{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LGO6ED4S55QJVOJMG2FOYUWESM","short_pith_number":"pith:LGO6ED4S","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"},"canonical_sha256":"599de20f92ef609ab92c368aec52c4931962d02966db81551a13e145f0baaf93","source":{"kind":"arxiv","id":"2401.17824","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17824","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17824v1","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17824","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_12","alias_value":"LGO6ED4S55QJ","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_16","alias_value":"LGO6ED4S55QJVOJM","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_8","alias_value":"LGO6ED4S","created_at":"2026-07-05T07:39:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LGO6ED4S55QJVOJMG2FOYUWESM","target":"record","payload":{"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"},"canonical_sha256":"599de20f92ef609ab92c368aec52c4931962d02966db81551a13e145f0baaf93","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"},"source_kind":"arxiv","source_id":"2401.17824","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":"2026-07-05T07:39:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZ/04w0DK92/8txuwHMipCT1RxL+jcdR+k0wtqdz02Ba+96H8Np4l3WasXJD87qr+HWX4RPgMA2Vc4XJsRLTAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:41:38.877813Z"},"content_sha256":"7e64d6a8f322573f05031c9a673afffc3d5acd7f13bccc98d3d4a1d2b5044eaf","schema_version":"1.0","event_id":"sha256:7e64d6a8f322573f05031c9a673afffc3d5acd7f13bccc98d3d4a1d2b5044eaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LGO6ED4S55QJVOJMG2FOYUWESM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:39:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X0M4bXToCaeylazXis/pd+zRiet9DkXhOU3CtgZOmHe1J69tHf4y0vk2akU59dnjLnCllaPCOh2oyul1X0BDAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T18:41:38.878311Z"},"content_sha256":"b7d363ce592813b9b55877f3f21262e37603bb6dd1ad8f1238256dff5718a18a","schema_version":"1.0","event_id":"sha256:b7d363ce592813b9b55877f3f21262e37603bb6dd1ad8f1238256dff5718a18a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM/bundle.json","state_url":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LGO6ED4S55QJVOJMG2FOYUWESM/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":"2026-08-08T18:41:38Z","links":{"resolver":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM","bundle":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM/bundle.json","state":"https://pith.science/pith/LGO6ED4S55QJVOJMG2FOYUWESM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LGO6ED4S55QJVOJMG2FOYUWESM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LGO6ED4S55QJVOJMG2FOYUWESM","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":"e8453c85f7253c28ebd36eb43b663025496200aaf6f800ea1c24b4d07ea54889","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T13:35:07Z","title_canon_sha256":"bbd497ec2c1fa847d8743ed6c50be9aca327785552702805c4a06bad9be00978"},"schema_version":"1.0","source":{"id":"2401.17824","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17824","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17824v1","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17824","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_12","alias_value":"LGO6ED4S55QJ","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_16","alias_value":"LGO6ED4S55QJVOJM","created_at":"2026-07-05T07:39:42Z"},{"alias_kind":"pith_short_8","alias_value":"LGO6ED4S","created_at":"2026-07-05T07:39:42Z"}],"graph_snapshots":[{"event_id":"sha256:b7d363ce592813b9b55877f3f21262e37603bb6dd1ad8f1238256dff5718a18a","target":"graph","created_at":"2026-07-05T07:39:42Z","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/2401.17824/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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,","authors_text":"Akiko Aizawa, Anh Khoa Duong Nguyen, An Tuan Dao, Florian Boudin, Huy Quoc To, Junfeng Jiang, Kaito Sugimoto, Xanh Ho, Yuki Chida","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T13:35:07Z","title":"A Survey of Pre-trained Language Models for Processing Scientific Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17824","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":"sha256:7e64d6a8f322573f05031c9a673afffc3d5acd7f13bccc98d3d4a1d2b5044eaf","target":"record","created_at":"2026-07-05T07:39:42Z","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":"e8453c85f7253c28ebd36eb43b663025496200aaf6f800ea1c24b4d07ea54889","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-31T13:35:07Z","title_canon_sha256":"bbd497ec2c1fa847d8743ed6c50be9aca327785552702805c4a06bad9be00978"},"schema_version":"1.0","source":{"id":"2401.17824","kind":"arxiv","version":1}},"canonical_sha256":"599de20f92ef609ab92c368aec52c4931962d02966db81551a13e145f0baaf93","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"599de20f92ef609ab92c368aec52c4931962d02966db81551a13e145f0baaf93","first_computed_at":"2026-07-05T07:39:42.928612Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:42.928612Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2czLrXhmZCnBFM5ItBYYo6jHd7T/lAeatxA7Baq8AAXWAoouFbDA9EAaVPfK8AbjmBlKDVsAH4X4OPhQFLjJAg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:42.929083Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.17824","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7e64d6a8f322573f05031c9a673afffc3d5acd7f13bccc98d3d4a1d2b5044eaf","sha256:b7d363ce592813b9b55877f3f21262e37603bb6dd1ad8f1238256dff5718a18a"],"state_sha256":"e256ab3e11dadc8378f8cfbb6cbdb1a9f6044500cdbd55279a506c5737ac7264"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bTynKyBtvY3/Ric6/nZE/HyHkOu0lyHzw2iSuz7iERh4QD8MhBHzuVu+54wopZPfS1p6TPxJ5P6t5GTL4hK3BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T18:41:38.883950Z","bundle_sha256":"a9d372cecb113a26edfebac95b23322742ba35c3874e305020a4dac890bb4cb9"}}