZPu54HCmIN1L31wcsvn5/tBGCUzUApF5h8+Z6wUKWZof21piwrB0/HgorY44onWAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T07:59:06.204800Z"},"content_sha256":"218d135bcd7343d04226622648ff80014b08fffb3d843ab33734f83f9de76493","schema_version":"1.0","event_id":"sha256:218d135bcd7343d04226622648ff80014b08fffb3d843ab33734f83f9de76493"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7GV23MFBPYYL6K67BIKYGRTNP5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gaussian Word Embedding with a Wasserstein Distance Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chi Sun, Hang Yan, Xipeng Qiu, Xuanjing Huang","submitted_at":"2018-08-21T16:59:39Z","abstract_excerpt":"Compared with word embedding based on point representation, distribution-based word embedding shows more flexibility in expressing uncertainty and therefore embeds richer semantic information when representing words. The Wasserstein distance provides a natural notion of dissimilarity with probability measures and has a closed-form solution when measuring the distance between two Gaussian distributions. Therefore, with the aim of representing words in a highly efficient way, we propose to operate a Gaussian word embedding model with a loss function based on the Wasserstein distance. Also, exter"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07016","kind":"arxiv","version":7},"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":"2026-05-18T00:06:36Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UQJIkOr0CsVN3dHXuheWiaCUks1jLWndtOGarEF6h1CA81DTBRh+++byzE1fsx3y8n0ohYpJJcre0sLXiKG1DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T07:59:06.205489Z"},"content_sha256":"83d2714f98a3f1c88e0af30614914c8047bbc7ea114514cb35550ba6299c6bf5","schema_version":"1.0","event_id":"sha256:83d2714f98a3f1c88e0af30614914c8047bbc7ea114514cb35550ba6299c6bf5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7GV23MFBPYYL6K67BIKYGRTNP5/bundle.json","state_url":"https://pith.science/pith/7GV23MFBPYYL6K67BIKYGRTNP5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7GV23MFBPYYL6K67BIKYGRTNP5/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":"2026-05-23T07:59:06Z","links":{"resolver":"https://pith.science/pith/7GV23MFBPYYL6K67BIKYGRTNP5","bundle":"https://pith.science/pith/7GV23MFBPYYL6K67BIKYGRTNP5/bundle.json","state":"https://pith.science/pith/7GV23MFBPYYL6K67BIKYGRTNP5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7GV23MFBPYYL6K67BIKYGRTNP5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7GV23MFBPYYL6K67BIKYGRTNP5","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":"d436268c2750f5e1f9682964570130c605a70a7473c6cdca28f663ffd2ab6b33","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-21T16:59:39Z","title_canon_sha256":"188f2e419d18d5974495fd1c88843b64b6f972ed4998cc9920c2c209a8e3452b"},"schema_version":"1.0","source":{"id":"1808.07016","kind":"arxiv","version":7}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07016","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07016v7","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07016","created_at":"2026-05-18T00:06:36Z"},{"alias_kind":"pith_short_12","alias_value":"7GV23MFBPYYL","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_16","alias_value":"7GV23MFBPYYL6K67","created_at":"2026-05-18T12:32:11Z"},{"alias_kind":"pith_short_8","alias_value":"7GV23MFB","created_at":"2026-05-18T12:32:11Z"}],"graph_snapshots":[{"event_id":"sha256:83d2714f98a3f1c88e0af30614914c8047bbc7ea114514cb35550ba6299c6bf5","target":"graph","created_at":"2026-05-18T00:06:36Z","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":"Compared with word embedding based on point representation, distribution-based word embedding shows more flexibility in expressing uncertainty and therefore embeds richer semantic information when representing words. The Wasserstein distance provides a natural notion of dissimilarity with probability measures and has a closed-form solution when measuring the distance between two Gaussian distributions. Therefore, with the aim of representing words in a highly efficient way, we propose to operate a Gaussian word embedding model with a loss function based on the Wasserstein distance. Also, exter","authors_text":"Chi Sun, Hang Yan, Xipeng Qiu, Xuanjing Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-21T16:59:39Z","title":"Gaussian Word Embedding with a Wasserstein Distance Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07016","kind":"arxiv","version":7},"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":"sha256:218d135bcd7343d04226622648ff80014b08fffb3d843ab33734f83f9de76493","target":"record","created_at":"2026-05-18T00:06:36Z","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":"d436268c2750f5e1f9682964570130c605a70a7473c6cdca28f663ffd2ab6b33","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-21T16:59:39Z","title_canon_sha256":"188f2e419d18d5974495fd1c88843b64b6f972ed4998cc9920c2c209a8e3452b"},"schema_version":"1.0","source":{"id":"1808.07016","kind":"arxiv","version":7}},"canonical_sha256":"f9abadb0a17e30bf2bdf0a1583466d7f51e0a6a7727f94f2b8ab7e2cae85cdbc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9abadb0a17e30bf2bdf0a1583466d7f51e0a6a7727f94f2b8ab7e2cae85cdbc","first_computed_at":"2026-05-18T00:06:36.912861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:06:36.912861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"piZ8QhVRmTRIMjzLKr8noc86pkB70jd/chlRgT8t5ParYMGuRUw4/JCtohR5vmEc4CqCtgXWnYHWZsBDywT8CQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:06:36.913228Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.07016","source_kind":"arxiv","source_version":7}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:218d135bcd7343d04226622648ff80014b08fffb3d843ab33734f83f9de76493","sha256:83d2714f98a3f1c88e0af30614914c8047bbc7ea114514cb35550ba6299c6bf5"],"state_sha256":"88e369ff3c0e89192e495865cbb62c46a0643e76c587618446f688e12e8f69e7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qu6boPtWIVSwd64YMvliUEVcak7nJEkRZ+Nqqcvydillw/6FDnDC8+4kVZl4y4SyrUvJUCYgxD0aqtJTzVsZBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T07:59:06.208754Z","bundle_sha256":"6d1c725aa2bd8c15fb1e970a3e0a310b3adb5c62a2e233a7c0e823a06c4b9e76"}}