{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:35CGQBSOZX4DOXYXACWKF3HPBB","short_pith_number":"pith:35CGQBSO","canonical_record":{"source":{"id":"2504.19021","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-26T21:06:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6e9fd092d7c5dd51ef407f61589918d134f41399d03e9b78b3145d5ca1c6596","abstract_canon_sha256":"47c741b366510d9cd24f3d22d28a934d34b441aa2421340033485ff6e3022d6d"},"schema_version":"1.0"},"canonical_sha256":"df4468064ecdf8375f1700aca2ecef0849f1dfaf6083f3ca364ffc4bdd1a6925","source":{"kind":"arxiv","id":"2504.19021","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19021","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19021v2","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19021","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"35CGQBSOZX4D","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"35CGQBSOZX4DOXYX","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"35CGQBSO","created_at":"2026-07-05T12:06:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:35CGQBSOZX4DOXYXACWKF3HPBB","target":"record","payload":{"canonical_record":{"source":{"id":"2504.19021","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-26T21:06:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c6e9fd092d7c5dd51ef407f61589918d134f41399d03e9b78b3145d5ca1c6596","abstract_canon_sha256":"47c741b366510d9cd24f3d22d28a934d34b441aa2421340033485ff6e3022d6d"},"schema_version":"1.0"},"canonical_sha256":"df4468064ecdf8375f1700aca2ecef0849f1dfaf6083f3ca364ffc4bdd1a6925","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:09.943638Z","signature_b64":"PEiGQQ1QtgoO5g4CUa7gx+zDN6MdQWNnbKFK2nwTMbnDGh4N4DDMOINbUq2IuE9uEMlt5bV4KpaYVAK4VQYsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df4468064ecdf8375f1700aca2ecef0849f1dfaf6083f3ca364ffc4bdd1a6925","last_reissued_at":"2026-07-05T12:06:09.943052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:09.943052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.19021","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VlyMdxH7COvV5U8OzYYANXGJ41BwwKGIdKttTgEqkdh0IC3OjEOVd/Gy+R5WiOhe5VQ9g/ewFS12DBXHjl3mAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:43:17.572305Z"},"content_sha256":"d200eda06c5dba5f84dff8620d2a3b66ad9ae634a4f4213142f5664c9239580a","schema_version":"1.0","event_id":"sha256:d200eda06c5dba5f84dff8620d2a3b66ad9ae634a4f4213142f5664c9239580a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:35CGQBSOZX4DOXYXACWKF3HPBB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Advancing Scientific Text Classification: Fine-Tuned Models with Dataset Expansion and Hard-Voting","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"G\\'abor Kert\\'esz, Zhyar Rzgar K Rostam","submitted_at":"2025-04-26T21:06:49Z","abstract_excerpt":"Efficient text classification is essential for handling the increasing volume of academic publications. This study explores the use of pre-trained language models (PLMs), including BERT, SciBERT, BioBERT, and BlueBERT, fine-tuned on the Web of Science (WoS-46985) dataset for scientific text classification. To enhance performance, we augment the dataset by executing seven targeted queries in the WoS database, retrieving 1,000 articles per category aligned with WoS-46985's main classes. PLMs predict labels for this unlabeled data, and a hard-voting strategy combines predictions for improved accu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19021","kind":"arxiv","version":2},"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/2504.19021/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":"2026-07-05T12:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9WaZcIlvXjgxH2fySFhfSCoNyUk3ZOczgJT2JVwj6mkn/Ww5oY087RBfrpbPEJb07nv29ISfvtj13xVVj5JWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T13:43:17.572873Z"},"content_sha256":"146a6ab81c8f0843924c7094029ec5dbc2765795e8332a597d75fe09fa456f9e","schema_version":"1.0","event_id":"sha256:146a6ab81c8f0843924c7094029ec5dbc2765795e8332a597d75fe09fa456f9e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB/bundle.json","state_url":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/35CGQBSOZX4DOXYXACWKF3HPBB/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":"2026-08-17T13:43:17Z","links":{"resolver":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB","bundle":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB/bundle.json","state":"https://pith.science/pith/35CGQBSOZX4DOXYXACWKF3HPBB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/35CGQBSOZX4DOXYXACWKF3HPBB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:35CGQBSOZX4DOXYXACWKF3HPBB","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":"47c741b366510d9cd24f3d22d28a934d34b441aa2421340033485ff6e3022d6d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-26T21:06:49Z","title_canon_sha256":"c6e9fd092d7c5dd51ef407f61589918d134f41399d03e9b78b3145d5ca1c6596"},"schema_version":"1.0","source":{"id":"2504.19021","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.19021","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2504.19021v2","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19021","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"35CGQBSOZX4D","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"35CGQBSOZX4DOXYX","created_at":"2026-07-05T12:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"35CGQBSO","created_at":"2026-07-05T12:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:146a6ab81c8f0843924c7094029ec5dbc2765795e8332a597d75fe09fa456f9e","target":"graph","created_at":"2026-07-05T12:06:09Z","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/2504.19021/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Efficient text classification is essential for handling the increasing volume of academic publications. This study explores the use of pre-trained language models (PLMs), including BERT, SciBERT, BioBERT, and BlueBERT, fine-tuned on the Web of Science (WoS-46985) dataset for scientific text classification. To enhance performance, we augment the dataset by executing seven targeted queries in the WoS database, retrieving 1,000 articles per category aligned with WoS-46985's main classes. PLMs predict labels for this unlabeled data, and a hard-voting strategy combines predictions for improved accu","authors_text":"G\\'abor Kert\\'esz, Zhyar Rzgar K Rostam","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-26T21:06:49Z","title":"Advancing Scientific Text Classification: Fine-Tuned Models with Dataset Expansion and Hard-Voting"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19021","kind":"arxiv","version":2},"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:d200eda06c5dba5f84dff8620d2a3b66ad9ae634a4f4213142f5664c9239580a","target":"record","created_at":"2026-07-05T12:06:09Z","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":"47c741b366510d9cd24f3d22d28a934d34b441aa2421340033485ff6e3022d6d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-04-26T21:06:49Z","title_canon_sha256":"c6e9fd092d7c5dd51ef407f61589918d134f41399d03e9b78b3145d5ca1c6596"},"schema_version":"1.0","source":{"id":"2504.19021","kind":"arxiv","version":2}},"canonical_sha256":"df4468064ecdf8375f1700aca2ecef0849f1dfaf6083f3ca364ffc4bdd1a6925","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df4468064ecdf8375f1700aca2ecef0849f1dfaf6083f3ca364ffc4bdd1a6925","first_computed_at":"2026-07-05T12:06:09.943052Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:09.943052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PEiGQQ1QtgoO5g4CUa7gx+zDN6MdQWNnbKFK2nwTMbnDGh4N4DDMOINbUq2IuE9uEMlt5bV4KpaYVAK4VQYsAw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:09.943638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.19021","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d200eda06c5dba5f84dff8620d2a3b66ad9ae634a4f4213142f5664c9239580a","sha256:146a6ab81c8f0843924c7094029ec5dbc2765795e8332a597d75fe09fa456f9e"],"state_sha256":"b8edbff036fd06ae3d2a8f5de44d54c4a1c3efc8c2bb4a845d214c0d5c098e1e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZFziKY8bNN3ShZymOZ8G9I5qg4Uv6arHIC+CMV5MprjjCWolZ7fDtmTcwDYWySqdkHCE2Ghw3GHg9m9+jQQ/Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T13:43:17.577134Z","bundle_sha256":"ab9f35675283b7548bc90ee525ba5436d6b9e70975902c2d3d1999d2531ed49f"}}