{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WRXQI3MRH637OUMUOIYIT7CBK5","short_pith_number":"pith:WRXQI3MR","schema_version":"1.0","canonical_sha256":"b46f046d913fb7f75194723089fc415777608b870e6f6f1c49d37175aa48a5bb","source":{"kind":"arxiv","id":"1709.00947","version":1},"attestation_state":"computed","paper":{"title":"Learning Word Embeddings from the Portuguese Twitter Stream: A Study of some Practical Aspects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Carlos Soares, Eduarda Mendes Rodrigues, Eug\\'enio Oliveira, Lu\\'is Sarmento, Pedro Saleiro","submitted_at":"2017-09-04T13:30:23Z","abstract_excerpt":"This paper describes a preliminary study for producing and distributing a large-scale database of embeddings from the Portuguese Twitter stream. We start by experimenting with a relatively small sample and focusing on three challenges: volume of training data, vocabulary size and intrinsic evaluation metrics. Using a single GPU, we were able to scale up vocabulary size from 2048 words embedded and 500K training examples to 32768 words over 10M training examples while keeping a stable validation loss and approximately linear trend on training time per epoch. We also observed that using less tha"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1709.00947","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-04T13:30:23Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fcdcda77d6082e7b83fc5425adef40b448d3d8c3fb5bbc6b4ce14267c20d6c6b","abstract_canon_sha256":"12dd43a678c1c7656662d85729394aaa6e93a171e6720d42fef25bc44aeea34e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:04.649099Z","signature_b64":"zzP3RYYsPkYs1dvG6gTVLYez3h7Nq++ntzMCGGtpWAFZrAov/ZGqcc0ybJJIA/ZVzK30YHWzOFTs4aXfoI8hAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b46f046d913fb7f75194723089fc415777608b870e6f6f1c49d37175aa48a5bb","last_reissued_at":"2026-05-18T00:36:04.648574Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:04.648574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Word Embeddings from the Portuguese Twitter Stream: A Study of some Practical Aspects","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Carlos Soares, Eduarda Mendes Rodrigues, Eug\\'enio Oliveira, Lu\\'is Sarmento, Pedro Saleiro","submitted_at":"2017-09-04T13:30:23Z","abstract_excerpt":"This paper describes a preliminary study for producing and distributing a large-scale database of embeddings from the Portuguese Twitter stream. We start by experimenting with a relatively small sample and focusing on three challenges: volume of training data, vocabulary size and intrinsic evaluation metrics. Using a single GPU, we were able to scale up vocabulary size from 2048 words embedded and 500K training examples to 32768 words over 10M training examples while keeping a stable validation loss and approximately linear trend on training time per epoch. We also observed that using less tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00947","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1709.00947","created_at":"2026-05-18T00:36:04.648651+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.00947v1","created_at":"2026-05-18T00:36:04.648651+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00947","created_at":"2026-05-18T00:36:04.648651+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRXQI3MRH637","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRXQI3MRH637OUMU","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRXQI3MR","created_at":"2026-05-18T12:31:53.515858+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5","json":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5.json","graph_json":"https://pith.science/api/pith-number/WRXQI3MRH637OUMUOIYIT7CBK5/graph.json","events_json":"https://pith.science/api/pith-number/WRXQI3MRH637OUMUOIYIT7CBK5/events.json","paper":"https://pith.science/paper/WRXQI3MR"},"agent_actions":{"view_html":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5","download_json":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5.json","view_paper":"https://pith.science/paper/WRXQI3MR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.00947&json=true","fetch_graph":"https://pith.science/api/pith-number/WRXQI3MRH637OUMUOIYIT7CBK5/graph.json","fetch_events":"https://pith.science/api/pith-number/WRXQI3MRH637OUMUOIYIT7CBK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5/action/storage_attestation","attest_author":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5/action/author_attestation","sign_citation":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5/action/citation_signature","submit_replication":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5/action/replication_record"}},"created_at":"2026-05-18T00:36:04.648651+00:00","updated_at":"2026-05-18T00:36:04.648651+00:00"}