{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:A4JCCQWZ23QPTIAU7RDOKYX7LO","short_pith_number":"pith:A4JCCQWZ","canonical_record":{"source":{"id":"1805.03710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T19:54:58Z","cross_cats_sorted":[],"title_canon_sha256":"ea7aab82afe432dfe1ad1f4107786f205a12eaa7d7c9cf1206444f13cd54d96d","abstract_canon_sha256":"0649abcc7ee739c57b50884f4e6774cdc915868267a78d857114d80cdb16e40b"},"schema_version":"1.0"},"canonical_sha256":"07122142d9d6e0f9a014fc46e562ff5bbe2f106a7593bc5f63c443c573f464a1","source":{"kind":"arxiv","id":"1805.03710","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03710","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03710v1","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03710","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"A4JCCQWZ23QP","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A4JCCQWZ23QPTIAU","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A4JCCQWZ","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:A4JCCQWZ23QPTIAU7RDOKYX7LO","target":"record","payload":{"canonical_record":{"source":{"id":"1805.03710","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T19:54:58Z","cross_cats_sorted":[],"title_canon_sha256":"ea7aab82afe432dfe1ad1f4107786f205a12eaa7d7c9cf1206444f13cd54d96d","abstract_canon_sha256":"0649abcc7ee739c57b50884f4e6774cdc915868267a78d857114d80cdb16e40b"},"schema_version":"1.0"},"canonical_sha256":"07122142d9d6e0f9a014fc46e562ff5bbe2f106a7593bc5f63c443c573f464a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:16:18.962884Z","signature_b64":"D1ckE3jmut02tdV510wZtBN9wlmp+gwZTY6CthnitCo5bG4uP4YRKR+DWivhXb97XV9BesRRELbRblHJ0iAoCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07122142d9d6e0f9a014fc46e562ff5bbe2f106a7593bc5f63c443c573f464a1","last_reissued_at":"2026-05-18T00:16:18.962473Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:16:18.962473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.03710","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":"2026-05-18T00:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ljASVWQFf7d3q9n08r5TEGS1yuV28de+CAW1wCrwGB/qdJ5IO3uNhDKJhOXPVbhcE+OMLfUdVJxcH8bnynSECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:15:23.837734Z"},"content_sha256":"993a062b49facc3fdc0261eba2b79524ea6299b776896c8bc70d185b321a00b0","schema_version":"1.0","event_id":"sha256:993a062b49facc3fdc0261eba2b79524ea6299b776896c8bc70d185b321a00b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:A4JCCQWZ23QPTIAU7RDOKYX7LO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incorporating Subword Information into Matrix Factorization Word Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexandre Salle, Aline Villavicencio","submitted_at":"2018-05-09T19:54:58Z","abstract_excerpt":"The positive effect of adding subword information to word embeddings has been demonstrated for predictive models. In this paper we investigate whether similar benefits can also be derived from incorporating subwords into counting models. We evaluate the impact of different types of subwords (n-grams and unsupervised morphemes), with results confirming the importance of subword information in learning representations of rare and out-of-vocabulary words."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03710","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":"2026-05-18T00:16:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8+tl/waVo6ntA26Zxzh1VKLW5naRadLEieoaiuCWopJmRZomiukUP1B8CRzBGQb7UoivcgCGXFiaYt/R2Q9PAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:15:23.838377Z"},"content_sha256":"4c87e9a863990bb184aacd11d15ad949f9f1bde5043e1be51057b3bc423c39ff","schema_version":"1.0","event_id":"sha256:4c87e9a863990bb184aacd11d15ad949f9f1bde5043e1be51057b3bc423c39ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A4JCCQWZ23QPTIAU7RDOKYX7LO/bundle.json","state_url":"https://pith.science/pith/A4JCCQWZ23QPTIAU7RDOKYX7LO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A4JCCQWZ23QPTIAU7RDOKYX7LO/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":"2026-06-05T04:15:23Z","links":{"resolver":"https://pith.science/pith/A4JCCQWZ23QPTIAU7RDOKYX7LO","bundle":"https://pith.science/pith/A4JCCQWZ23QPTIAU7RDOKYX7LO/bundle.json","state":"https://pith.science/pith/A4JCCQWZ23QPTIAU7RDOKYX7LO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A4JCCQWZ23QPTIAU7RDOKYX7LO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:A4JCCQWZ23QPTIAU7RDOKYX7LO","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":"0649abcc7ee739c57b50884f4e6774cdc915868267a78d857114d80cdb16e40b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T19:54:58Z","title_canon_sha256":"ea7aab82afe432dfe1ad1f4107786f205a12eaa7d7c9cf1206444f13cd54d96d"},"schema_version":"1.0","source":{"id":"1805.03710","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.03710","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"arxiv_version","alias_value":"1805.03710v1","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.03710","created_at":"2026-05-18T00:16:18Z"},{"alias_kind":"pith_short_12","alias_value":"A4JCCQWZ23QP","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A4JCCQWZ23QPTIAU","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A4JCCQWZ","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:4c87e9a863990bb184aacd11d15ad949f9f1bde5043e1be51057b3bc423c39ff","target":"graph","created_at":"2026-05-18T00:16:18Z","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":"The positive effect of adding subword information to word embeddings has been demonstrated for predictive models. In this paper we investigate whether similar benefits can also be derived from incorporating subwords into counting models. We evaluate the impact of different types of subwords (n-grams and unsupervised morphemes), with results confirming the importance of subword information in learning representations of rare and out-of-vocabulary words.","authors_text":"Alexandre Salle, Aline Villavicencio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T19:54:58Z","title":"Incorporating Subword Information into Matrix Factorization Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.03710","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":"sha256:993a062b49facc3fdc0261eba2b79524ea6299b776896c8bc70d185b321a00b0","target":"record","created_at":"2026-05-18T00:16:18Z","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":"0649abcc7ee739c57b50884f4e6774cdc915868267a78d857114d80cdb16e40b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-09T19:54:58Z","title_canon_sha256":"ea7aab82afe432dfe1ad1f4107786f205a12eaa7d7c9cf1206444f13cd54d96d"},"schema_version":"1.0","source":{"id":"1805.03710","kind":"arxiv","version":1}},"canonical_sha256":"07122142d9d6e0f9a014fc46e562ff5bbe2f106a7593bc5f63c443c573f464a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07122142d9d6e0f9a014fc46e562ff5bbe2f106a7593bc5f63c443c573f464a1","first_computed_at":"2026-05-18T00:16:18.962473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:16:18.962473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"D1ckE3jmut02tdV510wZtBN9wlmp+gwZTY6CthnitCo5bG4uP4YRKR+DWivhXb97XV9BesRRELbRblHJ0iAoCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:16:18.962884Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.03710","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:993a062b49facc3fdc0261eba2b79524ea6299b776896c8bc70d185b321a00b0","sha256:4c87e9a863990bb184aacd11d15ad949f9f1bde5043e1be51057b3bc423c39ff"],"state_sha256":"66166740db99c22b5509940af09e0fea02b6dc47f5ecc2986134fc63838cea9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oHJyHBbPXuZAQ+rjFun6jpDPySGTnk1N/t+F8yoD6rGYFeHS+Vrlhw92iE0y7yVNpMdErbqUr3X2B0ThjdWVBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T04:15:23.842026Z","bundle_sha256":"ae974fb9eea0ae84c5f87fe4cc015064f52fb0bb1f7644fb8267182845014949"}}