{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:SRQZSRVVJWQL62EPN5XXLIQ652","short_pith_number":"pith:SRQZSRVV","canonical_record":{"source":{"id":"1903.09878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T20:25:40Z","cross_cats_sorted":[],"title_canon_sha256":"7e0039d05c9aca50eda0a5399e1417868b6853e35c6b2a35b2a1a1ba83c012c1","abstract_canon_sha256":"4d944844487835093c763e8e52919685cd980d60983586952b98537276de258e"},"schema_version":"1.0"},"canonical_sha256":"94619946b54da0bf688f6f6f75a21eee97ba4746f7f9015c1673e6a19efd9a9d","source":{"kind":"arxiv","id":"1903.09878","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09878","created_at":"2026-05-17T23:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09878v2","created_at":"2026-05-17T23:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09878","created_at":"2026-05-17T23:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"SRQZSRVVJWQL","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SRQZSRVVJWQL62EP","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SRQZSRVV","created_at":"2026-05-18T12:33:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:SRQZSRVVJWQL62EPN5XXLIQ652","target":"record","payload":{"canonical_record":{"source":{"id":"1903.09878","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T20:25:40Z","cross_cats_sorted":[],"title_canon_sha256":"7e0039d05c9aca50eda0a5399e1417868b6853e35c6b2a35b2a1a1ba83c012c1","abstract_canon_sha256":"4d944844487835093c763e8e52919685cd980d60983586952b98537276de258e"},"schema_version":"1.0"},"canonical_sha256":"94619946b54da0bf688f6f6f75a21eee97ba4746f7f9015c1673e6a19efd9a9d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:50:04.320036Z","signature_b64":"GJhfOXLseIW8q1qNbTxZ54OFRbTKFtwpcqWfomvUpjHBw77lPuCGnqS4DIa0vQQuweFh2WW7AhkAZ+vPmpYJCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94619946b54da0bf688f6f6f75a21eee97ba4746f7f9015c1673e6a19efd9a9d","last_reissued_at":"2026-05-17T23:50:04.319593Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:50:04.319593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1903.09878","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":"2026-05-17T23:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"puQsoSV57/hS9zWu7T29bvkTAJe8UCfNTw7PTDH8E4/3HoDn661/zQkPD9PzOjMI6quSMPRhJaaM0WffrhPUDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:53:52.192717Z"},"content_sha256":"1ed11e7e2ca1781df840a789958657c1cfe1e88fc123e34dad34dba8186c13a0","schema_version":"1.0","event_id":"sha256:1ed11e7e2ca1781df840a789958657c1cfe1e88fc123e34dad34dba8186c13a0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:SRQZSRVVJWQL62EPN5XXLIQ652","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Expanding the Text Classification Toolbox with Cross-Lingual Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andreea Hossmann, Claudiu Musat, Meryem M'hamdi, Michael Baeriswyl, Robert West","submitted_at":"2019-03-23T20:25:40Z","abstract_excerpt":"Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the artificial intelligence (AI) divide. Transfer-based approaches, such as Cross-Lingual Text Classification (CLTC) - the task of categorizing texts written in different languages into a common taxonomy, are a promising solution to the emerging AI divide. Recent work on CLTC has focused on demonstrating the benefits of using bilingual word embeddings as features, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09878","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":""},"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":"2026-05-17T23:50:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X2zVzmMie3a4dMPH/fAq6Lg9BZlD7I9BK4+hQHKzydAHriCBWC6C8XPB4PVrl4E51rutlW2ciiXETPkYcVyOAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T04:53:52.193349Z"},"content_sha256":"0f88281882be2d6f3201c813357cc0ded770a31a0717f9177de5bad8bf6c705a","schema_version":"1.0","event_id":"sha256:0f88281882be2d6f3201c813357cc0ded770a31a0717f9177de5bad8bf6c705a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652/bundle.json","state_url":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRQZSRVVJWQL62EPN5XXLIQ652/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