{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2015:TOGEHEHNC2O4KJDXRIUPZFJBLF","short_pith_number":"pith:TOGEHEHN","canonical_record":{"source":{"id":"1508.02285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-10T15:29:22Z","cross_cats_sorted":[],"title_canon_sha256":"6b1a4de06254998c900728620ef3eb96e69f660fb5e33403722122ef6c023907","abstract_canon_sha256":"27aef3c5ad704d3ae09e93983686664a2e3a24169d9e4be8962f9fd659a0c1ca"},"schema_version":"1.0"},"canonical_sha256":"9b8c4390ed169dc524778a28fc9521596761980ec4e2d9b224c92f67c98be988","source":{"kind":"arxiv","id":"1508.02285","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.02285","created_at":"2026-05-18T01:35:33Z"},{"alias_kind":"arxiv_version","alias_value":"1508.02285v1","created_at":"2026-05-18T01:35:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.02285","created_at":"2026-05-18T01:35:33Z"},{"alias_kind":"pith_short_12","alias_value":"TOGEHEHNC2O4","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"TOGEHEHNC2O4KJDX","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"TOGEHEHN","created_at":"2026-05-18T12:29:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2015:TOGEHEHNC2O4KJDXRIUPZFJBLF","target":"record","payload":{"canonical_record":{"source":{"id":"1508.02285","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-10T15:29:22Z","cross_cats_sorted":[],"title_canon_sha256":"6b1a4de06254998c900728620ef3eb96e69f660fb5e33403722122ef6c023907","abstract_canon_sha256":"27aef3c5ad704d3ae09e93983686664a2e3a24169d9e4be8962f9fd659a0c1ca"},"schema_version":"1.0"},"canonical_sha256":"9b8c4390ed169dc524778a28fc9521596761980ec4e2d9b224c92f67c98be988","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:35:33.654849Z","signature_b64":"uYSHGlNEjvJgxvywLKYwKMZSqvnCQhKiTD+f7I6gLMo5gJTnfzjni/CCP4ducnUzUdroe/kfPlHq/u3eKLe8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b8c4390ed169dc524778a28fc9521596761980ec4e2d9b224c92f67c98be988","last_reissued_at":"2026-05-18T01:35:33.654184Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:35:33.654184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1508.02285","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":"2026-05-18T01:35:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HKLWg6wHj+EPPjUX4IBuqlIlWZQkHl4TBtWeVi61eAfIln2xv9e4Om1y4VxJ2Noo0meM2PBTNow7agK6zbrqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:32:41.905041Z"},"content_sha256":"96c9789b9041ee6421d0bedaa485353056671c1d1880e524abe71ebb26f9c7af","schema_version":"1.0","event_id":"sha256:96c9789b9041ee6421d0bedaa485353056671c1d1880e524abe71ebb26f9c7af"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2015:TOGEHEHNC2O4KJDXRIUPZFJBLF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adapting Phrase-based Machine Translation to Normalise Medical Terms in Social Media Messages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Nigel Collier, Nut Limsopatham","submitted_at":"2015-08-10T15:29:22Z","abstract_excerpt":"Previous studies have shown that health reports in social media, such as DailyStrength and Twitter, have potential for monitoring health conditions (e.g. adverse drug reactions, infectious diseases) in particular communities. However, in order for a machine to understand and make inferences on these health conditions, the ability to recognise when laymen's terms refer to a particular medical concept (i.e.\\ text normalisation) is required. To achieve this, we propose to adapt an existing phrase-based machine translation (MT) technique and a vector representation of words to map between a social"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.02285","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":"2026-05-18T01:35:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J1d0XkIrs/uZR2d28zU/RJTGB/q56R9yiA/Y6tYRI8QZrlqAYQlX3r6zTkg6Tb8mhmLkcEzF4KI5kQan/h0SBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T12:32:41.905391Z"},"content_sha256":"715bacb2be735c315dd6d5f24de65d35455d3490c82b358b868429921b85cd34","schema_version":"1.0","event_id":"sha256:715bacb2be735c315dd6d5f24de65d35455d3490c82b358b868429921b85cd34"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TOGEHEHNC2O4KJDXRIUPZFJBLF/bundle.json","state_url":"https://pith.science/pith/TOGEHEHNC2O4KJDXRIUPZFJBLF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TOGEHEHNC2O4KJDXRIUPZFJBLF/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":"2026-06-09T12:32:41Z","links":{"resolver":"https://pith.science/pith/TOGEHEHNC2O4KJDXRIUPZFJBLF","bundle":"https://pith.science/pith/TOGEHEHNC2O4KJDXRIUPZFJBLF/bundle.json","state":"https://pith.science/pith/TOGEHEHNC2O4KJDXRIUPZFJBLF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TOGEHEHNC2O4KJDXRIUPZFJBLF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2015:TOGEHEHNC2O4KJDXRIUPZFJBLF","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":"27aef3c5ad704d3ae09e93983686664a2e3a24169d9e4be8962f9fd659a0c1ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-10T15:29:22Z","title_canon_sha256":"6b1a4de06254998c900728620ef3eb96e69f660fb5e33403722122ef6c023907"},"schema_version":"1.0","source":{"id":"1508.02285","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1508.02285","created_at":"2026-05-18T01:35:33Z"},{"alias_kind":"arxiv_version","alias_value":"1508.02285v1","created_at":"2026-05-18T01:35:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1508.02285","created_at":"2026-05-18T01:35:33Z"},{"alias_kind":"pith_short_12","alias_value":"TOGEHEHNC2O4","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_16","alias_value":"TOGEHEHNC2O4KJDX","created_at":"2026-05-18T12:29:42Z"},{"alias_kind":"pith_short_8","alias_value":"TOGEHEHN","created_at":"2026-05-18T12:29:42Z"}],"graph_snapshots":[{"event_id":"sha256:715bacb2be735c315dd6d5f24de65d35455d3490c82b358b868429921b85cd34","target":"graph","created_at":"2026-05-18T01:35:33Z","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":"Previous studies have shown that health reports in social media, such as DailyStrength and Twitter, have potential for monitoring health conditions (e.g. adverse drug reactions, infectious diseases) in particular communities. However, in order for a machine to understand and make inferences on these health conditions, the ability to recognise when laymen's terms refer to a particular medical concept (i.e.\\ text normalisation) is required. To achieve this, we propose to adapt an existing phrase-based machine translation (MT) technique and a vector representation of words to map between a social","authors_text":"Nigel Collier, Nut Limsopatham","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-10T15:29:22Z","title":"Adapting Phrase-based Machine Translation to Normalise Medical Terms in Social Media Messages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1508.02285","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":"sha256:96c9789b9041ee6421d0bedaa485353056671c1d1880e524abe71ebb26f9c7af","target":"record","created_at":"2026-05-18T01:35:33Z","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":"27aef3c5ad704d3ae09e93983686664a2e3a24169d9e4be8962f9fd659a0c1ca","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2015-08-10T15:29:22Z","title_canon_sha256":"6b1a4de06254998c900728620ef3eb96e69f660fb5e33403722122ef6c023907"},"schema_version":"1.0","source":{"id":"1508.02285","kind":"arxiv","version":1}},"canonical_sha256":"9b8c4390ed169dc524778a28fc9521596761980ec4e2d9b224c92f67c98be988","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9b8c4390ed169dc524778a28fc9521596761980ec4e2d9b224c92f67c98be988","first_computed_at":"2026-05-18T01:35:33.654184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:35:33.654184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uYSHGlNEjvJgxvywLKYwKMZSqvnCQhKiTD+f7I6gLMo5gJTnfzjni/CCP4ducnUzUdroe/kfPlHq/u3eKLe8Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T01:35:33.654849Z","signed_message":"canonical_sha256_bytes"},"source_id":"1508.02285","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:96c9789b9041ee6421d0bedaa485353056671c1d1880e524abe71ebb26f9c7af","sha256:715bacb2be735c315dd6d5f24de65d35455d3490c82b358b868429921b85cd34"],"state_sha256":"16ad27618427270534ee7bb54d9218b8e8bff379630873c27b950b41558fab0c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MUoTKxDfbDpJzLWcwLUi0FlvhFlYRJ30FT6fHcMKExdACpXNvUmWDkZFzFchHeBB8r0At2RJKHSf+eAGWasgAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T12:32:41.907159Z","bundle_sha256":"b026a45d02fb770cbeb4db27ecc1e83e431e548c497a6a8fc5c5be279e9f8d09"}}