{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:AYYQHHRRLJXQ3US3SC3ACMBI3Q","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":"b948e205206df1a87d59cb1f30b28e8beebe7b153ea28bf0fcbbeab24e7a9974","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-10-09T13:41:18Z","title_canon_sha256":"0c2cc944fcaafe9c3053869a5098914cb8b563f67677a2c6aefd25e320fe76d0"},"schema_version":"1.0","source":{"id":"1410.2455","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1410.2455","created_at":"2026-05-18T01:21:19Z"},{"alias_kind":"arxiv_version","alias_value":"1410.2455v3","created_at":"2026-05-18T01:21:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1410.2455","created_at":"2026-05-18T01:21:19Z"},{"alias_kind":"pith_short_12","alias_value":"AYYQHHRRLJXQ","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"AYYQHHRRLJXQ3US3","created_at":"2026-05-18T12:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"AYYQHHRR","created_at":"2026-05-18T12:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:3c642a05a249ad65d424f12d0201a3ed8a53691b2fe5ea43672c8bfd164d8213","target":"graph","created_at":"2026-05-18T01:21:19Z","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":"We introduce BilBOWA (Bilingual Bag-of-Words without Alignments), a simple and computationally-efficient model for learning bilingual distributed representations of words which can scale to large monolingual datasets and does not require word-aligned parallel training data. Instead it trains directly on monolingual data and extracts a bilingual signal from a smaller set of raw-text sentence-aligned data. This is achieved using a novel sampled bag-of-words cross-lingual objective, which is used to regularize two noise-contrastive language models for efficient cross-lingual feature learning. We ","authors_text":"Greg Corrado, Stephan Gouws, Yoshua Bengio","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-10-09T13:41:18Z","title":"BilBOWA: Fast Bilingual Distributed Representations without Word Alignments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1410.2455","kind":"arxiv","version":3},"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":"sha256:92dcd4d2d98bf55e9f4535ca7481cc19befcb799862e5417727fa59207d6c39e","target":"record","created_at":"2026-05-18T01:21:19Z","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":"b948e205206df1a87d59cb1f30b28e8beebe7b153ea28bf0fcbbeab24e7a9974","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2014-10-09T13:41:18Z","title_canon_sha256":"0c2cc944fcaafe9c3053869a5098914cb8b563f67677a2c6aefd25e320fe76d0"},"schema_version":"1.0","source":{"id":"1410.2455","kind":"arxiv","version":3}},"canonical_sha256":"0631039e315a6f0dd25b90b6013028dc17994fab421dce391929c64a1b55b088","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0631039e315a6f0dd25b90b6013028dc17994fab421dce391929c64a1b55b088","first_computed_at":"2026-05-18T01:21:19.879778Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:21:19.879778Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AvB2BBRq+wgX3PlnIViXpMmNlLN+pCCxwvKUFrEaYx0v+yRx/C5cbJ113B8meO0vtlB6dziJ0CtYuj2TE/SOBg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:21:19.880298Z","signed_message":"canonical_sha256_bytes"},"source_id":"1410.2455","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:92dcd4d2d98bf55e9f4535ca7481cc19befcb799862e5417727fa59207d6c39e","sha256:3c642a05a249ad65d424f12d0201a3ed8a53691b2fe5ea43672c8bfd164d8213"],"state_sha256":"e44bf52e3b9977f890f38828d578d259941df377eec66451185e79b63b3fa954"}