{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:NVZQR5MOKAY37LV7VQ4Z7YWZCV","short_pith_number":"pith:NVZQR5MO","canonical_record":{"source":{"id":"1906.04129","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-10T17:08:29Z","cross_cats_sorted":[],"title_canon_sha256":"d26ce9e72b7631bef49e3d770664276d741946b9e131d6e7449ab9fc6e374413","abstract_canon_sha256":"4466e4daf4832e623edf0792ce5bb2d8dc8d1cea7d87ac77491f26bea7dc1e7d"},"schema_version":"1.0"},"canonical_sha256":"6d7308f58e5031bfaebfac399fe2d9155e20d506c449c22beffb1afe1c398e74","source":{"kind":"arxiv","id":"1906.04129","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04129","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04129v1","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04129","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"pith_short_12","alias_value":"NVZQR5MOKAY3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NVZQR5MOKAY37LV7","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NVZQR5MO","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:NVZQR5MOKAY37LV7VQ4Z7YWZCV","target":"record","payload":{"canonical_record":{"source":{"id":"1906.04129","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-10T17:08:29Z","cross_cats_sorted":[],"title_canon_sha256":"d26ce9e72b7631bef49e3d770664276d741946b9e131d6e7449ab9fc6e374413","abstract_canon_sha256":"4466e4daf4832e623edf0792ce5bb2d8dc8d1cea7d87ac77491f26bea7dc1e7d"},"schema_version":"1.0"},"canonical_sha256":"6d7308f58e5031bfaebfac399fe2d9155e20d506c449c22beffb1afe1c398e74","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:43:43.816960Z","signature_b64":"RcFgXk/gmsrkB0OjMqskk2L57SFgtihYeDotjY3itU1UfzUi38IYbTK6GDFKLEkuxJ2kLUPZhrG0OhsZzhNPBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d7308f58e5031bfaebfac399fe2d9155e20d506c449c22beffb1afe1c398e74","last_reissued_at":"2026-05-17T23:43:43.816398Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:43:43.816398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1906.04129","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":"2026-05-17T23:43:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AYK3VZgtKbrXBzFprkg9Ypko5oHvj3RTPHr5Ynn0ghzmkbnT+YKzisvJC262QJaVXFw6OwleIHj7tbMy4ns5Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:47:39.334384Z"},"content_sha256":"d8b9ddc2628445a021c8913e282b69c3943a5113d740c30f0292a045c4d7180f","schema_version":"1.0","event_id":"sha256:d8b9ddc2628445a021c8913e282b69c3943a5113d740c30f0292a045c4d7180f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:NVZQR5MOKAY37LV7VQ4Z7YWZCV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"A. Pastor L\\'opez-Monroy, Fabio A. Gonz\\'alez, Gustavo Aguilar, Thamar Solorio","submitted_at":"2019-06-10T17:08:29Z","abstract_excerpt":"Recognizing named entities in a document is a key task in many NLP applications. Although current state-of-the-art approaches to this task reach a high performance on clean text (e.g. newswire genres), those algorithms dramatically degrade when they are moved to noisy environments such as social media domains. We present two systems that address the challenges of processing social media data using character-level phonetics and phonology, word embeddings, and Part-of-Speech tags as features. The first model is a multitask end-to-end Bidirectional Long Short-Term Memory (BLSTM)-Conditional Rando"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04129","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":"2026-05-17T23:43:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"o3wRWR/tA5WHQiTyre4rWoB1dxPW5Cssgx3OSS7rTXAQlxe3gXw3yp8KO1h9LzZc58jBsdKRe91ZR0hbgZZFAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T10:47:39.334772Z"},"content_sha256":"22853eb0eb334812e2682720683aa19cbf936e14f8ed119e7b03e1b596a6a66b","schema_version":"1.0","event_id":"sha256:22853eb0eb334812e2682720683aa19cbf936e14f8ed119e7b03e1b596a6a66b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NVZQR5MOKAY37LV7VQ4Z7YWZCV/bundle.json","state_url":"https://pith.science/pith/NVZQR5MOKAY37LV7VQ4Z7YWZCV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NVZQR5MOKAY37LV7VQ4Z7YWZCV/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":"2026-06-05T10:47:39Z","links":{"resolver":"https://pith.science/pith/NVZQR5MOKAY37LV7VQ4Z7YWZCV","bundle":"https://pith.science/pith/NVZQR5MOKAY37LV7VQ4Z7YWZCV/bundle.json","state":"https://pith.science/pith/NVZQR5MOKAY37LV7VQ4Z7YWZCV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NVZQR5MOKAY37LV7VQ4Z7YWZCV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:NVZQR5MOKAY37LV7VQ4Z7YWZCV","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":"4466e4daf4832e623edf0792ce5bb2d8dc8d1cea7d87ac77491f26bea7dc1e7d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-10T17:08:29Z","title_canon_sha256":"d26ce9e72b7631bef49e3d770664276d741946b9e131d6e7449ab9fc6e374413"},"schema_version":"1.0","source":{"id":"1906.04129","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1906.04129","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"arxiv_version","alias_value":"1906.04129v1","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.04129","created_at":"2026-05-17T23:43:43Z"},{"alias_kind":"pith_short_12","alias_value":"NVZQR5MOKAY3","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"NVZQR5MOKAY37LV7","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"NVZQR5MO","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:22853eb0eb334812e2682720683aa19cbf936e14f8ed119e7b03e1b596a6a66b","target":"graph","created_at":"2026-05-17T23:43:43Z","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":"Recognizing named entities in a document is a key task in many NLP applications. Although current state-of-the-art approaches to this task reach a high performance on clean text (e.g. newswire genres), those algorithms dramatically degrade when they are moved to noisy environments such as social media domains. We present two systems that address the challenges of processing social media data using character-level phonetics and phonology, word embeddings, and Part-of-Speech tags as features. The first model is a multitask end-to-end Bidirectional Long Short-Term Memory (BLSTM)-Conditional Rando","authors_text":"A. Pastor L\\'opez-Monroy, Fabio A. Gonz\\'alez, Gustavo Aguilar, Thamar Solorio","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-10T17:08:29Z","title":"Modeling Noisiness to Recognize Named Entities using Multitask Neural Networks on Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.04129","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:d8b9ddc2628445a021c8913e282b69c3943a5113d740c30f0292a045c4d7180f","target":"record","created_at":"2026-05-17T23:43:43Z","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":"4466e4daf4832e623edf0792ce5bb2d8dc8d1cea7d87ac77491f26bea7dc1e7d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-10T17:08:29Z","title_canon_sha256":"d26ce9e72b7631bef49e3d770664276d741946b9e131d6e7449ab9fc6e374413"},"schema_version":"1.0","source":{"id":"1906.04129","kind":"arxiv","version":1}},"canonical_sha256":"6d7308f58e5031bfaebfac399fe2d9155e20d506c449c22beffb1afe1c398e74","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d7308f58e5031bfaebfac399fe2d9155e20d506c449c22beffb1afe1c398e74","first_computed_at":"2026-05-17T23:43:43.816398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:43:43.816398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RcFgXk/gmsrkB0OjMqskk2L57SFgtihYeDotjY3itU1UfzUi38IYbTK6GDFKLEkuxJ2kLUPZhrG0OhsZzhNPBw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:43:43.816960Z","signed_message":"canonical_sha256_bytes"},"source_id":"1906.04129","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d8b9ddc2628445a021c8913e282b69c3943a5113d740c30f0292a045c4d7180f","sha256:22853eb0eb334812e2682720683aa19cbf936e14f8ed119e7b03e1b596a6a66b"],"state_sha256":"75d3d61d6f7ed11ad943a3a3135423abd09bd986ba1d4bfa4159c36699977d87"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BMx6Q1MOcDYFqCAou2000ZjqbdEcjrsoEGGQevOAhDrQtLgxXSzQKwAR1ShaT6lv3LlMeSG0gWuEG73lurN5CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T10:47:39.336743Z","bundle_sha256":"aad2be2d8648e3374222a47fdac48294b013dd6c55a22161757ab18c2fa3be20"}}