{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:26NKQVLBYMHWSYHW34IVCF72AK","short_pith_number":"pith:26NKQVLB","canonical_record":{"source":{"id":"1806.02901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-07T20:57:22Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"31f05f2a7e8bcbd6b49bf2e1912e5fd40f43e039cdff34be9dc7604e7398e4ae","abstract_canon_sha256":"f51bf8920a31872f5d7f706959fb2fb736a23134392d61dce5e01567733f2568"},"schema_version":"1.0"},"canonical_sha256":"d79aa85561c30f6960f6df115117fa02827a5212e5a08968e027c4a48dfadd60","source":{"kind":"arxiv","id":"1806.02901","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02901","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02901v1","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02901","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"26NKQVLBYMHW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"26NKQVLBYMHWSYHW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"26NKQVLB","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:26NKQVLBYMHWSYHW34IVCF72AK","target":"record","payload":{"canonical_record":{"source":{"id":"1806.02901","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-07T20:57:22Z","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"title_canon_sha256":"31f05f2a7e8bcbd6b49bf2e1912e5fd40f43e039cdff34be9dc7604e7398e4ae","abstract_canon_sha256":"f51bf8920a31872f5d7f706959fb2fb736a23134392d61dce5e01567733f2568"},"schema_version":"1.0"},"canonical_sha256":"d79aa85561c30f6960f6df115117fa02827a5212e5a08968e027c4a48dfadd60","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:13:54.410974Z","signature_b64":"CN0CLXxIvj1/ukGl6OgMwwNgGpAm53QNBUzhZD3rhVWLGxAzgSDZbWwLDpyS41Kxga14FwbSFj3vTTbUBlnTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d79aa85561c30f6960f6df115117fa02827a5212e5a08968e027c4a48dfadd60","last_reissued_at":"2026-05-18T00:13:54.410219Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:13:54.410219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1806.02901","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":"2026-05-18T00:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5ciewt1fiEpiUuaov9CGtVtJdCojIKvLdEZGj/osJXVp+UUbB4TtLZV4ADrQexLZubSFcXuxkoutMzJS3O01CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:27:02.475242Z"},"content_sha256":"7ea628b93c8bcbeeb098ae8acad1e3c2920258e183e8b5a9c0c62802c8921780","schema_version":"1.0","event_id":"sha256:7ea628b93c8bcbeeb098ae8acad1e3c2920258e183e8b5a9c0c62802c8921780"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:26NKQVLBYMHWSYHW34IVCF72AK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Probabilistic FastText for Multi-Sense Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","stat.ML"],"primary_cat":"cs.CL","authors_text":"Andrew Gordon Wilson, Anima Anandkumar, Ben Athiwaratkun","submitted_at":"2018-06-07T20:57:22Z","abstract_excerpt":"We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the mean of a mixture component is given by the sum of n-grams. This representation allows the model to share statistical strength across sub-word structures (e.g. Latin roots), producing accurate representations of rare, misspelt, or even unseen words. Moreover, each component of the mixture can capture a different word sense. Probabilistic FastText outperforms b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02901","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":"2026-05-18T00:13:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a9vyEq86QwDSiJNf8AkC03aOT2WqEHYTEjfpWhtSBDhyq5UnQep1LD3zvwyhIn+dwGvh1OSOLtzJolKZCYMGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T04:27:02.475971Z"},"content_sha256":"27baf86d32a57cb2c337d7cae79f05abd03bb5f2a4f38d8c1003851ebdb884d6","schema_version":"1.0","event_id":"sha256:27baf86d32a57cb2c337d7cae79f05abd03bb5f2a4f38d8c1003851ebdb884d6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK/bundle.json","state_url":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/26NKQVLBYMHWSYHW34IVCF72AK/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":"2026-06-06T04:27:02Z","links":{"resolver":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK","bundle":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK/bundle.json","state":"https://pith.science/pith/26NKQVLBYMHWSYHW34IVCF72AK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/26NKQVLBYMHWSYHW34IVCF72AK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:26NKQVLBYMHWSYHW34IVCF72AK","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":"f51bf8920a31872f5d7f706959fb2fb736a23134392d61dce5e01567733f2568","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-07T20:57:22Z","title_canon_sha256":"31f05f2a7e8bcbd6b49bf2e1912e5fd40f43e039cdff34be9dc7604e7398e4ae"},"schema_version":"1.0","source":{"id":"1806.02901","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1806.02901","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"arxiv_version","alias_value":"1806.02901v1","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.02901","created_at":"2026-05-18T00:13:54Z"},{"alias_kind":"pith_short_12","alias_value":"26NKQVLBYMHW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"26NKQVLBYMHWSYHW","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"26NKQVLB","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:27baf86d32a57cb2c337d7cae79f05abd03bb5f2a4f38d8c1003851ebdb884d6","target":"graph","created_at":"2026-05-18T00:13:54Z","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":"We introduce Probabilistic FastText, a new model for word embeddings that can capture multiple word senses, sub-word structure, and uncertainty information. In particular, we represent each word with a Gaussian mixture density, where the mean of a mixture component is given by the sum of n-grams. This representation allows the model to share statistical strength across sub-word structures (e.g. Latin roots), producing accurate representations of rare, misspelt, or even unseen words. Moreover, each component of the mixture can capture a different word sense. Probabilistic FastText outperforms b","authors_text":"Andrew Gordon Wilson, Anima Anandkumar, Ben Athiwaratkun","cross_cats":["cs.AI","cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-07T20:57:22Z","title":"Probabilistic FastText for Multi-Sense Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.02901","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":"sha256:7ea628b93c8bcbeeb098ae8acad1e3c2920258e183e8b5a9c0c62802c8921780","target":"record","created_at":"2026-05-18T00:13:54Z","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":"f51bf8920a31872f5d7f706959fb2fb736a23134392d61dce5e01567733f2568","cross_cats_sorted":["cs.AI","cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-06-07T20:57:22Z","title_canon_sha256":"31f05f2a7e8bcbd6b49bf2e1912e5fd40f43e039cdff34be9dc7604e7398e4ae"},"schema_version":"1.0","source":{"id":"1806.02901","kind":"arxiv","version":1}},"canonical_sha256":"d79aa85561c30f6960f6df115117fa02827a5212e5a08968e027c4a48dfadd60","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d79aa85561c30f6960f6df115117fa02827a5212e5a08968e027c4a48dfadd60","first_computed_at":"2026-05-18T00:13:54.410219Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:13:54.410219Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CN0CLXxIvj1/ukGl6OgMwwNgGpAm53QNBUzhZD3rhVWLGxAzgSDZbWwLDpyS41Kxga14FwbSFj3vTTbUBlnTDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:13:54.410974Z","signed_message":"canonical_sha256_bytes"},"source_id":"1806.02901","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ea628b93c8bcbeeb098ae8acad1e3c2920258e183e8b5a9c0c62802c8921780","sha256:27baf86d32a57cb2c337d7cae79f05abd03bb5f2a4f38d8c1003851ebdb884d6"],"state_sha256":"ec478f5805ac9d921316e38387b24b624611c8df80d55e30dbb3bfaf96a8629c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"otiZgeHK71zANqHJOop5uhspOCizlaJGx25IjF30H24LbidaX7tNGirUy0iJbOl3w0IULh2wFSGpDEXXqlFCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T04:27:02.485383Z","bundle_sha256":"bfca6479deecb0136e2a552b809e749da17e5050460646a90d57ceb2dd68312d"}}