{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:TO4YV5GICBYCOJGSM6KS4GHNQM","short_pith_number":"pith:TO4YV5GI","canonical_record":{"source":{"id":"1412.6623","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-20T07:42:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04ff6036c48db556a1561b9f579bea09744099c07642798c4cf15e747a8a3f3d","abstract_canon_sha256":"37b34b3dff79325ac26b8967b41d46df10e2bb6ff3817fbd829dabae21dd4cf3"},"schema_version":"1.0"},"canonical_sha256":"9bb98af4c810702724d267952e18ed830b27d5867fcf900f92f2710e66ea577f","source":{"kind":"arxiv","id":"1412.6623","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6623","created_at":"2026-05-18T02:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6623v4","created_at":"2026-05-18T02:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6623","created_at":"2026-05-18T02:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"TO4YV5GICBYC","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"TO4YV5GICBYCOJGS","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"TO4YV5GI","created_at":"2026-05-18T12:28:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:TO4YV5GICBYCOJGSM6KS4GHNQM","target":"record","payload":{"canonical_record":{"source":{"id":"1412.6623","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-20T07:42:40Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"04ff6036c48db556a1561b9f579bea09744099c07642798c4cf15e747a8a3f3d","abstract_canon_sha256":"37b34b3dff79325ac26b8967b41d46df10e2bb6ff3817fbd829dabae21dd4cf3"},"schema_version":"1.0"},"canonical_sha256":"9bb98af4c810702724d267952e18ed830b27d5867fcf900f92f2710e66ea577f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:17:21.685421Z","signature_b64":"TFRZKkqngKca+DbfURSp+oa1ofXWcaId1NjrtG/TXhOmvh02Nzk5mDppd44uoRLKG0F3OS8clfZMSHfSKAAOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9bb98af4c810702724d267952e18ed830b27d5867fcf900f92f2710e66ea577f","last_reissued_at":"2026-05-18T02:17:21.684710Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:17:21.684710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1412.6623","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:17:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YCDEaoWF/ieB/swRvrWa23hGlIIlecw3tGv4IWOaXebUQUA2+BCCKgo56IsNEocGh9nSNQqzYRUelGfQJYP1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:42:42.829886Z"},"content_sha256":"c42c665800c0ded4543a9593f099d87fb244d89ede70731f8d11e60608019d3a","schema_version":"1.0","event_id":"sha256:c42c665800c0ded4543a9593f099d87fb244d89ede70731f8d11e60608019d3a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:TO4YV5GICBYCOJGSM6KS4GHNQM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Word Representations via Gaussian Embedding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Andrew McCallum, Luke Vilnis","submitted_at":"2014-12-20T07:42:40Z","abstract_excerpt":"Current work in lexical distributed representations maps each word to a point vector in low-dimensional space. Mapping instead to a density provides many interesting advantages, including better capturing uncertainty about a representation and its relationships, expressing asymmetries more naturally than dot product or cosine similarity, and enabling more expressive parameterization of decision boundaries. This paper advocates for density-based distributed embeddings and presents a method for learning representations in the space of Gaussian distributions. We compare performance on various wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6623","kind":"arxiv","version":4},"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":"2026-05-18T02:17:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wIGZC8t0Ka96aVAbBNy2V8mnqEMzBoPQrwqNglJ/acoUQenZ9vc18+CKr06PzLAB6dnD7p/EEbpRea/lRB1aBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T14:42:42.830265Z"},"content_sha256":"5073ade99a826bf5e81f58e86124f34e39fcabc8a3db7b32960931f8985d6fcd","schema_version":"1.0","event_id":"sha256:5073ade99a826bf5e81f58e86124f34e39fcabc8a3db7b32960931f8985d6fcd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TO4YV5GICBYCOJGSM6KS4GHNQM/bundle.json","state_url":"https://pith.science/pith/TO4YV5GICBYCOJGSM6KS4GHNQM