{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2014:HHFJRBXFPR6G6RFPINN64JPR2S","short_pith_number":"pith:HHFJRBXF","canonical_record":{"source":{"id":"1409.4614","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-09-16T12:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"d6f429ff605b1f72bd5a6f4b9be2edddb84d5aeac0cb2639b000c231adc80728","abstract_canon_sha256":"76ce06879d1a14764535610b56fccf6512146dfd6835b97547be4f5fe24732b7"},"schema_version":"1.0"},"canonical_sha256":"39ca9886e57c7c6f44af435bee25f1d483fcd3d3c3363977a74878bda4d8ec80","source":{"kind":"arxiv","id":"1409.4614","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.4614","created_at":"2026-05-18T01:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"1409.4614v4","created_at":"2026-05-18T01:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.4614","created_at":"2026-05-18T01:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"HHFJRBXFPR6G","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"HHFJRBXFPR6G6RFP","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"HHFJRBXF","created_at":"2026-05-18T12:28:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2014:HHFJRBXFPR6G6RFPINN64JPR2S","target":"record","payload":{"canonical_record":{"source":{"id":"1409.4614","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-09-16T12:59:07Z","cross_cats_sorted":[],"title_canon_sha256":"d6f429ff605b1f72bd5a6f4b9be2edddb84d5aeac0cb2639b000c231adc80728","abstract_canon_sha256":"76ce06879d1a14764535610b56fccf6512146dfd6835b97547be4f5fe24732b7"},"schema_version":"1.0"},"canonical_sha256":"39ca9886e57c7c6f44af435bee25f1d483fcd3d3c3363977a74878bda4d8ec80","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:32:37.734503Z","signature_b64":"Gls7usyhKyadFa7uI1zLj9Y4aksDLzBSVNLA1ynFFNeZZQ52FmHBQkJlLjHdm5INqqjCCcqJ2+ZczV9hzoxDDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39ca9886e57c7c6f44af435bee25f1d483fcd3d3c3363977a74878bda4d8ec80","last_reissued_at":"2026-05-18T01:32:37.733897Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:32:37.733897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1409.4614","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T01:32:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ADIf3N2YEslcBQggrY/WAH2XRuAfaYlfPz3hFbs2MaaoJb8Yos3DVkymtWl3AaFvI4b5zq4YTXjG9jUkIFv4Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:15:14.158211Z"},"content_sha256":"71597a7087919006f22d22183af6c0e3c54096d5478494cfcee303625251af17","schema_version":"1.0","event_id":"sha256:71597a7087919006f22d22183af6c0e3c54096d5478494cfcee303625251af17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2014:HHFJRBXFPR6G6RFPINN64JPR2S","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Lexical Normalisation of Twitter Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bilal Ahmed","submitted_at":"2014-09-16T12:59:07Z","abstract_excerpt":"Twitter with over 500 million users globally, generates over 100,000 tweets per minute . The 140 character limit per tweet, perhaps unintentionally, encourages users to use shorthand notations and to strip spellings to their bare minimum \"syllables\" or elisions e.g. \"srsly\". The analysis of twitter messages which typically contain misspellings, elisions, and grammatical errors, poses a challenge to established Natural Language Processing (NLP) tools which are generally designed with the assumption that the data conforms to the basic grammatical structure commonly used in English language. In o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.4614","kind":"arxiv","version":4},"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":"2026-05-18T01:32:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i/hiDRI5BUMawdUYf6sZ4jN+tAGmiW0YqOz4mwY5qLO6fGURmCVBRej3YHDwiiQevWFwiNEOqJt6lBwG3pLzBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-30T07:15:14.158842Z"},"content_sha256":"45ed188b009d148fae46a16af0cd536b89674632dc80ef20ea5ac1cd7dd875b0","schema_version":"1.0","event_id":"sha256:45ed188b009d148fae46a16af0cd536b89674632dc80ef20ea5ac1cd7dd875b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HHFJRBXFPR6G6RFPINN64JPR2S/bundle.json","state_url":"https://pith.science/pith/HHFJRBXFPR6G6RFPINN64JPR2S/