{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:CLYGXK7JQW4T7HHVNMKOCM53VV","short_pith_number":"pith:CLYGXK7J","canonical_record":{"source":{"id":"2204.12061","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T03:52:21Z","cross_cats_sorted":[],"title_canon_sha256":"e1a7fb27afea5818017c745af67f0809be66fc7895157f18c90a49e2c7771ce0","abstract_canon_sha256":"6a8b4b4d4fbfce8952c82ef9e78e8a49683a13a68a22c8e52d2167985c09126a"},"schema_version":"1.0"},"canonical_sha256":"12f06babe985b93f9cf56b14e133bbad44e5fafc92eca6ae05ac8eda245ef314","source":{"kind":"arxiv","id":"2204.12061","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12061","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12061v2","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12061","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"pith_short_12","alias_value":"CLYGXK7JQW4T","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"pith_short_16","alias_value":"CLYGXK7JQW4T7HHV","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"pith_short_8","alias_value":"CLYGXK7J","created_at":"2026-07-05T04:18:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:CLYGXK7JQW4T7HHVNMKOCM53VV","target":"record","payload":{"canonical_record":{"source":{"id":"2204.12061","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T03:52:21Z","cross_cats_sorted":[],"title_canon_sha256":"e1a7fb27afea5818017c745af67f0809be66fc7895157f18c90a49e2c7771ce0","abstract_canon_sha256":"6a8b4b4d4fbfce8952c82ef9e78e8a49683a13a68a22c8e52d2167985c09126a"},"schema_version":"1.0"},"canonical_sha256":"12f06babe985b93f9cf56b14e133bbad44e5fafc92eca6ae05ac8eda245ef314","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:52.590607Z","signature_b64":"9Kd7Ygw0jGXhLJjG64cO6HT36q4lAjYu4WrUx4NAhUprHWhJsKoj5QEuOqlwuQWh9+NLHfa/vsfoV30saZIlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12f06babe985b93f9cf56b14e133bbad44e5fafc92eca6ae05ac8eda245ef314","last_reissued_at":"2026-07-05T04:18:52.590165Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:52.590165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.12061","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:18:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wxLwJbWP7hsB781BWyjzjkOR7QjERW2FCYlORvDfH7ws1qQ+YJfCbZ1w7nXmZIvM4pcfGH3BGAs1iG8men3jBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:46:21.245721Z"},"content_sha256":"15e5f4a14c5394ceb4b4d7f43e02fe95ae8458687efa274b70304950b41b5cf8","schema_version":"1.0","event_id":"sha256:15e5f4a14c5394ceb4b4d7f43e02fe95ae8458687efa274b70304950b41b5cf8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:CLYGXK7JQW4T7HHVNMKOCM53VV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PLOD: An Abbreviation Detection Dataset for Scientific Documents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Constantin Or\\u{a}san, Diptesh Kanojia, Hadeel Saadany, Leonardo Zilio, Prashant Sharma","submitted_at":"2022-04-26T03:52:21Z","abstract_excerpt":"The detection and extraction of abbreviations from unstructured texts can help to improve the performance of Natural Language Processing tasks, such as machine translation and information retrieval. However, in terms of publicly available datasets, there is not enough data for training deep-neural-networks-based models to the point of generalising well over data. This paper presents PLOD, a large-scale dataset for abbreviation detection and extraction that contains 160k+ segments automatically annotated with abbreviations and their long forms. We performed manual validation over a set of insta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12061","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2204.12061/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T04:18:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2iDV+sSg1mM5ju3iXTFokA+pi37NGOWCtw+10qwmeOheG5Ok3Mah96IQOi3ejJHS1OFDEOYHHumCRtF78X1ODw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:46:21.246232Z"},"content_sha256":"143e3d427518685f496831ea3db344607139ec4604b22069f9af5d455393a523","schema_version":"1.0","event_id":"sha256:143e3d427518685f496831ea3db344607139ec4604b22069f9af5d455393a523"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CLYGXK7JQW4T7HHVNMKOCM53VV/bundle.json","state_url":"https://pith.science/pith/CLYGXK7JQW4T7HHVNMKOCM53VV