{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:64PQDJUGCWGG2B7NBRDNIRXR74","short_pith_number":"pith:64PQDJUG","canonical_record":{"source":{"id":"2203.04729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-09T14:10:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1b307347b92eb3c4fcd823e66492f036f6368319f1f06b578193c2eb4dfb50d9","abstract_canon_sha256":"cc3c5b122ed82b7851c52befed845db2ab7aabfaee5959f03ad6482d6f4a1169"},"schema_version":"1.0"},"canonical_sha256":"f71f01a686158c6d07ed0c46d446f1ff0c0904b6e5c031d048968010e76b9b1b","source":{"kind":"arxiv","id":"2203.04729","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.04729","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"2203.04729v1","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04729","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"64PQDJUGCWGG","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"pith_short_16","alias_value":"64PQDJUGCWGG2B7N","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"pith_short_8","alias_value":"64PQDJUG","created_at":"2026-07-05T04:33:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:64PQDJUGCWGG2B7NBRDNIRXR74","target":"record","payload":{"canonical_record":{"source":{"id":"2203.04729","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-09T14:10:55Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1b307347b92eb3c4fcd823e66492f036f6368319f1f06b578193c2eb4dfb50d9","abstract_canon_sha256":"cc3c5b122ed82b7851c52befed845db2ab7aabfaee5959f03ad6482d6f4a1169"},"schema_version":"1.0"},"canonical_sha256":"f71f01a686158c6d07ed0c46d446f1ff0c0904b6e5c031d048968010e76b9b1b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:33:32.222366Z","signature_b64":"RKAuBnq4g3+ZO+t4Nvde7F1EMGBEcFCoiQTlAbKYCP0R5gsL5hohoaX5OmDVcBlQgm1lugZHHc03vDVbaPprBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f71f01a686158c6d07ed0c46d446f1ff0c0904b6e5c031d048968010e76b9b1b","last_reissued_at":"2026-07-05T04:33:32.221891Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:33:32.221891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.04729","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":"2026-07-05T04:33:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6Sl01oHYF6VF6DpRIRdNDP8Ds5tbXfSredEFAF8dJGEag3vOzSf+D/V74sF1DaF9rsdZwF8CJlNQ1UvxsO0qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T10:51:47.055348Z"},"content_sha256":"a5c6765a07123a5dd48123d14bd2d0d6096330a930bf521d1b043d93ed00eca8","schema_version":"1.0","event_id":"sha256:a5c6765a07123a5dd48123d14bd2d0d6096330a930bf521d1b043d93ed00eca8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:64PQDJUGCWGG2B7NBRDNIRXR74","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pretrained Domain-Specific Language Model for General Information Retrieval Tasks in the AEC Domain","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jia-Rui Lin, Ke-Yin Chen, Xin-Zheng Lu, Yu-Cheng Zhou, Zhe Zheng","submitted_at":"2022-03-09T14:10:55Z","abstract_excerpt":"As an essential task for the architecture, engineering, and construction (AEC) industry, information retrieval (IR) from unstructured textual data based on natural language processing (NLP) is gaining increasing attention. Although various deep learning (DL) models for IR tasks have been investigated in the AEC domain, it is still unclear how domain corpora and domain-specific pretrained DL models can improve performance in various IR tasks. To this end, this work systematically explores the impacts of domain corpora and various transfer learning techniques on the performance of DL models for "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04729","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/2203.04729/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":"2026-07-05T04:33:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y9/EX+DdXckPuhY3BATXFJAQ57xXkUojlvSbSKmP+FMl9DnpROFcIzDaENBDmvHNwDXXdtCWJGjJ18IDZtkDCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-28T10:51:47.055733Z"},"content_sha256":"22d9f2e6d8d8b235a068244dfa29970ce71ce54f06be261a2cf9cc02a4b2c57e","schema_version":"1.0","event_id":"sha256:22d9f2e6d8d8b235a068244dfa29970ce71ce54f06be261a2cf9cc02a4b2c57e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/64PQDJUGCWGG2B7NBRDNIRXR74/bundle.json","state_url":"https://pith.science/pith/64PQDJUGCWGG2B7