{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:7O2JLAY5LFJXR3SUD2ERFBMSWF","short_pith_number":"pith:7O2JLAY5","canonical_record":{"source":{"id":"1707.00621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-03T16:06:16Z","cross_cats_sorted":[],"title_canon_sha256":"b6a53481552e5174308203987953123847f367aba3bc12135fa3847e7b5ebc05","abstract_canon_sha256":"ee5da8f622464a3347cbcf8d0ecca2bb1e59f183ace5debbe68e9e1a89a2e8a8"},"schema_version":"1.0"},"canonical_sha256":"fbb495831d595378ee541e89128592b14ab04b648d8878a092d36fcd4928f84a","source":{"kind":"arxiv","id":"1707.00621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.00621","created_at":"2026-05-18T00:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"1707.00621v1","created_at":"2026-05-18T00:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00621","created_at":"2026-05-18T00:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"7O2JLAY5LFJX","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7O2JLAY5LFJXR3SU","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7O2JLAY5","created_at":"2026-05-18T12:31:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:7O2JLAY5LFJXR3SUD2ERFBMSWF","target":"record","payload":{"canonical_record":{"source":{"id":"1707.00621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-03T16:06:16Z","cross_cats_sorted":[],"title_canon_sha256":"b6a53481552e5174308203987953123847f367aba3bc12135fa3847e7b5ebc05","abstract_canon_sha256":"ee5da8f622464a3347cbcf8d0ecca2bb1e59f183ace5debbe68e9e1a89a2e8a8"},"schema_version":"1.0"},"canonical_sha256":"fbb495831d595378ee541e89128592b14ab04b648d8878a092d36fcd4928f84a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:02.875020Z","signature_b64":"vHiAv/wKtDx4bDTfxM57z7ibC7t6OcACZlPCMq+eFik3lzR8+P2f3R2LpJknN6FoyqFyW6QjpHAAVQ8qxHJCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb495831d595378ee541e89128592b14ab04b648d8878a092d36fcd4928f84a","last_reissued_at":"2026-05-18T00:41:02.874281Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:02.874281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.00621","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":"2026-05-18T00:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+q6MQTI/9CifPkHo7Yd3zgXJvkFqCjMxNOUXPjSGNeUQzCzy4LJ7svWERXvm2r80oPu7FcPSYql41HdgsnuCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:05:58.891486Z"},"content_sha256":"6a4c4e397153afb74badc304114f224a02e65975bc6f703c8f7172fe3c56d30c","schema_version":"1.0","event_id":"sha256:6a4c4e397153afb74badc304114f224a02e65975bc6f703c8f7172fe3c56d30c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:7O2JLAY5LFJXR3SUD2ERFBMSWF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Including Dialects and Language Varieties in Author Profiling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alina Maria Ciobanu, Liviu P. Dinu, Marcos Zampieri, Shervin Malmasi","submitted_at":"2017-07-03T16:06:16Z","abstract_excerpt":"This paper presents a computational approach to author profiling taking gender and language variety into account. We apply an ensemble system with the output of multiple linear SVM classifiers trained on character and word $n$-grams. We evaluate the system using the dataset provided by the organizers of the 2017 PAN lab on author profiling. Our approach achieved 75% average accuracy on gender identification on tweets written in four languages and 97% accuracy on language variety identification for Portuguese."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00621","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":"2026-05-18T00:41:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NTG5SDWE2CW6MeutwYgEYm8mI6qkDMKVBuuFyeaC0Xg1LAI7L8bKCh5ycKg9fz2UiuYSfvn9hh7tHyV4htWhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T16:05:58.892201Z"},"content_sha256":"1182ca5a23e85031ca42f5ce1ec0f8afdc3756521a01ea64c7a88f95a644a515","schema_version":"1.0","event_id":"sha256:1182ca5a23e85031ca42f5ce1ec0f8afdc3756521a01ea64c7a88f95a644a515"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/bundle.json","state_url":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/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":"2026-06-07T16:05:58Z","links":{"resolver":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF","bundle":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/bundle.json","state":"https://pith.science/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7O2JLAY5LFJXR3SUD2ERFBMSWF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:7O2JLAY5LFJXR3SUD2ERFBMSWF","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":"ee5da8f622464a3347cbcf8d0ecca2bb1e59f183ace5debbe68e9e1a89a2e8a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-03T16:06:16Z","title_canon_sha256":"b6a53481552e5174308203987953123847f367aba3bc12135fa3847e7b5ebc05"},"schema_version":"1.0","source":{"id":"1707.00621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.00621","created_at":"2026-05-18T00:41:02Z"},{"alias_kind":"arxiv_version","alias_value":"1707.00621v1","created_at":"2026-05-18T00:41:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.00621","created_at":"2026-05-18T00:41:02Z"},{"alias_kind":"pith_short_12","alias_value":"7O2JLAY5LFJX","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_16","alias_value":"7O2JLAY5LFJXR3SU","created_at":"2026-05-18T12:31:05Z"},{"alias_kind":"pith_short_8","alias_value":"7O2JLAY5","created_at":"2026-05-18T12:31:05Z"}],"graph_snapshots":[{"event_id":"sha256:1182ca5a23e85031ca42f5ce1ec0f8afdc3756521a01ea64c7a88f95a644a515","target":"graph","created_at":"2026-05-18T00:41:02Z","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 presents a computational approach to author profiling taking gender and language variety into account. We apply an ensemble system with the output of multiple linear SVM classifiers trained on character and word $n$-grams. We evaluate the system using the dataset provided by the organizers of the 2017 PAN lab on author profiling. Our approach achieved 75% average accuracy on gender identification on tweets written in four languages and 97% accuracy on language variety identification for Portuguese.","authors_text":"Alina Maria Ciobanu, Liviu P. Dinu, Marcos Zampieri, Shervin Malmasi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-03T16:06:16Z","title":"Including Dialects and Language Varieties in Author Profiling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.00621","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":"sha256:6a4c4e397153afb74badc304114f224a02e65975bc6f703c8f7172fe3c56d30c","target":"record","created_at":"2026-05-18T00:41:02Z","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":"ee5da8f622464a3347cbcf8d0ecca2bb1e59f183ace5debbe68e9e1a89a2e8a8","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-03T16:06:16Z","title_canon_sha256":"b6a53481552e5174308203987953123847f367aba3bc12135fa3847e7b5ebc05"},"schema_version":"1.0","source":{"id":"1707.00621","kind":"arxiv","version":1}},"canonical_sha256":"fbb495831d595378ee541e89128592b14ab04b648d8878a092d36fcd4928f84a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbb495831d595378ee541e89128592b14ab04b648d8878a092d36fcd4928f84a","first_computed_at":"2026-05-18T00:41:02.874281Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:41:02.874281Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vHiAv/wKtDx4bDTfxM57z7ibC7t6OcACZlPCMq+eFik3lzR8+P2f3R2LpJknN6FoyqFyW6QjpHAAVQ8qxHJCDA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:41:02.875020Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.00621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a4c4e397153afb74badc304114f224a02e65975bc6f703c8f7172fe3c56d30c","sha256:1182ca5a23e85031ca42f5ce1ec0f8afdc3756521a01ea64c7a88f95a644a515"],"state_sha256":"730ee567b9f4ad3028acf9dd46bd64e25289b38b385afdee9074220d8ca7229d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7U9vt19n55WQhZz+gTcfNOcxrGfyuTiYhksvV4ZQyXJUsnoq+nouEAe3eRyk6swEEERil1BenKq/cl2M+yY7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T16:05:58.896082Z","bundle_sha256":"a878904c03b374caa58c2f4b41c9bb32b7aa70a2972380d6090bceb5767866ed"}}