{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:X2IQTYQU5GFU73FLMSCPSKAMHO","short_pith_number":"pith:X2IQTYQU","canonical_record":{"source":{"id":"1904.06100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T08:45:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"381a35ecffde9b4cb27491c323fd3de18ede15feaea710dab4f100796fe15e89","abstract_canon_sha256":"56e9c2eb77f6aaaa4da819c2d52c6ceac5588b92585af67de535495ca52f975d"},"schema_version":"1.0"},"canonical_sha256":"be9109e214e98b4fecab6484f9280c3babdf83c2bbb59d62e157d52dc15ea385","source":{"kind":"arxiv","id":"1904.06100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06100","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06100v1","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06100","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"pith_short_12","alias_value":"X2IQTYQU5GFU","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X2IQTYQU5GFU73FL","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X2IQTYQU","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:X2IQTYQU5GFU73FLMSCPSKAMHO","target":"record","payload":{"canonical_record":{"source":{"id":"1904.06100","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T08:45:43Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"381a35ecffde9b4cb27491c323fd3de18ede15feaea710dab4f100796fe15e89","abstract_canon_sha256":"56e9c2eb77f6aaaa4da819c2d52c6ceac5588b92585af67de535495ca52f975d"},"schema_version":"1.0"},"canonical_sha256":"be9109e214e98b4fecab6484f9280c3babdf83c2bbb59d62e157d52dc15ea385","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:48:44.142529Z","signature_b64":"lpGp1TX9uT0zGxtlj3S0Ja0beFOLX65bWBGVUlpi12OenP8XCJinUHBP9JaUoRmHt2z4wyvE5Uu+SrW77ao+AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be9109e214e98b4fecab6484f9280c3babdf83c2bbb59d62e157d52dc15ea385","last_reissued_at":"2026-05-17T23:48:44.141824Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:48:44.141824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.06100","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":"2026-05-17T23:48:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4P5QJrZom2IP4xcYQK5BIBsNWVKCyXiYWqxa/vD7Ja+KyVATEGNL7+1fAg7+CUf1qGJ05HA2DpDyGSuVrz9ZBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:08:14.694456Z"},"content_sha256":"90d98ed97028bd3d465e2d70a70d0ca29cb14cff5c6c20aa6d2866bb1282db49","schema_version":"1.0","event_id":"sha256:90d98ed97028bd3d465e2d70a70d0ca29cb14cff5c6c20aa6d2866bb1282db49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:X2IQTYQU5GFU73FLMSCPSKAMHO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting Sequence to Sequence models for Text Normalization in Social Media","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"ChengXiang Zhai, Ismini Lourentzou, Kabir Manghnani","submitted_at":"2019-04-12T08:45:43Z","abstract_excerpt":"Social media offer an abundant source of valuable raw data, however informal writing can quickly become a bottleneck for many natural language processing (NLP) tasks. Off-the-shelf tools are usually trained on formal text and cannot explicitly handle noise found in short online posts. Moreover, the variety of frequently occurring linguistic variations presents several challenges, even for humans who might not be able to comprehend the meaning of such posts, especially when they contain slang and abbreviations. Text Normalization aims to transform online user-generated text to a canonical form."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06100","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":"2026-05-17T23:48:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZWwhay/42LVN+1APZzShdPy30mcamCaMo6fwH/03I62bso7gw/4lpN0T7xk8QnMCUdfTv4uocmDmu6SK40rECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:08:14.695118Z"},"content_sha256":"e043c5259434823476af7f78b7a4edd31bdb6359ffc4d1fb4ce05f260c0d8b32","schema_version":"1.0","event_id":"sha256:e043c5259434823476af7f78b7a4edd31bdb6359ffc4d1fb4ce05f260c0d8b32"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X2IQTYQU5GFU73FLMSCPSKAMHO/bundle.json","state_url":"https://pith.science/pith/X2IQTYQU5GFU73FLMSCPSKAMHO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X2IQTYQU5GFU73FLMSCPSKAMHO/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":"2026-06-09T09:08:14Z","links":{"resolver":"https://pith.science/pith/X2IQTYQU5GFU73FLMSCPSKAMHO","bundle":"https://pith.science/pith/X2IQTYQU5GFU73FLMSCPSKAMHO/bundle.json","state":"https://pith.science/pith/X2IQTYQU5GFU73FLMSCPSKAMHO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X2IQTYQU5GFU73FLMSCPSKAMHO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:X2IQTYQU5GFU73FLMSCPSKAMHO","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":"56e9c2eb77f6aaaa4da819c2d52c6ceac5588b92585af67de535495ca52f975d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T08:45:43Z","title_canon_sha256":"381a35ecffde9b4cb27491c323fd3de18ede15feaea710dab4f100796fe15e89"},"schema_version":"1.0","source":{"id":"1904.06100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.06100","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"arxiv_version","alias_value":"1904.06100v1","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.06100","created_at":"2026-05-17T23:48:44Z"},{"alias_kind":"pith_short_12","alias_value":"X2IQTYQU5GFU","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"X2IQTYQU5GFU73FL","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"X2IQTYQU","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:e043c5259434823476af7f78b7a4edd31bdb6359ffc4d1fb4ce05f260c0d8b32","target":"graph","created_at":"2026-05-17T23:48:44Z","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":"Social media offer an abundant source of valuable raw data, however informal writing can quickly become a bottleneck for many natural language processing (NLP) tasks. Off-the-shelf tools are usually trained on formal text and cannot explicitly handle noise found in short online posts. Moreover, the variety of frequently occurring linguistic variations presents several challenges, even for humans who might not be able to comprehend the meaning of such posts, especially when they contain slang and abbreviations. Text Normalization aims to transform online user-generated text to a canonical form.","authors_text":"ChengXiang Zhai, Ismini Lourentzou, Kabir Manghnani","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T08:45:43Z","title":"Adapting Sequence to Sequence models for Text Normalization in Social Media"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.06100","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":"sha256:90d98ed97028bd3d465e2d70a70d0ca29cb14cff5c6c20aa6d2866bb1282db49","target":"record","created_at":"2026-05-17T23:48:44Z","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":"56e9c2eb77f6aaaa4da819c2d52c6ceac5588b92585af67de535495ca52f975d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-04-12T08:45:43Z","title_canon_sha256":"381a35ecffde9b4cb27491c323fd3de18ede15feaea710dab4f100796fe15e89"},"schema_version":"1.0","source":{"id":"1904.06100","kind":"arxiv","version":1}},"canonical_sha256":"be9109e214e98b4fecab6484f9280c3babdf83c2bbb59d62e157d52dc15ea385","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be9109e214e98b4fecab6484f9280c3babdf83c2bbb59d62e157d52dc15ea385","first_computed_at":"2026-05-17T23:48:44.141824Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:48:44.141824Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lpGp1TX9uT0zGxtlj3S0Ja0beFOLX65bWBGVUlpi12OenP8XCJinUHBP9JaUoRmHt2z4wyvE5Uu+SrW77ao+AQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:48:44.142529Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.06100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90d98ed97028bd3d465e2d70a70d0ca29cb14cff5c6c20aa6d2866bb1282db49","sha256:e043c5259434823476af7f78b7a4edd31bdb6359ffc4d1fb4ce05f260c0d8b32"],"state_sha256":"8fa8c2860b05e5079c89bb2480ddb95789c44f3034bf7e4c9682716f9089c76d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J931sr89NLj8Qzrd/HqdATGuPnRQzRAtelVEWrrGGd1g59zg2HZ40avE+vTx7fOdIclymBcrYXuUH0aFg06UDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T09:08:14.698868Z","bundle_sha256":"30542b1536b2734b64af79de1d20cff9ee1f3fbd1c1c2458ab1b0359333ee29c"}}