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HHFJRBXFPR6G6RFPINN64JPR2S/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":"2026-05-30T07:15:14Z","links":{"resolver":"https://pith.science/pith/HHFJRBXFPR6G6RFPINN64JPR2S","bundle":"https://pith.science/pith/HHFJRBXFPR6G6RFPINN64JPR2S/bundle.json","state":"https://pith.science/pith/HHFJRBXFPR6G6RFPINN64JPR2S/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HHFJRBXFPR6G6RFPINN64JPR2S/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2014:HHFJRBXFPR6G6RFPINN64JPR2S","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":"76ce06879d1a14764535610b56fccf6512146dfd6835b97547be4f5fe24732b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-09-16T12:59:07Z","title_canon_sha256":"d6f429ff605b1f72bd5a6f4b9be2edddb84d5aeac0cb2639b000c231adc80728"},"schema_version":"1.0","source":{"id":"1409.4614","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1409.4614","created_at":"2026-05-18T01:32:37Z"},{"alias_kind":"arxiv_version","alias_value":"1409.4614v4","created_at":"2026-05-18T01:32:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1409.4614","created_at":"2026-05-18T01:32:37Z"},{"alias_kind":"pith_short_12","alias_value":"HHFJRBXFPR6G","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_16","alias_value":"HHFJRBXFPR6G6RFP","created_at":"2026-05-18T12:28:30Z"},{"alias_kind":"pith_short_8","alias_value":"HHFJRBXF","created_at":"2026-05-18T12:28:30Z"}],"graph_snapshots":[{"event_id":"sha256:45ed188b009d148fae46a16af0cd536b89674632dc80ef20ea5ac1cd7dd875b0","target":"graph","created_at":"2026-05-18T01:32:37Z","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":"Twitter with over 500 million users globally, generates over 100,000 tweets per minute . The 140 character limit per tweet, perhaps unintentionally, encourages users to use shorthand notations and to strip spellings to their bare minimum \"syllables\" or elisions e.g. \"srsly\". The analysis of twitter messages which typically contain misspellings, elisions, and grammatical errors, poses a challenge to established Natural Language Processing (NLP) tools which are generally designed with the assumption that the data conforms to the basic grammatical structure commonly used in English language. In o","authors_text":"Bilal Ahmed","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-09-16T12:59:07Z","title":"Lexical Normalisation of Twitter Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1409.4614","kind":"arxiv","version":4},"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":"sha256:71597a7087919006f22d22183af6c0e3c54096d5478494cfcee303625251af17","target":"record","created_at":"2026-05-18T01:32:37Z","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":"76ce06879d1a14764535610b56fccf6512146dfd6835b97547be4f5fe24732b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2014-09-16T12:59:07Z","title_canon_sha256":"d6f429ff605b1f72bd5a6f4b9be2edddb84d5aeac0cb2639b000c231adc80728"},"schema_version":"1.0","source":{"id":"1409.4614","kind":"arxiv","version":4}},"canonical_sha256":"39ca9886e57c7c6f44af435bee25f1d483fcd3d3c3363977a74878bda4d8ec80","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"39ca9886e57c7c6f44af435bee25f1d483fcd3d3c3363977a74878bda4d8ec80","first_computed_at":"2026-05-18T01:32:37.733897Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:32:37.733897Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gls7usyhKyadFa7uI1zLj9Y4aksDLzBSVNLA1ynFFNeZZQ52FmHBQkJlLjHdm5INqqjCCcqJ2+ZczV9hzoxDDw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:32:37.734503Z","signed_message":"canonical_sha256_bytes"},"source_id":"1409.4614","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:71597a7087919006f22d22183af6c0e3c54096d5478494cfcee303625251af17","sha256:45ed188b009d148fae46a16af0cd536b89674632dc80ef20ea5ac1cd7dd875b0"],"state_sha256":"2d3f0f02032f5cc735234836dd7bbce10a8540fd23e2403b653a45be00274f2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Skj9G+Mxxxq9DLkLcmevEjU/ET99eZQARkWjHml7830h67Tv3RtXjcJUlY2wdjNUciu6rQSh7RNFRi5m79ELDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-30T07:15:14.161628Z","bundle_sha256":"66a826809721d48b861107163ed008fd676027397ccdd1968bbc7e088ece897c"}}