{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:52YDBYVIRCOLLHFYT6VB6Z3GKO","short_pith_number":"pith:52YDBYVI","canonical_record":{"source":{"id":"2206.15221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T12:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"acc4df5685fdcff4778210e40003db2b267ab9f4f3772ebc9481c083db7f6348","abstract_canon_sha256":"dc37daef48e335d6957f501fd73f8b2f76759a694c1ce03f64758fef207c3b3e"},"schema_version":"1.0"},"canonical_sha256":"eeb030e2a8889cb59cb89faa1f676653bb3b56682c62d8d19aae802371507a6f","source":{"kind":"arxiv","id":"2206.15221","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15221","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15221v1","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15221","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"pith_short_12","alias_value":"52YDBYVIRCOL","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"pith_short_16","alias_value":"52YDBYVIRCOLLHFY","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"pith_short_8","alias_value":"52YDBYVI","created_at":"2026-07-05T04:36:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:52YDBYVIRCOLLHFYT6VB6Z3GKO","target":"record","payload":{"canonical_record":{"source":{"id":"2206.15221","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T12:11:39Z","cross_cats_sorted":[],"title_canon_sha256":"acc4df5685fdcff4778210e40003db2b267ab9f4f3772ebc9481c083db7f6348","abstract_canon_sha256":"dc37daef48e335d6957f501fd73f8b2f76759a694c1ce03f64758fef207c3b3e"},"schema_version":"1.0"},"canonical_sha256":"eeb030e2a8889cb59cb89faa1f676653bb3b56682c62d8d19aae802371507a6f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:26.735500Z","signature_b64":"RL8+24TrcYrMs5VQpOv9YnOI9CeD4ZFULvo86u9GbG5H3GDJSoaDWWr9OtvLhTTBBPPz9O5M9N/oGDOGcv2fDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eeb030e2a8889cb59cb89faa1f676653bb3b56682c62d8d19aae802371507a6f","last_reissued_at":"2026-07-05T04:36:26.735094Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:26.735094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.15221","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":"2026-07-05T04:36:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"S1UM8X3Yt9HBls62aHFoSkRnTNPBtVZQ21EceYijSuN+Jp/htDXpTFUhtaC4gNsbRr7Ud5/+TA/56SG33pSrBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:16:00.919873Z"},"content_sha256":"6f2c20a77762f1c9db67d60d723bbad00c269c194ddce3a489bc2dd726c86b4f","schema_version":"1.0","event_id":"sha256:6f2c20a77762f1c9db67d60d723bbad00c269c194ddce3a489bc2dd726c86b4f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:52YDBYVIRCOLLHFYT6VB6Z3GKO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Domain Adaptive Pretraining for Multilingual Acronym Extraction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Stefan Langer, Usama Yaseen","submitted_at":"2022-06-30T12:11:39Z","abstract_excerpt":"This paper presents our findings from participating in the multilingual acronym extraction shared task SDU@AAAI-22. The task consists of acronym extraction from documents in 6 languages within scientific and legal domains. To address multilingual acronym extraction we employed BiLSTM-CRF with multilingual XLM-RoBERTa embeddings. We pretrained the XLM-RoBERTa model on the shared task corpus to further adapt XLM-RoBERTa embeddings to the shared task domain(s). Our system (team: SMR-NLP) achieved competitive performance for acronym extraction across all the languages."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15221","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.15221/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":"2026-07-05T04:36:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A7EkbbkD0uwjxOis7usJWbY+ORBb2pXNHWZLv8p+aBkkVhG/mevhFxkKRbSa54Nh5xJKG8T1mrHmMC8Y4Kp/AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:16:00.920253Z"},"content_sha256":"eae34ccd0ad5b573c4aa9decd0032a2262b6a654de89090f9689cd407738a50c","schema_version":"1.0","event_id":"sha256:eae34ccd0ad5b573c4aa9decd0032a2262b6a654de89090f9689cd407738a50c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/52YDBYVIRCOLLHFYT6VB6Z3GKO/bundle.json","state_url":"https://pith.science