{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LGO6ED4S55QJVOJMG2FOYUWESM","short_pith_number":"pith:LGO6ED4S","schema_version":"1.0","canonical_sha256":"599de20f92ef609ab92c368aec52c4931962d02966db81551a13e145f0baaf93","source":{"kind":"arxiv","id":"2401.17824","version":1},"attestation_state":"computed","paper":{"title":"A Survey of Pre-trained Language Models for Processing Scientific Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akiko Aizawa, Anh Khoa Duong Nguyen, An Tuan Dao, Florian Boudin, Huy Quoc To, Junfeng Jiang, Kaito Sugimoto, Xanh Ho, Yuki Chida","submitted_at":"2024-01-31T13:35:07Z","abstract_excerpt":"The number of Language Models (LMs) dedicated to processing scientific text is on the rise. Keeping pace with the rapid growth of scientific LMs (SciLMs) has become a daunting task for researchers. To date, no comprehensive surveys on SciLMs have been undertaken, leaving this issue unaddressed. Given the constant stream of new SciLMs, appraising the state-of-the-art and how they compare to each other remain largely unknown. This work fills that gap and provides a comprehensive review of SciLMs, including an extensive analysis of their effectiveness across different domains, tasks and datasets,"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2401.17824","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T13:35:07Z","cross_cats_sorted":[],"title_canon_sha256":"bbd497ec2c1fa847d8743ed6c50be9aca327785552702805c4a06bad9be00978","abstract_canon_sha256":"e8453c85f7253c28ebd36eb43b663025496200aaf6f800ea1c24b4d07ea54889"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:42.929083Z","signature_b64":"2czLrXhmZCnBFM5ItBYYo6jHd7T/lAeatxA7Baq8AAXWAoouFbDA9EAaVPfK8AbjmBlKDVsAH4X4OPhQFLjJAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"599de20f92ef609ab92c368aec52c4931962d02966db81551a13e145f0baaf93","last_reissued_at":"2026-07-05T07:39:42.928612Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:42.928612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey of Pre-trained Language Models for Processing Scientific Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akiko Aizawa, Anh Khoa Duong Nguyen, An Tuan Dao, Florian Boudin, Huy Quoc To, Junfeng Jiang, Kaito Sugimoto, Xanh Ho, Yuki Chida","submitted_at":"2024-01-31T13:35:07Z","abstract_excerpt":"The number of Language Models (LMs) dedicated to processing scientific text is on the rise. Keeping pace with the rapid growth of scientific LMs (SciLMs) has become a daunting task for researchers. To date, no comprehensive surveys on SciLMs have been undertaken, leaving this issue unaddressed. Given the constant stream of new SciLMs, appraising the state-of-the-art and how they compare to each other remain largely unknown. This work fills that gap and provides a comprehensive review of SciLMs, including an extensive analysis of their effectiveness across different domains, tasks and datasets,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17824","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/2401.17824/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2401.17824","created_at":"2026-07-05T07:39:42.928669+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17824v1","created_at":"2026-07-05T07:39:42.928669+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17824","created_at":"2026-07-05T07:39:42.928669+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGO6ED4S55QJ","created_at":"2026-07-05T07:39:42.928669+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGO6ED4S55QJVOJM","created_at":"2026-07-05T07:39:42.928669+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGO6ED4S","created_at":"2026-07-05T07:39:42.928669+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.20556","citing_title":"KeySI: An Interaction Framework for Tuning Text Embeddings Based on Human Feedback","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM","json":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM.json","graph_json":"https://pith.science/api/pith-number/LGO6ED4S55QJVOJMG2FOYUWESM/graph.json","events_json":"https://pith.science/api/pith-number/LGO6ED4S55QJVOJMG2FOYUWESM/events.json","paper":"https://pith.science/paper/LGO6ED4S"},"agent_actions":{"view_html":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM","download_json":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM.json","view_paper":"https://pith.science/paper/LGO6ED4S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17824&json=true","fetch_graph":"https://pith.science/api/pith-number/LGO6ED4S55QJVOJMG2FOYUWESM/graph.json","fetch_events":"https://pith.science/api/pith-number/LGO6ED4S55QJVOJMG2FOYUWESM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM/action/storage_attestation","attest_author":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM/action/author_attestation","sign_citation":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM/action/citation_signature","submit_replication":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM/action/replication_record"}},"created_at":"2026-07-05T07:39:42.928669+00:00","updated_at":"2026-07-05T07:39:42.928669+00:00"}