{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:3LQSZKHABFETDZO4TNU2NMD65B","short_pith_number":"pith:3LQSZKHA","canonical_record":{"source":{"id":"1904.03799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T01:50:45Z","cross_cats_sorted":[],"title_canon_sha256":"d306b03b4bb3561e66317a1fc0d9f69404d679733ccd92c28a15017f04555a31","abstract_canon_sha256":"363b3638d82ca90f920fd3411d1877089abd71701181776e9816b7d542bd055b"},"schema_version":"1.0"},"canonical_sha256":"dae12ca8e0094931e5dc9b69a6b07ee85ce396840e36afe3c58c87661ddc02ee","source":{"kind":"arxiv","id":"1904.03799","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03799","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03799v2","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03799","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"3LQSZKHABFET","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"3LQSZKHABFETDZO4","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"3LQSZKHA","created_at":"2026-07-05T02:06:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:3LQSZKHABFETDZO4TNU2NMD65B","target":"record","payload":{"canonical_record":{"source":{"id":"1904.03799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T01:50:45Z","cross_cats_sorted":[],"title_canon_sha256":"d306b03b4bb3561e66317a1fc0d9f69404d679733ccd92c28a15017f04555a31","abstract_canon_sha256":"363b3638d82ca90f920fd3411d1877089abd71701181776e9816b7d542bd055b"},"schema_version":"1.0"},"canonical_sha256":"dae12ca8e0094931e5dc9b69a6b07ee85ce396840e36afe3c58c87661ddc02ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:06:28.577752Z","signature_b64":"Fv6wjsAwE2QZmFWscSH1HPmzJB/XRJCHmylhBEerM1lSCoC5Mvsh2J1R3sNueac73WM1KCOKlST3Yvuo50sRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dae12ca8e0094931e5dc9b69a6b07ee85ce396840e36afe3c58c87661ddc02ee","last_reissued_at":"2026-07-05T02:06:28.577362Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:06:28.577362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.03799","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:06:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"38228tMI2qrPD5RzGyENh4KP2rZJx2bideOOp5oP7+UJBbNhBfFGfXDXYFAQchx+C9kTUF5O74qhlv95ycm7BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:26:45.332224Z"},"content_sha256":"6a031b359b4eeeb88bab5d15fd1a4f6ccade30ea3f673b1425c75e3348152cd9","schema_version":"1.0","event_id":"sha256:6a031b359b4eeeb88bab5d15fd1a4f6ccade30ea3f673b1425c75e3348152cd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:3LQSZKHABFETDZO4TNU2NMD65B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Eng Siong Chng, Haihua Xu, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","submitted_at":"2019-04-08T01:50:45Z","abstract_excerpt":"The neural language models (NLM) achieve strong generalization capability by learning the dense representation of words and using them to estimate probability distribution function. However, learning the representation of rare words is a challenging problem causing the NLM to produce unreliable probability estimates. To address this problem, we propose a method to enrich representations of rare words in pre-trained NLM and consequently improve its probability estimation performance. The proposed method augments the word embedding matrices of pre-trained NLM while keeping other parameters uncha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03799","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/1904.03799/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T02:06:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4w9cgFBY3XdkOzxVDHsp3KHIJMiDKycFZOVzmULo5HtJUT4V9/pQ4/ZhRZNFzEf0zZtUlxt+8hFQKiWA0+okCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:26:45.332722Z"},"content_sha256":"57a3d84f4907e28b9b3a099b08ed926fff370ee81a393166bf51eb3edf35e180","schema_version":"1.0","event_id":"sha256:57a3d84f4907e28b9b3a099b08ed926fff370ee81a393166bf51eb3edf35e180"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3LQSZKHABFETDZO4TNU2NMD65B/bundle.json","state_url":"https://pith.science/pith/3LQSZKHABFETDZO4TNU2NMD65B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3LQSZKHABFETDZO4TNU2NMD65B/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