{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:VEWOFLBS2RMQJ5MXTNEZSZXMQI","short_pith_number":"pith:VEWOFLBS","canonical_record":{"source":{"id":"1710.04989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-13T16:24:23Z","cross_cats_sorted":[],"title_canon_sha256":"5fa5cd4989c237417eab723313a8ad3fd90286169ff28432321a69006df00d12","abstract_canon_sha256":"8361d6a8e0da645dfbab815aa06b1613496491f09acc61245fd2246fff44bcc7"},"schema_version":"1.0"},"canonical_sha256":"a92ce2ac32d45904f5979b499966ec8225699794041877384d21d31fa28e9da0","source":{"kind":"arxiv","id":"1710.04989","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04989","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04989v1","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04989","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"pith_short_12","alias_value":"VEWOFLBS2RMQ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VEWOFLBS2RMQJ5MX","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VEWOFLBS","created_at":"2026-05-18T12:31:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:VEWOFLBS2RMQJ5MXTNEZSZXMQI","target":"record","payload":{"canonical_record":{"source":{"id":"1710.04989","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-13T16:24:23Z","cross_cats_sorted":[],"title_canon_sha256":"5fa5cd4989c237417eab723313a8ad3fd90286169ff28432321a69006df00d12","abstract_canon_sha256":"8361d6a8e0da645dfbab815aa06b1613496491f09acc61245fd2246fff44bcc7"},"schema_version":"1.0"},"canonical_sha256":"a92ce2ac32d45904f5979b499966ec8225699794041877384d21d31fa28e9da0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:32:56.088507Z","signature_b64":"jOw3VRNCHeEwnO7Y7bod1/u+s1hlXfZt/kg5g7LoOlkzv9z3OtvwVGNNTMx86C0h4H29soRCKDNhN3lojLq5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a92ce2ac32d45904f5979b499966ec8225699794041877384d21d31fa28e9da0","last_reissued_at":"2026-05-18T00:32:56.087842Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:32:56.087842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1710.04989","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":"2026-05-18T00:32:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BDeL4lxX/UzGvxN+OSE4s4aeKN0435PWVgH3W8YayzyXEsJblpCwcoUf6K6CaatK/7i7Noeeqzwo04VVJu8yDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T14:22:41.718282Z"},"content_sha256":"c6f7882f44cc457f0cd80d7ca36ae208972b84dc83aae56fab66bf1b91991693","schema_version":"1.0","event_id":"sha256:c6f7882f44cc457f0cd80d7ca36ae208972b84dc83aae56fab66bf1b91991693"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:VEWOFLBS2RMQJ5MXTNEZSZXMQI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Complex Word Identification: Challenges in Data Annotation and System Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Gustavo Paetzold, Lucia Specia, Marcos Zampieri, Shervin Malmasi","submitted_at":"2017-10-13T16:24:23Z","abstract_excerpt":"This paper revisits the problem of complex word identification (CWI) following up the SemEval CWI shared task. We use ensemble classifiers to investigate how well computational methods can discriminate between complex and non-complex words. Furthermore, we analyze the classification performance to understand what makes lexical complexity challenging. Our findings show that most systems performed poorly on the SemEval CWI dataset, and one of the reasons for that is the way in which human annotation was performed."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04989","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":"2026-05-18T00:32:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ju1D62UoAx8J0MT8/026DnkgBwMPTdc0jOWb3m+MSvrlIuVrKTooJonaEMTIQ1zoIii7cc829BLeAkKxdrH6CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T14:22:41.718661Z"},"content_sha256":"192a382b51ba8d2d026aa1cc85dde60a3ee32cd225997759243902653e5aed49","schema_version":"1.0","event_id":"sha256:192a382b51ba8d2d026aa1cc85dde60a3ee32cd225997759243902653e5aed49"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VEWOFLBS2RMQJ5MXTNEZSZXMQI/bundle.json","state_url":"https://pith.science/pith/VEWOFLBS2RMQJ5MXTNEZSZXMQI