{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:WRXQI3MRH637OUMUOIYIT7CBK5","short_pith_number":"pith:WRXQI3MR","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"},"canonical_sha256":"b46f046d913fb7f75194723089fc415777608b870e6f6f1c49d37175aa48a5bb","source":{"kind":"arxiv","id":"1709.00947","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00947","created_at":"2026-05-18T00:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00947v1","created_at":"2026-05-18T00:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00947","created_at":"2026-05-18T00:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"WRXQI3MRH637","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WRXQI3MRH637OUMU","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WRXQI3MR","created_at":"2026-05-18T12:31:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:WRXQI3MRH637OUMUOIYIT7CBK5","target":"record","payload":{"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"},"canonical_sha256":"b46f046d913fb7f75194723089fc415777608b870e6f6f1c49d37175aa48a5bb","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"},"source_kind":"arxiv","source_id":"1709.00947","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":"2026-05-18T00:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NOJp6CVCFLarVzR4xyIQusXrZg5hELIlh0tbMxpRSWwYI9ZKzOCN5r1aba2/tLuwyBrl7TRQfJhdjCRO9ZnPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:23:31.187244Z"},"content_sha256":"de03f25ba273d1e3122a372822f72c17048b8f4945962efd64286c82d1c5aac7","schema_version":"1.0","event_id":"sha256:de03f25ba273d1e3122a372822f72c17048b8f4945962efd64286c82d1c5aac7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:WRXQI3MRH637OUMUOIYIT7CBK5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:36:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sx2icRsVdVaDyun0xrDNTxTzHQsYT7KVFcEaGX6eT9Owau61vj/x6fFNIFLiP33/+gUnTcFaFWan9S19dmvHAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T22:23:31.187947Z"},"content_sha256":"ffca296cce397ba253de59159d079b1d8d4324fdb68a359bdc37f89f1a2cdfcc","schema_version":"1.0","event_id":"sha256:ffca296cce397ba253de59159d079b1d8d4324fdb68a359bdc37f89f1a2cdfcc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5/bundle.json","state_url":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WRXQI3MRH637OUMUOIYIT7CBK5/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":"2026-05-27T22:23:31Z","links":{"resolver":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5","bundle":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5/bundle.json","state":"https://pith.science/pith/WRXQI3MRH637OUMUOIYIT7CBK5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WRXQI3MRH637OUMUOIYIT7CBK5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:WRXQI3MRH637OUMUOIYIT7CBK5","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":"12dd43a678c1c7656662d85729394aaa6e93a171e6720d42fef25bc44aeea34e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-04T13:30:23Z","title_canon_sha256":"fcdcda77d6082e7b83fc5425adef40b448d3d8c3fb5bbc6b4ce14267c20d6c6b"},"schema_version":"1.0","source":{"id":"1709.00947","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.00947","created_at":"2026-05-18T00:36:04Z"},{"alias_kind":"arxiv_version","alias_value":"1709.00947v1","created_at":"2026-05-18T00:36:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.00947","created_at":"2026-05-18T00:36:04Z"},{"alias_kind":"pith_short_12","alias_value":"WRXQI3MRH637","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_16","alias_value":"WRXQI3MRH637OUMU","created_at":"2026-05-18T12:31:53Z"},{"alias_kind":"pith_short_8","alias_value":"WRXQI3MR","created_at":"2026-05-18T12:31:53Z"}],"graph_snapshots":[{"event_id":"sha256:ffca296cce397ba253de59159d079b1d8d4324fdb68a359bdc37f89f1a2cdfcc","target":"graph","created_at":"2026-05-18T00:36:04Z","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":"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","authors_text":"Carlos Soares, Eduarda Mendes Rodrigues, Eug\\'enio Oliveira, Lu\\'is Sarmento, Pedro Saleiro","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-04T13:30:23Z","title":"Learning Word Embeddings from the Portuguese Twitter Stream: A Study of some Practical Aspects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.00947","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:de03f25ba273d1e3122a372822f72c17048b8f4945962efd64286c82d1c5aac7","target":"record","created_at":"2026-05-18T00:36:04Z","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":"12dd43a678c1c7656662d85729394aaa6e93a171e6720d42fef25bc44aeea34e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-09-04T13:30:23Z","title_canon_sha256":"fcdcda77d6082e7b83fc5425adef40b448d3d8c3fb5bbc6b4ce14267c20d6c6b"},"schema_version":"1.0","source":{"id":"1709.00947","kind":"arxiv","version":1}},"canonical_sha256":"b46f046d913fb7f75194723089fc415777608b870e6f6f1c49d37175aa48a5bb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b46f046d913fb7f75194723089fc415777608b870e6f6f1c49d37175aa48a5bb","first_computed_at":"2026-05-18T00:36:04.648574Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:04.648574Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zzP3RYYsPkYs1dvG6gTVLYez3h7Nq++ntzMCGGtpWAFZrAov/ZGqcc0ybJJIA/ZVzK30YHWzOFTs4aXfoI8hAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:04.649099Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.00947","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de03f25ba273d1e3122a372822f72c17048b8f4945962efd64286c82d1c5aac7","sha256:ffca296cce397ba253de59159d079b1d8d4324fdb68a359bdc37f89f1a2cdfcc"],"state_sha256":"30d7cc102551db8cbcf7ef9ec99615d11a58f14bb7975d8eec5d34ebd24f9a41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AzoMtAOWdc1gfOV0CGARwxSgk8gLN/FHRl7DQ10sRNpBK0gVQvErj81l2RwICxinTqTvv5QrPoOBd5acmLaUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T22:23:31.191608Z","bundle_sha256":"d73de9c52e0af82099415575637ce2e7ac1c263d9a60c0de98cdb978629344d5"}}