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TO4YV5GICBYCOJGSM6KS4GHNQM/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":"2026-05-27T14:42:42Z","links":{"resolver":"https://pith.science/pith/TO4YV5GICBYCOJGSM6KS4GHNQM","bundle":"https://pith.science/pith/TO4YV5GICBYCOJGSM6KS4GHNQM/bundle.json","state":"https://pith.science/pith/TO4YV5GICBYCOJGSM6KS4GHNQM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TO4YV5GICBYCOJGSM6KS4GHNQM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:TO4YV5GICBYCOJGSM6KS4GHNQM","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":"37b34b3dff79325ac26b8967b41d46df10e2bb6ff3817fbd829dabae21dd4cf3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-20T07:42:40Z","title_canon_sha256":"04ff6036c48db556a1561b9f579bea09744099c07642798c4cf15e747a8a3f3d"},"schema_version":"1.0","source":{"id":"1412.6623","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1412.6623","created_at":"2026-05-18T02:17:21Z"},{"alias_kind":"arxiv_version","alias_value":"1412.6623v4","created_at":"2026-05-18T02:17:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1412.6623","created_at":"2026-05-18T02:17:21Z"},{"alias_kind":"pith_short_12","alias_value":"TO4YV5GICBYC","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_16","alias_value":"TO4YV5GICBYCOJGS","created_at":"2026-05-18T12:28:49Z"},{"alias_kind":"pith_short_8","alias_value":"TO4YV5GI","created_at":"2026-05-18T12:28:49Z"}],"graph_snapshots":[{"event_id":"sha256:5073ade99a826bf5e81f58e86124f34e39fcabc8a3db7b32960931f8985d6fcd","target":"graph","created_at":"2026-05-18T02:17:21Z","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":"Current work in lexical distributed representations maps each word to a point vector in low-dimensional space. Mapping instead to a density provides many interesting advantages, including better capturing uncertainty about a representation and its relationships, expressing asymmetries more naturally than dot product or cosine similarity, and enabling more expressive parameterization of decision boundaries. This paper advocates for density-based distributed embeddings and presents a method for learning representations in the space of Gaussian distributions. We compare performance on various wor","authors_text":"Andrew McCallum, Luke Vilnis","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-20T07:42:40Z","title":"Word Representations via Gaussian Embedding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1412.6623","kind":"arxiv","version":4},"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:c42c665800c0ded4543a9593f099d87fb244d89ede70731f8d11e60608019d3a","target":"record","created_at":"2026-05-18T02:17:21Z","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":"37b34b3dff79325ac26b8967b41d46df10e2bb6ff3817fbd829dabae21dd4cf3","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-12-20T07:42:40Z","title_canon_sha256":"04ff6036c48db556a1561b9f579bea09744099c07642798c4cf15e747a8a3f3d"},"schema_version":"1.0","source":{"id":"1412.6623","kind":"arxiv","version":4}},"canonical_sha256":"9bb98af4c810702724d267952e18ed830b27d5867fcf900f92f2710e66ea577f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9bb98af4c810702724d267952e18ed830b27d5867fcf900f92f2710e66ea577f","first_computed_at":"2026-05-18T02:17:21.684710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:17:21.684710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TFRZKkqngKca+DbfURSp+oa1ofXWcaId1NjrtG/TXhOmvh02Nzk5mDppd44uoRLKG0F3OS8clfZMSHfSKAAOAA==","signature_status":"signed_v1","signed_at":"2026-05-18T02:17:21.685421Z","signed_message":"canonical_sha256_bytes"},"source_id":"1412.6623","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c42c665800c0ded4543a9593f099d87fb244d89ede70731f8d11e60608019d3a","sha256:5073ade99a826bf5e81f58e86124f34e39fcabc8a3db7b32960931f8985d6fcd"],"state_sha256":"1fa52aafe7d62ffe63dc64b9ddd683e9991cd630ac1f3c26e2bb8bc5c9776b26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CHfVa4t5BCnNjeLr0LCkqndpQSPOzwNaaigyzkRkKtR4RZ1B7oLP+4wGCntJin3u75So2h887pkuS+JvMI1YBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T14:42:42.833073Z","bundle_sha256":"7c6c520fe3f269b720fe70f8322ed21922eee85573eb70d97a677a0c12654208"}}