{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:T6IV6J7T6LA5TMLOZORFIWRHZG","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":"8ea1039aa3938956f90c3442a2b6d18daebf10e1716e6636a02cac559c3b4f19","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-04-18T18:19:03Z","title_canon_sha256":"d58cc68b259eaed66ec6b79a0f599c977d321c99943f2e6df16f8d926afa8a92"},"schema_version":"1.0","source":{"id":"2104.08928","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.08928","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"arxiv_version","alias_value":"2104.08928v4","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.08928","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"pith_short_12","alias_value":"T6IV6J7T6LA5","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"pith_short_16","alias_value":"T6IV6J7T6LA5TMLO","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"pith_short_8","alias_value":"T6IV6J7T","created_at":"2026-06-19T16:12:12Z"}],"graph_snapshots":[{"event_id":"sha256:37d489b9c2a5ad36d0211add2d686a3a0b72c32a4ecebe9acccca96f5bf4246c","target":"graph","created_at":"2026-06-19T16:12:12Z","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/2104.08928/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Unstructured text provides decision-makers with a rich data source in many domains, ranging from product reviews in retail to nursing notes in healthcare. To leverage this information, words are typically translated into word embeddings -- vectors that encode the semantic relationships between words -- through unsupervised learning algorithms such as matrix factorization. However, learning word embeddings from new domains with limited training data can be challenging, because the meaning/usage may be different in the new domain, e.g., the word ``positive'' typically has positive sentiment, but","authors_text":"Hamsa Bastani, Kan Xu, Osbert Bastani, Xuanyi Zhao","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-04-18T18:19:03Z","title":"Group-Sparse Matrix Factorization for Transfer Learning of Word Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.08928","kind":"arxiv","version":4},"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":"sha256:5ba4044096bf2b633d7a1e6b29b0337876217f30e80661f37195b7f8573ef076","target":"record","created_at":"2026-06-19T16:12:12Z","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":"8ea1039aa3938956f90c3442a2b6d18daebf10e1716e6636a02cac559c3b4f19","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2021-04-18T18:19:03Z","title_canon_sha256":"d58cc68b259eaed66ec6b79a0f599c977d321c99943f2e6df16f8d926afa8a92"},"schema_version":"1.0","source":{"id":"2104.08928","kind":"arxiv","version":4}},"canonical_sha256":"9f915f27f3f2c1d9b16ecba2545a27c9acdca5e18e519e8b78efd3aa627e19d6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f915f27f3f2c1d9b16ecba2545a27c9acdca5e18e519e8b78efd3aa627e19d6","first_computed_at":"2026-06-19T16:12:12.011024Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:12.011024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"faQrwSYUeNE5quMaZP0xe9lgM9ah+lHlSMzOBKfINkBblQt9EUcb2NoAvSXx26UK0nMgrjSQRrEJ2qnhA/YeBg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:12.011381Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.08928","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ba4044096bf2b633d7a1e6b29b0337876217f30e80661f37195b7f8573ef076","sha256:37d489b9c2a5ad36d0211add2d686a3a0b72c32a4ecebe9acccca96f5bf4246c"],"state_sha256":"b86f4ce8f24d62b3df6cf72d0fac7a510e3188967457804025a9b0e8972ac881"}