{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:W62J4NWLWHY7HIQ4RXAWIBRYPA","short_pith_number":"pith:W62J4NWL","canonical_record":{"source":{"id":"1805.09991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T06:10:54Z","cross_cats_sorted":[],"title_canon_sha256":"ae412ff581c2053ccee1a477b32a13482c6b8ad94d3c7ef7987209718be1f1e1","abstract_canon_sha256":"713f15e81438a547909ea0694594449e256f0cf6ab7ab231efb29a26ad3a77ab"},"schema_version":"1.0"},"canonical_sha256":"b7b49e36cbb1f1f3a21c8dc16406387823a6c1525ca9172f06cc24a03bf26691","source":{"kind":"arxiv","id":"1805.09991","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09991","created_at":"2026-05-18T00:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09991v1","created_at":"2026-05-18T00:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09991","created_at":"2026-05-18T00:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"W62J4NWLWHY7","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"W62J4NWLWHY7HIQ4","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"W62J4NWL","created_at":"2026-05-18T12:32:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:W62J4NWLWHY7HIQ4RXAWIBRYPA","target":"record","payload":{"canonical_record":{"source":{"id":"1805.09991","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T06:10:54Z","cross_cats_sorted":[],"title_canon_sha256":"ae412ff581c2053ccee1a477b32a13482c6b8ad94d3c7ef7987209718be1f1e1","abstract_canon_sha256":"713f15e81438a547909ea0694594449e256f0cf6ab7ab231efb29a26ad3a77ab"},"schema_version":"1.0"},"canonical_sha256":"b7b49e36cbb1f1f3a21c8dc16406387823a6c1525ca9172f06cc24a03bf26691","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:14:58.567671Z","signature_b64":"AtmRgVP6UVGEGAIYWQQjBYUTTvZP1ISZeT8fj1kkwyqF+KjC+hz9i6X48InjU8dOvnModqBm0A1kG/6iq5AtCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7b49e36cbb1f1f3a21c8dc16406387823a6c1525ca9172f06cc24a03bf26691","last_reissued_at":"2026-05-18T00:14:58.567081Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:14:58.567081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1805.09991","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":"2026-05-18T00:14:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mj0fYntRSlM7FvB5T/pOWTjuFU+DCkA7wes46BLnmgsPW/YRueiRJXhivRwpmbn4L87VbLqI8Cjg5BBln8w2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T15:27:17.786945Z"},"content_sha256":"597f21952fad8d4b1a7fd13d6f4e42dabe26c729c7fe4ac592a0bddd1e73faa8","schema_version":"1.0","event_id":"sha256:597f21952fad8d4b1a7fd13d6f4e42dabe26c729c7fe4ac592a0bddd1e73faa8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:W62J4NWLWHY7HIQ4RXAWIBRYPA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lifelong Domain Word Embedding via Meta-Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Liu, Hu Xu, Lei Shu, Philip S. Yu","submitted_at":"2018-05-25T06:10:54Z","abstract_excerpt":"Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks. General-purpose embeddings trained on large-scale corpora are often sub-optimal for domain-specific applications. However, domain-specific tasks often do not have large in-domain corpora for training high-quality domain embeddings. In this paper, we propose a novel lifelong learning setting for domain embedding. That is, when performing the new domain embedding, the system has seen many past domains, and it tries to expand the new in-domain corpus by exploiting the corpora from the past "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09991","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":"2026-05-18T00:14:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rJs6bWK9sa7XJF6gvw530HGoYh8MuxMSqFzzHG3KbPntK4Pt+StrgRFWBV+igoQC+27Nh5pnwLl2GXmmuDEgDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T15:27:17.787305Z"},"content_sha256":"d8b20a4d943bf02c56fc4a49f52763d7cbb3e4410e6de35ec9b79734cfb1913b","schema_version":"1.0","event_id":"sha256:d8b20a4d943bf02c56fc4a49f52763d7cbb3e4410e6de35ec9b79734cfb1913b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W62J4NWLWHY7HIQ4RXAWIBRYPA/bundle.json","state_url":"https://pith.science/pith/W62J4NWLWHY7HIQ4RXAWIBRYPA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