NBRDNIRXR74/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/64PQDJUGCWGG2B7NBRDNIRXR74/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":"2026-07-28T10:51:47Z","links":{"resolver":"https://pith.science/pith/64PQDJUGCWGG2B7NBRDNIRXR74","bundle":"https://pith.science/pith/64PQDJUGCWGG2B7NBRDNIRXR74/bundle.json","state":"https://pith.science/pith/64PQDJUGCWGG2B7NBRDNIRXR74/state.json","well_known_bundle":"https://pith.science/.well-known/pith/64PQDJUGCWGG2B7NBRDNIRXR74/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:64PQDJUGCWGG2B7NBRDNIRXR74","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":"cc3c5b122ed82b7851c52befed845db2ab7aabfaee5959f03ad6482d6f4a1169","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-09T14:10:55Z","title_canon_sha256":"1b307347b92eb3c4fcd823e66492f036f6368319f1f06b578193c2eb4dfb50d9"},"schema_version":"1.0","source":{"id":"2203.04729","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.04729","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"arxiv_version","alias_value":"2203.04729v1","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.04729","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"pith_short_12","alias_value":"64PQDJUGCWGG","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"pith_short_16","alias_value":"64PQDJUGCWGG2B7N","created_at":"2026-07-05T04:33:32Z"},{"alias_kind":"pith_short_8","alias_value":"64PQDJUG","created_at":"2026-07-05T04:33:32Z"}],"graph_snapshots":[{"event_id":"sha256:22d9f2e6d8d8b235a068244dfa29970ce71ce54f06be261a2cf9cc02a4b2c57e","target":"graph","created_at":"2026-07-05T04:33:32Z","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/2203.04729/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As an essential task for the architecture, engineering, and construction (AEC) industry, information retrieval (IR) from unstructured textual data based on natural language processing (NLP) is gaining increasing attention. Although various deep learning (DL) models for IR tasks have been investigated in the AEC domain, it is still unclear how domain corpora and domain-specific pretrained DL models can improve performance in various IR tasks. To this end, this work systematically explores the impacts of domain corpora and various transfer learning techniques on the performance of DL models for ","authors_text":"Jia-Rui Lin, Ke-Yin Chen, Xin-Zheng Lu, Yu-Cheng Zhou, Zhe Zheng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-09T14:10:55Z","title":"Pretrained Domain-Specific Language Model for General Information Retrieval Tasks in the AEC Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.04729","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:a5c6765a07123a5dd48123d14bd2d0d6096330a930bf521d1b043d93ed00eca8","target":"record","created_at":"2026-07-05T04:33:32Z","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":"cc3c5b122ed82b7851c52befed845db2ab7aabfaee5959f03ad6482d6f4a1169","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-09T14:10:55Z","title_canon_sha256":"1b307347b92eb3c4fcd823e66492f036f6368319f1f06b578193c2eb4dfb50d9"},"schema_version":"1.0","source":{"id":"2203.04729","kind":"arxiv","version":1}},"canonical_sha256":"f71f01a686158c6d07ed0c46d446f1ff0c0904b6e5c031d048968010e76b9b1b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f71f01a686158c6d07ed0c46d446f1ff0c0904b6e5c031d048968010e76b9b1b","first_computed_at":"2026-07-05T04:33:32.221891Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:33:32.221891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RKAuBnq4g3+ZO+t4Nvde7F1EMGBEcFCoiQTlAbKYCP0R5gsL5hohoaX5OmDVcBlQgm1lugZHHc03vDVbaPprBw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:33:32.222366Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.04729","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a5c6765a07123a5dd48123d14bd2d0d6096330a930bf521d1b043d93ed00eca8","sha256:22d9f2e6d8d8b235a068244dfa29970ce71ce54f06be261a2cf9cc02a4b2c57e"],"state_sha256":"cb823c8b6215e286c4f338a5d29fb64deff6717e361bc52d3db1f6764473f2c4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YIltCX1ok1H6GRptgLE91b8U9j8CZEzaqoLtg0JImnoNxsoQoGiCfit5iaoUMrvRIiCFJz3D2/x6jtltmdmWDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-28T10:51:47.058308Z","bundle_sha256":"cfa40b971196e9322cc9ec3c94c105d2bea905bb77ba29d3ff0ad99809951d6e"}}