":"2026-08-03T16:26:45Z","links":{"resolver":"https://pith.science/pith/3LQSZKHABFETDZO4TNU2NMD65B","bundle":"https://pith.science/pith/3LQSZKHABFETDZO4TNU2NMD65B/bundle.json","state":"https://pith.science/pith/3LQSZKHABFETDZO4TNU2NMD65B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3LQSZKHABFETDZO4TNU2NMD65B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:3LQSZKHABFETDZO4TNU2NMD65B","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":"363b3638d82ca90f920fd3411d1877089abd71701181776e9816b7d542bd055b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T01:50:45Z","title_canon_sha256":"d306b03b4bb3561e66317a1fc0d9f69404d679733ccd92c28a15017f04555a31"},"schema_version":"1.0","source":{"id":"1904.03799","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.03799","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"arxiv_version","alias_value":"1904.03799v2","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.03799","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"pith_short_12","alias_value":"3LQSZKHABFET","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"pith_short_16","alias_value":"3LQSZKHABFETDZO4","created_at":"2026-07-05T02:06:28Z"},{"alias_kind":"pith_short_8","alias_value":"3LQSZKHA","created_at":"2026-07-05T02:06:28Z"}],"graph_snapshots":[{"event_id":"sha256:57a3d84f4907e28b9b3a099b08ed926fff370ee81a393166bf51eb3edf35e180","target":"graph","created_at":"2026-07-05T02:06:28Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1904.03799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The neural language models (NLM) achieve strong generalization capability by learning the dense representation of words and using them to estimate probability distribution function. However, learning the representation of rare words is a challenging problem causing the NLM to produce unreliable probability estimates. To address this problem, we propose a method to enrich representations of rare words in pre-trained NLM and consequently improve its probability estimation performance. The proposed method augments the word embedding matrices of pre-trained NLM while keeping other parameters uncha","authors_text":"Eng Siong Chng, Haihua Xu, Van Tung Pham, Yerbolat Khassanov, Zhiping Zeng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T01:50:45Z","title":"Enriching Rare Word Representations in Neural Language Models by Embedding Matrix Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.03799","kind":"arxiv","version":2},"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":"sha256:6a031b359b4eeeb88bab5d15fd1a4f6ccade30ea3f673b1425c75e3348152cd9","target":"record","created_at":"2026-07-05T02:06:28Z","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":"363b3638d82ca90f920fd3411d1877089abd71701181776e9816b7d542bd055b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-08T01:50:45Z","title_canon_sha256":"d306b03b4bb3561e66317a1fc0d9f69404d679733ccd92c28a15017f04555a31"},"schema_version":"1.0","source":{"id":"1904.03799","kind":"arxiv","version":2}},"canonical_sha256":"dae12ca8e0094931e5dc9b69a6b07ee85ce396840e36afe3c58c87661ddc02ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"dae12ca8e0094931e5dc9b69a6b07ee85ce396840e36afe3c58c87661ddc02ee","first_computed_at":"2026-07-05T02:06:28.577362Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:06:28.577362Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Fv6wjsAwE2QZmFWscSH1HPmzJB/XRJCHmylhBEerM1lSCoC5Mvsh2J1R3sNueac73WM1KCOKlST3Yvuo50sRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:06:28.577752Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.03799","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a031b359b4eeeb88bab5d15fd1a4f6ccade30ea3f673b1425c75e3348152cd9","sha256:57a3d84f4907e28b9b3a099b08ed926fff370ee81a393166bf51eb3edf35e180"],"state_sha256":"fccc2ce9c10d13b88c336ed04af68087775fef55e2d7ee6565984a8c9af1182f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oU/DHtbHLJKBf8a5//XWlUrI0BntyRUsDz3QWj4SjV1ExrMTLwhwd16DsLAuQcmkFnvDAwckpxvA1CQcWgeQDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:26:45.338685Z","bundle_sha256":"bc99bfa5a01d4781125d702ea792cf8716033f08593ec348f368e1a30ad87da1"}}