{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6ZAWU6TPZCWBL7ZXUD7G2TU7GH","short_pith_number":"pith:6ZAWU6TP","schema_version":"1.0","canonical_sha256":"f6416a7a6fc8ac15ff37a0fe6d4e9f31ddf6e155ea8713c2c862314e347bac61","source":{"kind":"arxiv","id":"2401.12005","version":2},"attestation_state":"computed","paper":{"title":"ALMs: Authorial Language Models for Authorship Attribution","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akira Murakami, Jack Grieve, Weihang Huang","submitted_at":"2024-01-22T14:53:59Z","abstract_excerpt":"In this paper, we introduce an authorship attribution method called Authorial Language Models (ALMs) that involves identifying the most likely author of a questioned document based on the perplexity of the questioned document calculated for a set of causal language models fine-tuned on the writings of a set of candidate author. We benchmarked ALMs against state-of-art-systems using the CCAT50 dataset and the Blogs50 datasets. We find that ALMs achieves a macro-average accuracy score of 83.6% on Blogs50, outperforming all other methods, and 74.9% on CCAT50, matching the performance of the best "},"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":"2401.12005","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-22T14:53:59Z","cross_cats_sorted":[],"title_canon_sha256":"1f56d1caf6b0cd16940e1df6fd5d8b7ac6c6af224958651f9828854eb77025df","abstract_canon_sha256":"16a9724687424093cfaee5e11ffd3d1f6322d046ed1acb0f1711a3ebb5da0703"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:44:22.545414Z","signature_b64":"uBHNNdT5k0uAFBIibNw4GYQsn2IZbEefKOTYmJ1PClxrk5IoOXf8zJElz/DBZ/vKyH0BpS+BtOTW4iZiRKiWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f6416a7a6fc8ac15ff37a0fe6d4e9f31ddf6e155ea8713c2c862314e347bac61","last_reissued_at":"2026-07-05T07:44:22.544976Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:44:22.544976Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ALMs: Authorial Language Models for Authorship Attribution","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Akira Murakami, Jack Grieve, Weihang Huang","submitted_at":"2024-01-22T14:53:59Z","abstract_excerpt":"In this paper, we introduce an authorship attribution method called Authorial Language Models (ALMs) that involves identifying the most likely author of a questioned document based on the perplexity of the questioned document calculated for a set of causal language models fine-tuned on the writings of a set of candidate author. We benchmarked ALMs against state-of-art-systems using the CCAT50 dataset and the Blogs50 datasets. We find that ALMs achieves a macro-average accuracy score of 83.6% on Blogs50, outperforming all other methods, and 74.9% on CCAT50, matching the performance of the best "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12005","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/2401.12005/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":"2401.12005","created_at":"2026-07-05T07:44:22.545042+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.12005v2","created_at":"2026-07-05T07:44:22.545042+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12005","created_at":"2026-07-05T07:44:22.545042+00:00"},{"alias_kind":"pith_short_12","alias_value":"6ZAWU6TPZCWB","created_at":"2026-07-05T07:44:22.545042+00:00"},{"alias_kind":"pith_short_16","alias_value":"6ZAWU6TPZCWBL7ZX","created_at":"2026-07-05T07:44:22.545042+00:00"},{"alias_kind":"pith_short_8","alias_value":"6ZAWU6TP","created_at":"2026-07-05T07:44:22.545042+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6ZAWU6TPZCWBL7ZXUD7G2TU7GH","json":"https://pith.science/pith/6ZAWU6TPZCWBL7ZXUD7G2TU7GH.json","graph_json":"https://pith.science/api/pith-number/6ZAWU6TPZCWBL7ZXUD7G2TU7GH/graph.json","events_json":"https://pith.science/api/pith-number/6ZAWU6TPZCWBL7ZXUD7G2TU7GH/events.json","paper":"https://pith.science/paper/6ZAWU6TP"},"agent_actions":{"view_html":"https://pith.science/pith/6ZAWU6TPZCWBL7ZXUD7G2TU7GH","download_json":"https://pith.science/pith/6ZAWU6TPZCWBL7ZXUD7G2TU7GH.json","view_paper":"https://pith.science/paper/6ZAWU6TP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.12005&json=true","fetch_graph":"https://pith.science/api/pith-number/6ZAWU6TPZCWBL7ZXUD7G2TU7GH/graph.json","fetch_events":"https://pith.science/api/pith-number/6ZAWU6TPZCWBL7ZXUD7G2TU7GH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6ZAWU6TPZCWBL7ZXUD7G2TU7GH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6ZAWU6TPZCWBL7ZXUD7G2TU7GH/action/storage_attestation","attest_author":"https://pith.science/pith/6ZAWU6TPZCWBL7ZXUD7G2TU7GH/action/author_attestation","sign_citation":"https://pith.science/pith/6ZAWU6TPZCWBL7ZXUD7G2TU7GH/action/citation_signature","submit_replication":"https://pith.science/pith/6ZAWU6TPZCWBL7ZXUD7G2TU7GH/action/replication_record"}},"created_at":"2026-07-05T07:44:22.545042+00:00","updated_at":"2026-07-05T07:44:22.545042+00:00"}