W62J4NWLWHY7HIQ4RXAWIBRYPA/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":"2026-07-04T15:27:17Z","links":{"resolver":"https://pith.science/pith/W62J4NWLWHY7HIQ4RXAWIBRYPA","bundle":"https://pith.science/pith/W62J4NWLWHY7HIQ4RXAWIBRYPA/bundle.json","state":"https://pith.science/pith/W62J4NWLWHY7HIQ4RXAWIBRYPA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W62J4NWLWHY7HIQ4RXAWIBRYPA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:W62J4NWLWHY7HIQ4RXAWIBRYPA","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":"713f15e81438a547909ea0694594449e256f0cf6ab7ab231efb29a26ad3a77ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T06:10:54Z","title_canon_sha256":"ae412ff581c2053ccee1a477b32a13482c6b8ad94d3c7ef7987209718be1f1e1"},"schema_version":"1.0","source":{"id":"1805.09991","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1805.09991","created_at":"2026-05-18T00:14:58Z"},{"alias_kind":"arxiv_version","alias_value":"1805.09991v1","created_at":"2026-05-18T00:14:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1805.09991","created_at":"2026-05-18T00:14:58Z"},{"alias_kind":"pith_short_12","alias_value":"W62J4NWLWHY7","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_16","alias_value":"W62J4NWLWHY7HIQ4","created_at":"2026-05-18T12:32:59Z"},{"alias_kind":"pith_short_8","alias_value":"W62J4NWL","created_at":"2026-05-18T12:32:59Z"}],"graph_snapshots":[{"event_id":"sha256:d8b20a4d943bf02c56fc4a49f52763d7cbb3e4410e6de35ec9b79734cfb1913b","target":"graph","created_at":"2026-05-18T00:14:58Z","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":"Learning high-quality domain word embeddings is important for achieving good performance in many NLP tasks. General-purpose embeddings trained on large-scale corpora are often sub-optimal for domain-specific applications. However, domain-specific tasks often do not have large in-domain corpora for training high-quality domain embeddings. In this paper, we propose a novel lifelong learning setting for domain embedding. That is, when performing the new domain embedding, the system has seen many past domains, and it tries to expand the new in-domain corpus by exploiting the corpora from the past ","authors_text":"Bing Liu, Hu Xu, Lei Shu, Philip S. Yu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T06:10:54Z","title":"Lifelong Domain Word Embedding via Meta-Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1805.09991","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":"sha256:597f21952fad8d4b1a7fd13d6f4e42dabe26c729c7fe4ac592a0bddd1e73faa8","target":"record","created_at":"2026-05-18T00:14:58Z","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":"713f15e81438a547909ea0694594449e256f0cf6ab7ab231efb29a26ad3a77ab","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-05-25T06:10:54Z","title_canon_sha256":"ae412ff581c2053ccee1a477b32a13482c6b8ad94d3c7ef7987209718be1f1e1"},"schema_version":"1.0","source":{"id":"1805.09991","kind":"arxiv","version":1}},"canonical_sha256":"b7b49e36cbb1f1f3a21c8dc16406387823a6c1525ca9172f06cc24a03bf26691","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b7b49e36cbb1f1f3a21c8dc16406387823a6c1525ca9172f06cc24a03bf26691","first_computed_at":"2026-05-18T00:14:58.567081Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:14:58.567081Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AtmRgVP6UVGEGAIYWQQjBYUTTvZP1ISZeT8fj1kkwyqF+KjC+hz9i6X48InjU8dOvnModqBm0A1kG/6iq5AtCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:14:58.567671Z","signed_message":"canonical_sha256_bytes"},"source_id":"1805.09991","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:597f21952fad8d4b1a7fd13d6f4e42dabe26c729c7fe4ac592a0bddd1e73faa8","sha256:d8b20a4d943bf02c56fc4a49f52763d7cbb3e4410e6de35ec9b79734cfb1913b"],"state_sha256":"8ebeb74b2d2eb99910f3dbddf433051bdf0aac4a92a72ceb4d4020768fea3bfc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZPmheujWB2LRFy/dboXGREsHl+EX8YBlId5wO75T+ckhQjlUpyIcpwp0cyyIyGHzLZDLq6e+CJSRuaxQ5BItBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T15:27:17.789456Z","bundle_sha256":"29b4b25865d92599229c505264cf3829590c56fc95ebbe942ecf54ac54d61bf5"}}