{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZTFE7UUBSZNZCBHDB4IQLGM4CI","short_pith_number":"pith:ZTFE7UUB","canonical_record":{"source":{"id":"2305.18324","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:26:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6da8d396558f67799027112058ee359dee12c50b9adb487660237bf0eb030d9d","abstract_canon_sha256":"64ffe92e405fb3ec1eda835ce14feabd680cc8e0892a6c1a374245c567fa97e8"},"schema_version":"1.0"},"canonical_sha256":"ccca4fd281965b9104e30f1105999c121c6d390a019fba8c80c1462150d4f5ae","source":{"kind":"arxiv","id":"2305.18324","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18324","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18324v1","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18324","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZTFE7UUBSZNZ","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZTFE7UUBSZNZCBHD","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZTFE7UUB","created_at":"2026-07-05T06:14:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZTFE7UUBSZNZCBHDB4IQLGM4CI","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18324","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:26:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6da8d396558f67799027112058ee359dee12c50b9adb487660237bf0eb030d9d","abstract_canon_sha256":"64ffe92e405fb3ec1eda835ce14feabd680cc8e0892a6c1a374245c567fa97e8"},"schema_version":"1.0"},"canonical_sha256":"ccca4fd281965b9104e30f1105999c121c6d390a019fba8c80c1462150d4f5ae","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:14:59.626231Z","signature_b64":"Qgv/9HV5qrDNsuR4o5BQtbOUeY19BymfgEnUwqxkH0HbVIJfO+5rHHMv20jM5SPKoqwRC/6Ne6I/F0eLglH/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccca4fd281965b9104e30f1105999c121c6d390a019fba8c80c1462150d4f5ae","last_reissued_at":"2026-07-05T06:14:59.625805Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:14:59.625805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18324","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":"2026-07-05T06:14:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pZrTcKduyxAnPUmvC3JAlvJ7lHWUyizBg+mlfFFxPxIOkxm51rsGuUo6lt3z82H9wyZIXdnKQB7Qru7oOsJVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:24:48.712554Z"},"content_sha256":"4a84e0d7102506198d663318b77276b1973371578d723f05a17ef05b623fbeaf","schema_version":"1.0","event_id":"sha256:4a84e0d7102506198d663318b77276b1973371578d723f05a17ef05b623fbeaf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZTFE7UUBSZNZCBHDB4IQLGM4CI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regex-augmented Domain Transfer Topic Classification based on a Pre-trained Language Model: An application in Financial Domain","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jimmy Lin, Syed Shariyar Murtaza, Vanessa Liao, Yifan Nie","submitted_at":"2023-05-23T03:26:32Z","abstract_excerpt":"A common way to use large pre-trained language models for downstream tasks is to fine tune them using additional layers. This may not work well if downstream domain is a specialized domain whereas the large language model has been pre-trained on a generic corpus. In this paper, we discuss the use of regular expression patterns employed as features for domain knowledge during the process of fine tuning, in addition to domain specific text. Our experiments on real scenario production data show that this method of fine tuning improves the downstream text classification tasks as compared to fine t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18324","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/2305.18324/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":"2026-07-05T06:14:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+S5w5B7zZdp+3MfJxPM43bzpGV/pd3luRn5/HwVp+X3hWJyAp+qqPVIryywa36DPAGUHvmuhikYgk8RojlOBDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:24:48.712922Z"},"content_sha256":"721f78f06b57a2c7e9e4fda79b351085c7d79918035d750bc37f75ada082a598","schema_version":"1.0","event_id":"sha256:721f78f06b57a2c7e9e4fda79b351085c7d79918035d750bc37f75ada082a598"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZTFE7UUBSZNZCBHDB4IQLGM4CI/bundle.json","state_url":"https://pith.science/pith/ZTFE7UUBSZNZCBHDB4IQLGM4CI