{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:5FNE4MMJW3GKHDZST24G634TMR","short_pith_number":"pith:5FNE4MMJ","canonical_record":{"source":{"id":"1811.04983","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T20:02:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0fffc3b26f65bd595cdae9abc63bfad7c012d2180b04d903b60007ade26f1199","abstract_canon_sha256":"6a361e741b6b6b32c5b74d14e7cfee1cc965507bb1e96f6a2b3e9a4d635246db"},"schema_version":"1.0"},"canonical_sha256":"e95a4e3189b6cca38f329eb86f6f93646780d132b71112831fe8b1768fc2a53e","source":{"kind":"arxiv","id":"1811.04983","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.04983","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"1811.04983v1","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04983","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"5FNE4MMJW3GK","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5FNE4MMJW3GKHDZS","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5FNE4MMJ","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:5FNE4MMJW3GKHDZST24G634TMR","target":"record","payload":{"canonical_record":{"source":{"id":"1811.04983","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T20:02:00Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0fffc3b26f65bd595cdae9abc63bfad7c012d2180b04d903b60007ade26f1199","abstract_canon_sha256":"6a361e741b6b6b32c5b74d14e7cfee1cc965507bb1e96f6a2b3e9a4d635246db"},"schema_version":"1.0"},"canonical_sha256":"e95a4e3189b6cca38f329eb86f6f93646780d132b71112831fe8b1768fc2a53e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:01.522390Z","signature_b64":"xyBuLNdqGCpu1WK7KUCzQ3z4QOCFB3SJjFQblES0OO1ZN9POoEV/nFPG9NNR8cSkGblVR3AQ+4sDrexMheykBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e95a4e3189b6cca38f329eb86f6f93646780d132b71112831fe8b1768fc2a53e","last_reissued_at":"2026-05-18T00:01:01.521827Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:01.521827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.04983","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":"2026-05-18T00:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mmM3yjL6MqmSjw+hvNz9vXgdUCJNN/r1dxwrCH2RaF9SmGgD8itD+ic+LFOT3+RTGpRaCwvx4WQeEyWa/wZqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T02:20:49.966653Z"},"content_sha256":"ffdeaa03b59c8b5981987a0f7086c69bf19387887154bca0285fb117059f8ec0","schema_version":"1.0","event_id":"sha256:ffdeaa03b59c8b5981987a0f7086c69bf19387887154bca0285fb117059f8ec0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:5FNE4MMJW3GKHDZST24G634TMR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Dimitri Kartsaklis, Mohammad Taher Pilehvar, Nigel Collier, Pietro Lio, Victor Prokhorov","submitted_at":"2018-11-12T20:02:00Z","abstract_excerpt":"Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of words do not usually appear frequently or at all in the training data. In this paper we put forward a technique that exploits the knowledge encoded in lexical resources, such as WordNet, to induce embeddings for unseen words. Our approach adapts graph embedding and cross-lingual vector space transformation techniques in order to merge lexical knowledge encoded in ontologies with that derived from corpus statistics. W"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04983","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":"2026-05-18T00:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"85bn5JSJarWb72XA0aCl6e59IQsCaLhOj+eWbPWxCtZ5zw7wcfy2eenxl3djFJ94fhtXtuM3IvwTXDOhaJdrDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T02:20:49.966996Z"},"content_sha256":"cda257a9fde9024a03995d82312c8844cc49b6106a2f50a29a5527cc7f114d44","schema_version":"1.0","event_id":"sha256:cda257a9fde9024a03995d82312c8844cc49b6106a2f50a29a5527cc7f114d44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5FNE4MMJW3GKHDZST24G634TMR/bundle.json","state_url":"https://pith.science/pith/5FNE4MMJW3GKHDZST24G634TMR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5FNE4MMJW3GKHDZST24G634TMR/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":"2026-07-04T02:20:49Z","links":{"resolver":"https://pith.science/pith/5FNE4MMJW3GKHDZST24G634TMR","bundle":"https://pith.science/pith/5FNE4MMJW3GKHDZST24G634TMR/bundle.json","state":"https://pith.science/pith/5FNE4MMJW3GKHDZST24G634TMR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5FNE4MMJW3GKHDZST24G634TMR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:5FNE4MMJW3GKHDZST24G634TMR","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":"6a361e741b6b6b32c5b74d14e7cfee1cc965507bb1e96f6a2b3e9a4d635246db","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T20:02:00Z","title_canon_sha256":"0fffc3b26f65bd595cdae9abc63bfad7c012d2180b04d903b60007ade26f1199"},"schema_version":"1.0","source":{"id":"1811.04983","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.04983","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"1811.04983v1","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.04983","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"5FNE4MMJW3GK","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"5FNE4MMJW3GKHDZS","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"5FNE4MMJ","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:cda257a9fde9024a03995d82312c8844cc49b6106a2f50a29a5527cc7f114d44","target":"graph","created_at":"2026-05-18T00:01:01Z","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":"Word embedding techniques heavily rely on the abundance of training data for individual words. Given the Zipfian distribution of words in natural language texts, a large number of words do not usually appear frequently or at all in the training data. In this paper we put forward a technique that exploits the knowledge encoded in lexical resources, such as WordNet, to induce embeddings for unseen words. Our approach adapts graph embedding and cross-lingual vector space transformation techniques in order to merge lexical knowledge encoded in ontologies with that derived from corpus statistics. W","authors_text":"Dimitri Kartsaklis, Mohammad Taher Pilehvar, Nigel Collier, Pietro Lio, Victor Prokhorov","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T20:02:00Z","title":"Unseen Word Representation by Aligning Heterogeneous Lexical Semantic Spaces"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.04983","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:ffdeaa03b59c8b5981987a0f7086c69bf19387887154bca0285fb117059f8ec0","target":"record","created_at":"2026-05-18T00:01:01Z","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":"6a361e741b6b6b32c5b74d14e7cfee1cc965507bb1e96f6a2b3e9a4d635246db","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-12T20:02:00Z","title_canon_sha256":"0fffc3b26f65bd595cdae9abc63bfad7c012d2180b04d903b60007ade26f1199"},"schema_version":"1.0","source":{"id":"1811.04983","kind":"arxiv","version":1}},"canonical_sha256":"e95a4e3189b6cca38f329eb86f6f93646780d132b71112831fe8b1768fc2a53e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e95a4e3189b6cca38f329eb86f6f93646780d132b71112831fe8b1768fc2a53e","first_computed_at":"2026-05-18T00:01:01.521827Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:01.521827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xyBuLNdqGCpu1WK7KUCzQ3z4QOCFB3SJjFQblES0OO1ZN9POoEV/nFPG9NNR8cSkGblVR3AQ+4sDrexMheykBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:01.522390Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.04983","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ffdeaa03b59c8b5981987a0f7086c69bf19387887154bca0285fb117059f8ec0","sha256:cda257a9fde9024a03995d82312c8844cc49b6106a2f50a29a5527cc7f114d44"],"state_sha256":"5b0f0cde9a51725e41207bb482fb3d1dbe212b5f702273100497e8ec32afafe4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"77vxX1xMEVdHiNhPDk3clc5Y2SaWbIO4+cdUVkK9EEmR4/Jb5/27IxoNn30LIWLrr3Lf8THGK+3G10opeTSfAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T02:20:49.968880Z","bundle_sha256":"3bee1201d507840b6c827ec7b68f1918b51c336bcd0cc994b1adde05eec40bdd"}}