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CLYGXK7JQW4T7HHVNMKOCM53VV/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":"2026-08-09T22:46:21Z","links":{"resolver":"https://pith.science/pith/CLYGXK7JQW4T7HHVNMKOCM53VV","bundle":"https://pith.science/pith/CLYGXK7JQW4T7HHVNMKOCM53VV/bundle.json","state":"https://pith.science/pith/CLYGXK7JQW4T7HHVNMKOCM53VV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CLYGXK7JQW4T7HHVNMKOCM53VV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:CLYGXK7JQW4T7HHVNMKOCM53VV","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":"6a8b4b4d4fbfce8952c82ef9e78e8a49683a13a68a22c8e52d2167985c09126a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T03:52:21Z","title_canon_sha256":"e1a7fb27afea5818017c745af67f0809be66fc7895157f18c90a49e2c7771ce0"},"schema_version":"1.0","source":{"id":"2204.12061","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.12061","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"arxiv_version","alias_value":"2204.12061v2","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.12061","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"pith_short_12","alias_value":"CLYGXK7JQW4T","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"pith_short_16","alias_value":"CLYGXK7JQW4T7HHV","created_at":"2026-07-05T04:18:52Z"},{"alias_kind":"pith_short_8","alias_value":"CLYGXK7J","created_at":"2026-07-05T04:18:52Z"}],"graph_snapshots":[{"event_id":"sha256:143e3d427518685f496831ea3db344607139ec4604b22069f9af5d455393a523","target":"graph","created_at":"2026-07-05T04:18:52Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2204.12061/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The detection and extraction of abbreviations from unstructured texts can help to improve the performance of Natural Language Processing tasks, such as machine translation and information retrieval. However, in terms of publicly available datasets, there is not enough data for training deep-neural-networks-based models to the point of generalising well over data. This paper presents PLOD, a large-scale dataset for abbreviation detection and extraction that contains 160k+ segments automatically annotated with abbreviations and their long forms. We performed manual validation over a set of insta","authors_text":"Constantin Or\\u{a}san, Diptesh Kanojia, Hadeel Saadany, Leonardo Zilio, Prashant Sharma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T03:52:21Z","title":"PLOD: An Abbreviation Detection Dataset for Scientific Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.12061","kind":"arxiv","version":2},"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":"sha256:15e5f4a14c5394ceb4b4d7f43e02fe95ae8458687efa274b70304950b41b5cf8","target":"record","created_at":"2026-07-05T04:18:52Z","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":"6a8b4b4d4fbfce8952c82ef9e78e8a49683a13a68a22c8e52d2167985c09126a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-04-26T03:52:21Z","title_canon_sha256":"e1a7fb27afea5818017c745af67f0809be66fc7895157f18c90a49e2c7771ce0"},"schema_version":"1.0","source":{"id":"2204.12061","kind":"arxiv","version":2}},"canonical_sha256":"12f06babe985b93f9cf56b14e133bbad44e5fafc92eca6ae05ac8eda245ef314","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"12f06babe985b93f9cf56b14e133bbad44e5fafc92eca6ae05ac8eda245ef314","first_computed_at":"2026-07-05T04:18:52.590165Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:18:52.590165Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9Kd7Ygw0jGXhLJjG64cO6HT36q4lAjYu4WrUx4NAhUprHWhJsKoj5QEuOqlwuQWh9+NLHfa/vsfoV30saZIlDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:18:52.590607Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.12061","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:15e5f4a14c5394ceb4b4d7f43e02fe95ae8458687efa274b70304950b41b5cf8","sha256:143e3d427518685f496831ea3db344607139ec4604b22069f9af5d455393a523"],"state_sha256":"1310ff12254318439d7e798ad288f672367d5d5050ef5010ad103eeb4e02d4f4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AkoPZpLu+5AhP1bjNJTGnq61brNlU+hkCVW0oJsGkci8wpIgA7/FZ2EKg2O8jfUnLP8VA2N1KmJ1a0H3y7u3DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:46:21.250536Z","bundle_sha256":"b7556f051d74a289c402cf10d75c25313d3c0f3a7e4032dbee96c783b2b93b69"}}