{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:62UE5YT2YTUGYZTMLZJRE5K2AY","short_pith_number":"pith:62UE5YT2","canonical_record":{"source":{"id":"1811.03866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T11:44:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3eb3ba95b17ca87b23940bba7ab5e7f365f86b8472c756504f63296220b7ad6","abstract_canon_sha256":"548acc4430759c8722f53cbcf339f034120869efbafacf3fbc38389e62140b43"},"schema_version":"1.0"},"canonical_sha256":"f6a84ee27ac4e86c666c5e5312755a061a594a5397ee5217a4adf027e0b03cf3","source":{"kind":"arxiv","id":"1811.03866","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03866","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03866v1","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03866","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"pith_short_12","alias_value":"62UE5YT2YTUG","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"62UE5YT2YTUGYZTM","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"62UE5YT2","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:62UE5YT2YTUGYZTMLZJRE5K2AY","target":"record","payload":{"canonical_record":{"source":{"id":"1811.03866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T11:44:05Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b3eb3ba95b17ca87b23940bba7ab5e7f365f86b8472c756504f63296220b7ad6","abstract_canon_sha256":"548acc4430759c8722f53cbcf339f034120869efbafacf3fbc38389e62140b43"},"schema_version":"1.0"},"canonical_sha256":"f6a84ee27ac4e86c666c5e5312755a061a594a5397ee5217a4adf027e0b03cf3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:11.760544Z","signature_b64":"0/RVCkoWXDAb8VTRV7lCVD5dYBIzrp39FFLY98NwUdhOF9xlXIN2Q0HipkzAlak3OhP4pkN9p8o9uFnUVEfEDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6a84ee27ac4e86c666c5e5312755a061a594a5397ee5217a4adf027e0b03cf3","last_reissued_at":"2026-05-18T00:01:11.759750Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:11.759750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.03866","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":"2026-05-18T00:01:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8EcFNQ7LQOo2yGCPdVMWzYdJSq0lKWDelfCEaiLsiRdTt++l1xpI2VDKz8KoLULPuiOnWFN6s8PvcJMtFH7kAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:13:34.138311Z"},"content_sha256":"6cb8ff6dc980311a61c2ac154d34b2267d368787c2b5556362a4278452401a27","schema_version":"1.0","event_id":"sha256:6cb8ff6dc980311a61c2ac154d34b2267d368787c2b5556362a4278452401a27"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:62UE5YT2YTUGYZTMLZJRE5K2AY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Semantic Representations for Novel Words: Leveraging Both Form and Context","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hinrich Sch\\\"utze, Timo Schick","submitted_at":"2018-11-09T11:44:05Z","abstract_excerpt":"Word embeddings are a key component of high-performing natural language processing (NLP) systems, but it remains a challenge to learn good representations for novel words on the fly, i.e., for words that did not occur in the training data. The general problem setting is that word embeddings are induced on an unlabeled training corpus and then a model is trained that embeds novel words into this induced embedding space. Currently, two approaches for learning embeddings of novel words exist: (i) learning an embedding from the novel word's surface-form (e.g., subword n-grams) and (ii) learning an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03866","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":"2026-05-18T00:01:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YP5tqP/ISNqvL7zBW6RfLRxjQBEkEZei6Befk9asTv9xyMhq0CYGrfNFwAwo5iS+ONG3nuX41jZGpB6jSBzyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T14:13:34.138971Z"},"content_sha256":"14911b39695a426717ee38e36e0687f4216a2f77e490519ca47820bbd79d3a9f","schema_version":"1.0","event_id":"sha256:14911b39695a426717ee38e36e0687f4216a2f77e490519ca47820bbd79d3a9f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/62UE5YT2YTUGYZTMLZJRE5K2AY/bundle.json","state_url":"https://pith.science/pith/62UE5YT2YTUGYZTMLZJRE5K2AY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/62UE5YT2YTUGYZTMLZJRE5K2AY/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":"2026-06-06T14:13:34Z","links":{"resolver":"https://pith.science/pith/62UE5YT2YTUGYZTMLZJRE5K2AY","bundle":"https://pith.science/pith/62UE5YT2YTUGYZTMLZJRE5K2AY/bundle.json","state":"https://pith.science/pith/62UE5YT2YTUGYZTMLZJRE5K2AY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/62UE5YT2YTUGYZTMLZJRE5K2AY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:62UE5YT2YTUGYZTMLZJRE5K2AY","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":"548acc4430759c8722f53cbcf339f034120869efbafacf3fbc38389e62140b43","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T11:44:05Z","title_canon_sha256":"b3eb3ba95b17ca87b23940bba7ab5e7f365f86b8472c756504f63296220b7ad6"},"schema_version":"1.0","source":{"id":"1811.03866","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.03866","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"arxiv_version","alias_value":"1811.03866v1","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.03866","created_at":"2026-05-18T00:01:11Z"},{"alias_kind":"pith_short_12","alias_value":"62UE5YT2YTUG","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"62UE5YT2YTUGYZTM","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"62UE5YT2","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:14911b39695a426717ee38e36e0687f4216a2f77e490519ca47820bbd79d3a9f","target":"graph","created_at":"2026-05-18T00:01:11Z","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 embeddings are a key component of high-performing natural language processing (NLP) systems, but it remains a challenge to learn good representations for novel words on the fly, i.e., for words that did not occur in the training data. The general problem setting is that word embeddings are induced on an unlabeled training corpus and then a model is trained that embeds novel words into this induced embedding space. Currently, two approaches for learning embeddings of novel words exist: (i) learning an embedding from the novel word's surface-form (e.g., subword n-grams) and (ii) learning an","authors_text":"Hinrich Sch\\\"utze, Timo Schick","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T11:44:05Z","title":"Learning Semantic Representations for Novel Words: Leveraging Both Form and Context"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.03866","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":"sha256:6cb8ff6dc980311a61c2ac154d34b2267d368787c2b5556362a4278452401a27","target":"record","created_at":"2026-05-18T00:01:11Z","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":"548acc4430759c8722f53cbcf339f034120869efbafacf3fbc38389e62140b43","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-09T11:44:05Z","title_canon_sha256":"b3eb3ba95b17ca87b23940bba7ab5e7f365f86b8472c756504f63296220b7ad6"},"schema_version":"1.0","source":{"id":"1811.03866","kind":"arxiv","version":1}},"canonical_sha256":"f6a84ee27ac4e86c666c5e5312755a061a594a5397ee5217a4adf027e0b03cf3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f6a84ee27ac4e86c666c5e5312755a061a594a5397ee5217a4adf027e0b03cf3","first_computed_at":"2026-05-18T00:01:11.759750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:11.759750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0/RVCkoWXDAb8VTRV7lCVD5dYBIzrp39FFLY98NwUdhOF9xlXIN2Q0HipkzAlak3OhP4pkN9p8o9uFnUVEfEDg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:11.760544Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.03866","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6cb8ff6dc980311a61c2ac154d34b2267d368787c2b5556362a4278452401a27","sha256:14911b39695a426717ee38e36e0687f4216a2f77e490519ca47820bbd79d3a9f"],"state_sha256":"5b13b6372fdc74433b4051faca579c47008450e67199a91fade2c90aa55ef7a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"40tgoA28Ipm0f0HDEZHotCtu3KtVKGukHRyndprUoxecxDZTHCpJr+jfL1gvFg8in5fkeCbzK/gp42Dd0aCVAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T14:13:34.142791Z","bundle_sha256":"7296ba18f76134d7caac71e18c3b01daa28a6a11fffcb4fa0cb93f881833950b"}}