":"2026-06-05T04:53:52Z","links":{"resolver":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652","bundle":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652/bundle.json","state":"https://pith.science/pith/SRQZSRVVJWQL62EPN5XXLIQ652/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRQZSRVVJWQL62EPN5XXLIQ652/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:SRQZSRVVJWQL62EPN5XXLIQ652","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":"4d944844487835093c763e8e52919685cd980d60983586952b98537276de258e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T20:25:40Z","title_canon_sha256":"7e0039d05c9aca50eda0a5399e1417868b6853e35c6b2a35b2a1a1ba83c012c1"},"schema_version":"1.0","source":{"id":"1903.09878","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1903.09878","created_at":"2026-05-17T23:50:04Z"},{"alias_kind":"arxiv_version","alias_value":"1903.09878v2","created_at":"2026-05-17T23:50:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.09878","created_at":"2026-05-17T23:50:04Z"},{"alias_kind":"pith_short_12","alias_value":"SRQZSRVVJWQL","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_16","alias_value":"SRQZSRVVJWQL62EP","created_at":"2026-05-18T12:33:27Z"},{"alias_kind":"pith_short_8","alias_value":"SRQZSRVV","created_at":"2026-05-18T12:33:27Z"}],"graph_snapshots":[{"event_id":"sha256:0f88281882be2d6f3201c813357cc0ded770a31a0717f9177de5bad8bf6c705a","target":"graph","created_at":"2026-05-17T23:50:04Z","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":"Most work in text classification and Natural Language Processing (NLP) focuses on English or a handful of other languages that have text corpora of hundreds of millions of words. This is creating a new version of the digital divide: the artificial intelligence (AI) divide. Transfer-based approaches, such as Cross-Lingual Text Classification (CLTC) - the task of categorizing texts written in different languages into a common taxonomy, are a promising solution to the emerging AI divide. Recent work on CLTC has focused on demonstrating the benefits of using bilingual word embeddings as features, ","authors_text":"Andreea Hossmann, Claudiu Musat, Meryem M'hamdi, Michael Baeriswyl, Robert West","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T20:25:40Z","title":"Expanding the Text Classification Toolbox with Cross-Lingual Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.09878","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":"sha256:1ed11e7e2ca1781df840a789958657c1cfe1e88fc123e34dad34dba8186c13a0","target":"record","created_at":"2026-05-17T23:50:04Z","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":"4d944844487835093c763e8e52919685cd980d60983586952b98537276de258e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-03-23T20:25:40Z","title_canon_sha256":"7e0039d05c9aca50eda0a5399e1417868b6853e35c6b2a35b2a1a1ba83c012c1"},"schema_version":"1.0","source":{"id":"1903.09878","kind":"arxiv","version":2}},"canonical_sha256":"94619946b54da0bf688f6f6f75a21eee97ba4746f7f9015c1673e6a19efd9a9d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94619946b54da0bf688f6f6f75a21eee97ba4746f7f9015c1673e6a19efd9a9d","first_computed_at":"2026-05-17T23:50:04.319593Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:50:04.319593Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GJhfOXLseIW8q1qNbTxZ54OFRbTKFtwpcqWfomvUpjHBw77lPuCGnqS4DIa0vQQuweFh2WW7AhkAZ+vPmpYJCg==","signature_status":"signed_v1","signed_at":"2026-05-17T23:50:04.320036Z","signed_message":"canonical_sha256_bytes"},"source_id":"1903.09878","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ed11e7e2ca1781df840a789958657c1cfe1e88fc123e34dad34dba8186c13a0","sha256:0f88281882be2d6f3201c813357cc0ded770a31a0717f9177de5bad8bf6c705a"],"state_sha256":"96e2309e0e87205b71bde79a951934892fa10441ce38902c6887cd55ea49f821"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sGKP/WUfCWEyoh55ZrKKxL71uoGtdzMC4PUZPuStl7E+rN31C3r0L5p5STdVC2QWH714g404cq3Q4SBcNE6zAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T04:53:52.198162Z","bundle_sha256":"d604adda17f37424e9851f31a82acf97e5911293f08059613e2dae83626c1983"}}