/pith/52YDBYVIRCOLLHFYT6VB6Z3GKO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/52YDBYVIRCOLLHFYT6VB6Z3GKO/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":"2026-08-05T17:16:00Z","links":{"resolver":"https://pith.science/pith/52YDBYVIRCOLLHFYT6VB6Z3GKO","bundle":"https://pith.science/pith/52YDBYVIRCOLLHFYT6VB6Z3GKO/bundle.json","state":"https://pith.science/pith/52YDBYVIRCOLLHFYT6VB6Z3GKO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/52YDBYVIRCOLLHFYT6VB6Z3GKO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:52YDBYVIRCOLLHFYT6VB6Z3GKO","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":"dc37daef48e335d6957f501fd73f8b2f76759a694c1ce03f64758fef207c3b3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T12:11:39Z","title_canon_sha256":"acc4df5685fdcff4778210e40003db2b267ab9f4f3772ebc9481c083db7f6348"},"schema_version":"1.0","source":{"id":"2206.15221","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.15221","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"arxiv_version","alias_value":"2206.15221v1","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.15221","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"pith_short_12","alias_value":"52YDBYVIRCOL","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"pith_short_16","alias_value":"52YDBYVIRCOLLHFY","created_at":"2026-07-05T04:36:26Z"},{"alias_kind":"pith_short_8","alias_value":"52YDBYVI","created_at":"2026-07-05T04:36:26Z"}],"graph_snapshots":[{"event_id":"sha256:eae34ccd0ad5b573c4aa9decd0032a2262b6a654de89090f9689cd407738a50c","target":"graph","created_at":"2026-07-05T04:36:26Z","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/2206.15221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents our findings from participating in the multilingual acronym extraction shared task SDU@AAAI-22. The task consists of acronym extraction from documents in 6 languages within scientific and legal domains. To address multilingual acronym extraction we employed BiLSTM-CRF with multilingual XLM-RoBERTa embeddings. We pretrained the XLM-RoBERTa model on the shared task corpus to further adapt XLM-RoBERTa embeddings to the shared task domain(s). Our system (team: SMR-NLP) achieved competitive performance for acronym extraction across all the languages.","authors_text":"Stefan Langer, Usama Yaseen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T12:11:39Z","title":"Domain Adaptive Pretraining for Multilingual Acronym Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.15221","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":"sha256:6f2c20a77762f1c9db67d60d723bbad00c269c194ddce3a489bc2dd726c86b4f","target":"record","created_at":"2026-07-05T04:36:26Z","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":"dc37daef48e335d6957f501fd73f8b2f76759a694c1ce03f64758fef207c3b3e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-30T12:11:39Z","title_canon_sha256":"acc4df5685fdcff4778210e40003db2b267ab9f4f3772ebc9481c083db7f6348"},"schema_version":"1.0","source":{"id":"2206.15221","kind":"arxiv","version":1}},"canonical_sha256":"eeb030e2a8889cb59cb89faa1f676653bb3b56682c62d8d19aae802371507a6f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eeb030e2a8889cb59cb89faa1f676653bb3b56682c62d8d19aae802371507a6f","first_computed_at":"2026-07-05T04:36:26.735094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:26.735094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RL8+24TrcYrMs5VQpOv9YnOI9CeD4ZFULvo86u9GbG5H3GDJSoaDWWr9OtvLhTTBBPPz9O5M9N/oGDOGcv2fDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:26.735500Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.15221","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f2c20a77762f1c9db67d60d723bbad00c269c194ddce3a489bc2dd726c86b4f","sha256:eae34ccd0ad5b573c4aa9decd0032a2262b6a654de89090f9689cd407738a50c"],"state_sha256":"6938c072d16b841e8f5e3a2126f8d418963cf3b9a7b9efcf1b6abc9fc2c9bdfd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZNr2qt1ActLSu7aHIX1pw32n1LUqr6Fw5zVTZgg6Ow+pwiuSpNWQ2AFJVmEqZx1eBGakjKNJ7O730MHPbFjRCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:16:00.923359Z","bundle_sha256":"290ab21ae2f654d0198275727845caa19c12f6bc7199fdb83720fce39dae55bd"}}