{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:CZGYGLRJPD5X7LQ6ELO7EVQXZU","short_pith_number":"pith:CZGYGLRJ","canonical_record":{"source":{"id":"1702.06467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-21T16:26:54Z","cross_cats_sorted":["cs.CL","cs.SI"],"title_canon_sha256":"b1f6e8a7e725c0594d85a94b6e7cdd902b51260d875b171688f1d401cbb198a4","abstract_canon_sha256":"433fee27c4319989ef64be63aab5a89bb8c24cb8b58f05b8066647f99121e8df"},"schema_version":"1.0"},"canonical_sha256":"164d832e2978fb7fae1e22ddf25617cd29a3bdb4b59240d66448bef124a9c422","source":{"kind":"arxiv","id":"1702.06467","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.06467","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"arxiv_version","alias_value":"1702.06467v1","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06467","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"pith_short_12","alias_value":"CZGYGLRJPD5X","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CZGYGLRJPD5X7LQ6","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CZGYGLRJ","created_at":"2026-05-18T12:31:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:CZGYGLRJPD5X7LQ6ELO7EVQXZU","target":"record","payload":{"canonical_record":{"source":{"id":"1702.06467","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-21T16:26:54Z","cross_cats_sorted":["cs.CL","cs.SI"],"title_canon_sha256":"b1f6e8a7e725c0594d85a94b6e7cdd902b51260d875b171688f1d401cbb198a4","abstract_canon_sha256":"433fee27c4319989ef64be63aab5a89bb8c24cb8b58f05b8066647f99121e8df"},"schema_version":"1.0"},"canonical_sha256":"164d832e2978fb7fae1e22ddf25617cd29a3bdb4b59240d66448bef124a9c422","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:50:14.058158Z","signature_b64":"FqsAjJYs4Jp1mIw97xMY0i3s3Syq7ualv07UGv4mvfKNZpjvXB+9UHMzm/eEBGbwmA9yscrUXLChhUrOmWarAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"164d832e2978fb7fae1e22ddf25617cd29a3bdb4b59240d66448bef124a9c422","last_reissued_at":"2026-05-18T00:50:14.057732Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:50:14.057732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.06467","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":"2026-05-18T00:50:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WDXTdrd/RsA38PAWLNTHgkdF6iA1VIq+MXITbXfP3YyaF6VtAg/p3tYxojjPPWvZtAroz5hI60RfuAH/1wEqAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:15:29.697479Z"},"content_sha256":"9741fc24fc95e2b1d070bd6e4adcf16020d374e3eee8ed8e6ae5adeeb8c7e691","schema_version":"1.0","event_id":"sha256:9741fc24fc95e2b1d070bd6e4adcf16020d374e3eee8ed8e6ae5adeeb8c7e691"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:CZGYGLRJPD5X7LQ6ELO7EVQXZU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient Social Network Multilingual Classification using Character, POS n-grams and Dynamic Normalization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SI"],"primary_cat":"cs.IR","authors_text":"Azucena Montes Rend\\'on, Carlos-Emiliano Gonz\\'alez-Gallardo, Gerardo Sierra, Juan-Manuel Torres-Moreno","submitted_at":"2017-02-21T16:26:54Z","abstract_excerpt":"In this paper we describe a dynamic normalization process applied to social network multilingual documents (Facebook and Twitter) to improve the performance of the Author profiling task for short texts. After the normalization process, $n$-grams of characters and n-grams of POS tags are obtained to extract all the possible stylistic information encoded in the documents (emoticons, character flooding, capital letters, references to other users, hyperlinks, hashtags, etc.). Experiments with SVM showed up to 90% of performance."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06467","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":"2026-05-18T00:50:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oy17XL7RLqUdl6rD/Zfkdww+BkMunYumezUlMd8rF/kaxgare6OGIHMMXwDdmHqqquKs3/bxm+O5bt8/J/jeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T16:15:29.698094Z"},"content_sha256":"394fed43fef1666c7cddf2b3f41d0aee70d9383b6d2fb0b307dfa7a946476901","schema_version":"1.0","event_id":"sha256:394fed43fef1666c7cddf2b3f41d0aee70d9383b6d2fb0b307dfa7a946476901"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CZGYGLRJPD5X7LQ6ELO7EVQXZU/bundle.json","state_url":"https://pith.science/pith/CZGYGLRJPD5X7LQ6ELO7EVQXZU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CZGYGLRJPD5X7LQ6ELO7EVQXZU/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":"2026-05-30T16:15:29Z","links":{"resolver":"https://pith.science/pith/CZGYGLRJPD5X7LQ6ELO7EVQXZU","bundle":"https://pith.science/pith/CZGYGLRJPD5X7LQ6ELO7EVQXZU/bundle.json","state":"https://pith.science/pith/CZGYGLRJPD5X7LQ6ELO7EVQXZU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CZGYGLRJPD5X7LQ6ELO7EVQXZU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:CZGYGLRJPD5X7LQ6ELO7EVQXZU","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":"433fee27c4319989ef64be63aab5a89bb8c24cb8b58f05b8066647f99121e8df","cross_cats_sorted":["cs.CL","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-21T16:26:54Z","title_canon_sha256":"b1f6e8a7e725c0594d85a94b6e7cdd902b51260d875b171688f1d401cbb198a4"},"schema_version":"1.0","source":{"id":"1702.06467","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.06467","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"arxiv_version","alias_value":"1702.06467v1","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.06467","created_at":"2026-05-18T00:50:14Z"},{"alias_kind":"pith_short_12","alias_value":"CZGYGLRJPD5X","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_16","alias_value":"CZGYGLRJPD5X7LQ6","created_at":"2026-05-18T12:31:10Z"},{"alias_kind":"pith_short_8","alias_value":"CZGYGLRJ","created_at":"2026-05-18T12:31:10Z"}],"graph_snapshots":[{"event_id":"sha256:394fed43fef1666c7cddf2b3f41d0aee70d9383b6d2fb0b307dfa7a946476901","target":"graph","created_at":"2026-05-18T00:50:14Z","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":"In this paper we describe a dynamic normalization process applied to social network multilingual documents (Facebook and Twitter) to improve the performance of the Author profiling task for short texts. After the normalization process, $n$-grams of characters and n-grams of POS tags are obtained to extract all the possible stylistic information encoded in the documents (emoticons, character flooding, capital letters, references to other users, hyperlinks, hashtags, etc.). Experiments with SVM showed up to 90% of performance.","authors_text":"Azucena Montes Rend\\'on, Carlos-Emiliano Gonz\\'alez-Gallardo, Gerardo Sierra, Juan-Manuel Torres-Moreno","cross_cats":["cs.CL","cs.SI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-21T16:26:54Z","title":"Efficient Social Network Multilingual Classification using Character, POS n-grams and Dynamic Normalization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.06467","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":"sha256:9741fc24fc95e2b1d070bd6e4adcf16020d374e3eee8ed8e6ae5adeeb8c7e691","target":"record","created_at":"2026-05-18T00:50:14Z","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":"433fee27c4319989ef64be63aab5a89bb8c24cb8b58f05b8066647f99121e8df","cross_cats_sorted":["cs.CL","cs.SI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2017-02-21T16:26:54Z","title_canon_sha256":"b1f6e8a7e725c0594d85a94b6e7cdd902b51260d875b171688f1d401cbb198a4"},"schema_version":"1.0","source":{"id":"1702.06467","kind":"arxiv","version":1}},"canonical_sha256":"164d832e2978fb7fae1e22ddf25617cd29a3bdb4b59240d66448bef124a9c422","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"164d832e2978fb7fae1e22ddf25617cd29a3bdb4b59240d66448bef124a9c422","first_computed_at":"2026-05-18T00:50:14.057732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:50:14.057732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FqsAjJYs4Jp1mIw97xMY0i3s3Syq7ualv07UGv4mvfKNZpjvXB+9UHMzm/eEBGbwmA9yscrUXLChhUrOmWarAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:50:14.058158Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.06467","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9741fc24fc95e2b1d070bd6e4adcf16020d374e3eee8ed8e6ae5adeeb8c7e691","sha256:394fed43fef1666c7cddf2b3f41d0aee70d9383b6d2fb0b307dfa7a946476901"],"state_sha256":"5e40b5d74f3bab8bd2e488f4e93ae141036389a093d15971e180e1b1994d23ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IZ5ycbKSgvTg6trIwLxB6Rr858AZupONjEGnJxkLQwGJfyQC7j7wSoKvd93VbxhwURuyMv+Ih+ICRbE9e9FQDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T16:15:29.701479Z","bundle_sha256":"b079a4c3dec059d87e11a587e77d46ee10393173d00e4709be20d02ef243e59e"}}