{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:KAUEVVMRZQ3NBN37CTBCCPQXLS","short_pith_number":"pith:KAUEVVMR","canonical_record":{"source":{"id":"1707.03764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-12T15:34:21Z","cross_cats_sorted":[],"title_canon_sha256":"2f8f5d7ec90b2f0b644c470cf24a34d90c9a13b57cc331b9935b467bf0384871","abstract_canon_sha256":"aad717d281192e4ee3e0e22cb0d2b10d0121f2a59cc1803eda077ab99d627472"},"schema_version":"1.0"},"canonical_sha256":"50284ad591cc36d0b77f14c2213e175c9b512352569c8b33f3eff396b2419383","source":{"kind":"arxiv","id":"1707.03764","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03764","created_at":"2026-05-18T00:40:24Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03764v1","created_at":"2026-05-18T00:40:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03764","created_at":"2026-05-18T00:40:24Z"},{"alias_kind":"pith_short_12","alias_value":"KAUEVVMRZQ3N","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KAUEVVMRZQ3NBN37","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KAUEVVMR","created_at":"2026-05-18T12:31:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:KAUEVVMRZQ3NBN37CTBCCPQXLS","target":"record","payload":{"canonical_record":{"source":{"id":"1707.03764","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-12T15:34:21Z","cross_cats_sorted":[],"title_canon_sha256":"2f8f5d7ec90b2f0b644c470cf24a34d90c9a13b57cc331b9935b467bf0384871","abstract_canon_sha256":"aad717d281192e4ee3e0e22cb0d2b10d0121f2a59cc1803eda077ab99d627472"},"schema_version":"1.0"},"canonical_sha256":"50284ad591cc36d0b77f14c2213e175c9b512352569c8b33f3eff396b2419383","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:24.879233Z","signature_b64":"11K+FsO4Egvgf7ZIBabHKWnQ9TJeSiRcjnrHKvSlrbTn2zx7yY7pZWNhhFOUwRoEGyK9MfXlnSBB59/ggcm8BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"50284ad591cc36d0b77f14c2213e175c9b512352569c8b33f3eff396b2419383","last_reissued_at":"2026-05-18T00:40:24.878485Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:24.878485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.03764","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":"2026-05-18T00:40:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YXp62/bga1ixs5e+NCskv5VHOXB+ALyE/seAIO5KEAJ2NG3aPAJuFeX0P0Hlw6DeYTvAPHuUv0LqwUrNnSdsCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T19:28:01.460916Z"},"content_sha256":"ef7e0b00d2e3e526a4ec6d3e6e3752940586e3df6360aa6fdba065e53fd89955","schema_version":"1.0","event_id":"sha256:ef7e0b00d2e3e526a4ec6d3e6e3752940586e3df6360aa6fdba065e53fd89955"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:KAUEVVMRZQ3NBN37CTBCCPQXLS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"N-GrAM: New Groningen Author-profiling Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Angelo Basile, Gareth Dwyer, Hessel Haagsma, Josine Rawee, Malvina Nissim, Maria Medvedeva","submitted_at":"2017-07-12T15:34:21Z","abstract_excerpt":"We describe our participation in the PAN 2017 shared task on Author Profiling, identifying authors' gender and language variety for English, Spanish, Arabic and Portuguese. We describe both the final, submitted system, and a series of negative results. Our aim was to create a single model for both gender and language, and for all language varieties. Our best-performing system (on cross-validated results) is a linear support vector machine (SVM) with word unigrams and character 3- to 5-grams as features. A set of additional features, including POS tags, additional datasets, geographic entities,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03764","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":"2026-05-18T00:40:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PVvq0zJdUhfaPjqjA/TK9D9ca6TbqmdrhoIyTpL5HssYuvCQ058FMKYlZc4M8FfUIPNS2uwisgSfgss/mz0wCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T19:28:01.461245Z"},"content_sha256":"3c6ede3c9f07ce52bc8fadb3f75bf2d492f8af3e874a6e482732c3f51120022e","schema_version":"1.0","event_id":"sha256:3c6ede3c9f07ce52bc8fadb3f75bf2d492f8af3e874a6e482732c3f51120022e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KAUEVVMRZQ3NBN37CTBCCPQXLS/bundle.json","state_url":"https://pith.science/pith/KAUEVVMRZQ3NBN37CTBCCPQXLS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KAUEVVMRZQ3NBN37CTBCCPQXLS/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":"2026-06-28T19:28:01Z","links":{"resolver":"https://pith.science/pith/KAUEVVMRZQ3NBN37CTBCCPQXLS","bundle":"https://pith.science/pith/KAUEVVMRZQ3NBN37CTBCCPQXLS/bundle.json","state":"https://pith.science/pith/KAUEVVMRZQ3NBN37CTBCCPQXLS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KAUEVVMRZQ3NBN37CTBCCPQXLS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:KAUEVVMRZQ3NBN37CTBCCPQXLS","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":"aad717d281192e4ee3e0e22cb0d2b10d0121f2a59cc1803eda077ab99d627472","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-12T15:34:21Z","title_canon_sha256":"2f8f5d7ec90b2f0b644c470cf24a34d90c9a13b57cc331b9935b467bf0384871"},"schema_version":"1.0","source":{"id":"1707.03764","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.03764","created_at":"2026-05-18T00:40:24Z"},{"alias_kind":"arxiv_version","alias_value":"1707.03764v1","created_at":"2026-05-18T00:40:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.03764","created_at":"2026-05-18T00:40:24Z"},{"alias_kind":"pith_short_12","alias_value":"KAUEVVMRZQ3N","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_16","alias_value":"KAUEVVMRZQ3NBN37","created_at":"2026-05-18T12:31:24Z"},{"alias_kind":"pith_short_8","alias_value":"KAUEVVMR","created_at":"2026-05-18T12:31:24Z"}],"graph_snapshots":[{"event_id":"sha256:3c6ede3c9f07ce52bc8fadb3f75bf2d492f8af3e874a6e482732c3f51120022e","target":"graph","created_at":"2026-05-18T00:40:24Z","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 describe our participation in the PAN 2017 shared task on Author Profiling, identifying authors' gender and language variety for English, Spanish, Arabic and Portuguese. We describe both the final, submitted system, and a series of negative results. Our aim was to create a single model for both gender and language, and for all language varieties. Our best-performing system (on cross-validated results) is a linear support vector machine (SVM) with word unigrams and character 3- to 5-grams as features. A set of additional features, including POS tags, additional datasets, geographic entities,","authors_text":"Angelo Basile, Gareth Dwyer, Hessel Haagsma, Josine Rawee, Malvina Nissim, Maria Medvedeva","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-12T15:34:21Z","title":"N-GrAM: New Groningen Author-profiling Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.03764","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:ef7e0b00d2e3e526a4ec6d3e6e3752940586e3df6360aa6fdba065e53fd89955","target":"record","created_at":"2026-05-18T00:40:24Z","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":"aad717d281192e4ee3e0e22cb0d2b10d0121f2a59cc1803eda077ab99d627472","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-12T15:34:21Z","title_canon_sha256":"2f8f5d7ec90b2f0b644c470cf24a34d90c9a13b57cc331b9935b467bf0384871"},"schema_version":"1.0","source":{"id":"1707.03764","kind":"arxiv","version":1}},"canonical_sha256":"50284ad591cc36d0b77f14c2213e175c9b512352569c8b33f3eff396b2419383","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"50284ad591cc36d0b77f14c2213e175c9b512352569c8b33f3eff396b2419383","first_computed_at":"2026-05-18T00:40:24.878485Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:24.878485Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"11K+FsO4Egvgf7ZIBabHKWnQ9TJeSiRcjnrHKvSlrbTn2zx7yY7pZWNhhFOUwRoEGyK9MfXlnSBB59/ggcm8BA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:24.879233Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.03764","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef7e0b00d2e3e526a4ec6d3e6e3752940586e3df6360aa6fdba065e53fd89955","sha256:3c6ede3c9f07ce52bc8fadb3f75bf2d492f8af3e874a6e482732c3f51120022e"],"state_sha256":"b15c6172bd48a5c784e6c4f75777cb7b68cefa6acdeba2393c9aff16ed2d4dbf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dVExkSq3HLEK4ejxyZnPMCedGw3O6NpDdZguosWT8H5AhHpyh4NceBzaLqGxoo6BQ4GLcKZMRrISNFT4CXoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T19:28:01.463039Z","bundle_sha256":"788fdf749c8e96873cfd6fa3da2826a5df9625a9f323c120439c42c8e6dcea12"}}