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VEWOFLBS2RMQJ5MXTNEZSZXMQI/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":"2026-06-02T14:22:41Z","links":{"resolver":"https://pith.science/pith/VEWOFLBS2RMQJ5MXTNEZSZXMQI","bundle":"https://pith.science/pith/VEWOFLBS2RMQJ5MXTNEZSZXMQI/bundle.json","state":"https://pith.science/pith/VEWOFLBS2RMQJ5MXTNEZSZXMQI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VEWOFLBS2RMQJ5MXTNEZSZXMQI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:VEWOFLBS2RMQJ5MXTNEZSZXMQI","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":"8361d6a8e0da645dfbab815aa06b1613496491f09acc61245fd2246fff44bcc7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-13T16:24:23Z","title_canon_sha256":"5fa5cd4989c237417eab723313a8ad3fd90286169ff28432321a69006df00d12"},"schema_version":"1.0","source":{"id":"1710.04989","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1710.04989","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"arxiv_version","alias_value":"1710.04989v1","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.04989","created_at":"2026-05-18T00:32:56Z"},{"alias_kind":"pith_short_12","alias_value":"VEWOFLBS2RMQ","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_16","alias_value":"VEWOFLBS2RMQJ5MX","created_at":"2026-05-18T12:31:49Z"},{"alias_kind":"pith_short_8","alias_value":"VEWOFLBS","created_at":"2026-05-18T12:31:49Z"}],"graph_snapshots":[{"event_id":"sha256:192a382b51ba8d2d026aa1cc85dde60a3ee32cd225997759243902653e5aed49","target":"graph","created_at":"2026-05-18T00:32:56Z","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 revisits the problem of complex word identification (CWI) following up the SemEval CWI shared task. We use ensemble classifiers to investigate how well computational methods can discriminate between complex and non-complex words. Furthermore, we analyze the classification performance to understand what makes lexical complexity challenging. Our findings show that most systems performed poorly on the SemEval CWI dataset, and one of the reasons for that is the way in which human annotation was performed.","authors_text":"Gustavo Paetzold, Lucia Specia, Marcos Zampieri, Shervin Malmasi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-13T16:24:23Z","title":"Complex Word Identification: Challenges in Data Annotation and System Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.04989","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:c6f7882f44cc457f0cd80d7ca36ae208972b84dc83aae56fab66bf1b91991693","target":"record","created_at":"2026-05-18T00:32:56Z","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":"8361d6a8e0da645dfbab815aa06b1613496491f09acc61245fd2246fff44bcc7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-10-13T16:24:23Z","title_canon_sha256":"5fa5cd4989c237417eab723313a8ad3fd90286169ff28432321a69006df00d12"},"schema_version":"1.0","source":{"id":"1710.04989","kind":"arxiv","version":1}},"canonical_sha256":"a92ce2ac32d45904f5979b499966ec8225699794041877384d21d31fa28e9da0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a92ce2ac32d45904f5979b499966ec8225699794041877384d21d31fa28e9da0","first_computed_at":"2026-05-18T00:32:56.087842Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:32:56.087842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jOw3VRNCHeEwnO7Y7bod1/u+s1hlXfZt/kg5g7LoOlkzv9z3OtvwVGNNTMx86C0h4H29soRCKDNhN3lojLq5Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T00:32:56.088507Z","signed_message":"canonical_sha256_bytes"},"source_id":"1710.04989","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c6f7882f44cc457f0cd80d7ca36ae208972b84dc83aae56fab66bf1b91991693","sha256:192a382b51ba8d2d026aa1cc85dde60a3ee32cd225997759243902653e5aed49"],"state_sha256":"efe1cbd5f46e914b1603d10d77689f22af8cc1e357dd40706878cace0e29c992"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YH7h51VjOd13Rn+NG98jnwg2SaU9+WroLTIPAIGPkGkoK+4g4837EWZKa8OxWx9gW/cSTxuk6G/3xyQYVBmzDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T14:22:41.720647Z","bundle_sha256":"bc9dafdf072e3c58600841033102216dda631698046c63eb99e0691ac4a7a9f0"}}