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZTFE7UUBSZNZCBHDB4IQLGM4CI/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":"2026-07-06T17:24:48Z","links":{"resolver":"https://pith.science/pith/ZTFE7UUBSZNZCBHDB4IQLGM4CI","bundle":"https://pith.science/pith/ZTFE7UUBSZNZCBHDB4IQLGM4CI/bundle.json","state":"https://pith.science/pith/ZTFE7UUBSZNZCBHDB4IQLGM4CI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZTFE7UUBSZNZCBHDB4IQLGM4CI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZTFE7UUBSZNZCBHDB4IQLGM4CI","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":"64ffe92e405fb3ec1eda835ce14feabd680cc8e0892a6c1a374245c567fa97e8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:26:32Z","title_canon_sha256":"6da8d396558f67799027112058ee359dee12c50b9adb487660237bf0eb030d9d"},"schema_version":"1.0","source":{"id":"2305.18324","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18324","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18324v1","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18324","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"pith_short_12","alias_value":"ZTFE7UUBSZNZ","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"pith_short_16","alias_value":"ZTFE7UUBSZNZCBHD","created_at":"2026-07-05T06:14:59Z"},{"alias_kind":"pith_short_8","alias_value":"ZTFE7UUB","created_at":"2026-07-05T06:14:59Z"}],"graph_snapshots":[{"event_id":"sha256:721f78f06b57a2c7e9e4fda79b351085c7d79918035d750bc37f75ada082a598","target":"graph","created_at":"2026-07-05T06:14:59Z","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/2305.18324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A common way to use large pre-trained language models for downstream tasks is to fine tune them using additional layers. This may not work well if downstream domain is a specialized domain whereas the large language model has been pre-trained on a generic corpus. In this paper, we discuss the use of regular expression patterns employed as features for domain knowledge during the process of fine tuning, in addition to domain specific text. Our experiments on real scenario production data show that this method of fine tuning improves the downstream text classification tasks as compared to fine t","authors_text":"Jimmy Lin, Syed Shariyar Murtaza, Vanessa Liao, Yifan Nie","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:26:32Z","title":"Regex-augmented Domain Transfer Topic Classification based on a Pre-trained Language Model: An application in Financial Domain"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18324","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":"sha256:4a84e0d7102506198d663318b77276b1973371578d723f05a17ef05b623fbeaf","target":"record","created_at":"2026-07-05T06:14:59Z","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":"64ffe92e405fb3ec1eda835ce14feabd680cc8e0892a6c1a374245c567fa97e8","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-23T03:26:32Z","title_canon_sha256":"6da8d396558f67799027112058ee359dee12c50b9adb487660237bf0eb030d9d"},"schema_version":"1.0","source":{"id":"2305.18324","kind":"arxiv","version":1}},"canonical_sha256":"ccca4fd281965b9104e30f1105999c121c6d390a019fba8c80c1462150d4f5ae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccca4fd281965b9104e30f1105999c121c6d390a019fba8c80c1462150d4f5ae","first_computed_at":"2026-07-05T06:14:59.625805Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:14:59.625805Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qgv/9HV5qrDNsuR4o5BQtbOUeY19BymfgEnUwqxkH0HbVIJfO+5rHHMv20jM5SPKoqwRC/6Ne6I/F0eLglH/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:14:59.626231Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18324","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a84e0d7102506198d663318b77276b1973371578d723f05a17ef05b623fbeaf","sha256:721f78f06b57a2c7e9e4fda79b351085c7d79918035d750bc37f75ada082a598"],"state_sha256":"e21bf6cedb1a8783ecc031c3905fa17f61ff8d4fabfa0916b338cecf5b376064"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CR1iDSkgkB5UCLpXsYTcc1BlLAVFLt1/VWAi/iKFw6AoqdgmFKzBA8AKyPAJGvK85r372Dr/KKUt5LZoR+MuDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:24:48.714892Z","bundle_sha256":"0e55e2f52cb67dbac35e92eb4e1cd6df6603139f8d1381cc4090edcb80adb5e7"}}