{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UHOJOOR4SGE66TEBL4BXSU5E33","short_pith_number":"pith:UHOJOOR4","schema_version":"1.0","canonical_sha256":"a1dc973a3c9189ef4c815f037953a4ded8de48a7a46b0f2d88c808e60ba2268e","source":{"kind":"arxiv","id":"2412.17321","version":1},"attestation_state":"computed","paper":{"title":"Assessing Human Editing Effort on LLM-Generated Texts via Compression-Based Edit Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Louis Abraham, Nicolas Devatine","submitted_at":"2024-12-23T06:29:25Z","abstract_excerpt":"Assessing the extent of human edits on texts generated by Large Language Models (LLMs) is crucial to understanding the human-AI interactions and improving the quality of automated text generation systems. Existing edit distance metrics, such as Levenshtein, BLEU, ROUGE, and TER, often fail to accurately measure the effort required for post-editing, especially when edits involve substantial modifications, such as block operations. In this paper, we introduce a novel compression-based edit distance metric grounded in the Lempel-Ziv-77 algorithm, designed to quantify the amount of post-editing ap"},"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":"2412.17321","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-23T06:29:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ddfe666e7795a81885a0724d1bef1b09d8511ea3922426ecb44d04faa95be3ff","abstract_canon_sha256":"c6d4a608e7ebd753fb87963016b61b3c2c2c8a405edcfac33e3c6b0cd6f96710"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:20.826419Z","signature_b64":"SwJPQlIwRNuWvGf5tY8ijj5RW1X9rlcHTblL5gkktePvlQUtKOEr1nQGRwbq8gBrM4d/UVn32jxOMzZR9CHbBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1dc973a3c9189ef4c815f037953a4ded8de48a7a46b0f2d88c808e60ba2268e","last_reissued_at":"2026-07-05T09:53:20.825954Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:20.825954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Assessing Human Editing Effort on LLM-Generated Texts via Compression-Based Edit Distance","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Louis Abraham, Nicolas Devatine","submitted_at":"2024-12-23T06:29:25Z","abstract_excerpt":"Assessing the extent of human edits on texts generated by Large Language Models (LLMs) is crucial to understanding the human-AI interactions and improving the quality of automated text generation systems. Existing edit distance metrics, such as Levenshtein, BLEU, ROUGE, and TER, often fail to accurately measure the effort required for post-editing, especially when edits involve substantial modifications, such as block operations. In this paper, we introduce a novel compression-based edit distance metric grounded in the Lempel-Ziv-77 algorithm, designed to quantify the amount of post-editing ap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17321","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/2412.17321/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":"2412.17321","created_at":"2026-07-05T09:53:20.826013+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.17321v1","created_at":"2026-07-05T09:53:20.826013+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17321","created_at":"2026-07-05T09:53:20.826013+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHOJOOR4SGE6","created_at":"2026-07-05T09:53:20.826013+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHOJOOR4SGE66TEB","created_at":"2026-07-05T09:53:20.826013+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHOJOOR4","created_at":"2026-07-05T09:53:20.826013+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.06209","citing_title":"TelcoAgent-Bench: A Multilingual Benchmark for Telecom AI Agents","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23430","citing_title":"Automating Categorization of Scientific Texts with In-Context Learning and Prompt-Chaining in Large Language Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHOJOOR4SGE66TEBL4BXSU5E33","json":"https://pith.science/pith/UHOJOOR4SGE66TEBL4BXSU5E33.json","graph_json":"https://pith.science/api/pith-number/UHOJOOR4SGE66TEBL4BXSU5E33/graph.json","events_json":"https://pith.science/api/pith-number/UHOJOOR4SGE66TEBL4BXSU5E33/events.json","paper":"https://pith.science/paper/UHOJOOR4"},"agent_actions":{"view_html":"https://pith.science/pith/UHOJOOR4SGE66TEBL4BXSU5E33","download_json":"https://pith.science/pith/UHOJOOR4SGE66TEBL4BXSU5E33.json","view_paper":"https://pith.science/paper/UHOJOOR4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.17321&json=true","fetch_graph":"https://pith.science/api/pith-number/UHOJOOR4SGE66TEBL4BXSU5E33/graph.json","fetch_events":"https://pith.science/api/pith-number/UHOJOOR4SGE66TEBL4BXSU5E33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHOJOOR4SGE66TEBL4BXSU5E33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHOJOOR4SGE66TEBL4BXSU5E33/action/storage_attestation","attest_author":"https://pith.science/pith/UHOJOOR4SGE66TEBL4BXSU5E33/action/author_attestation","sign_citation":"https://pith.science/pith/UHOJOOR4SGE66TEBL4BXSU5E33/action/citation_signature","submit_replication":"https://pith.science/pith/UHOJOOR4SGE66TEBL4BXSU5E33/action/replication_record"}},"created_at":"2026-07-05T09:53:20.826013+00:00","updated_at":"2026-07-05T09:53:20.826013+00:00"}