{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:F2ZLQZGXZGYLTSN45LLL6CK3JC","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":"cff86f03eef1de02c8a66395ce7410869c590d94613871f3ff572a56609da88a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-25T08:57:33Z","title_canon_sha256":"a3347a60c99ba038b3fca9ea1cea08bdb6f3c6e946a04a814719c7c95abef7b5"},"schema_version":"1.0","source":{"id":"2401.14019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.14019","created_at":"2026-07-05T07:37:21Z"},{"alias_kind":"arxiv_version","alias_value":"2401.14019v1","created_at":"2026-07-05T07:37:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.14019","created_at":"2026-07-05T07:37:21Z"},{"alias_kind":"pith_short_12","alias_value":"F2ZLQZGXZGYL","created_at":"2026-07-05T07:37:21Z"},{"alias_kind":"pith_short_16","alias_value":"F2ZLQZGXZGYLTSN4","created_at":"2026-07-05T07:37:21Z"},{"alias_kind":"pith_short_8","alias_value":"F2ZLQZGX","created_at":"2026-07-05T07:37:21Z"}],"graph_snapshots":[{"event_id":"sha256:691fb0866947e3990cb40cbcd4050a094678c46e2b737fdb11cd31f6d5126788","target":"graph","created_at":"2026-07-05T07:37:21Z","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/2401.14019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the dynamic landscape of generative NLP, traditional text processing pipelines limit research flexibility and reproducibility, as they are tailored to specific dataset, task, and model combinations. The escalating complexity, involving system prompts, model-specific formats, instructions, and more, calls for a shift to a structured, modular, and customizable solution. Addressing this need, we present Unitxt, an innovative library for customizable textual data preparation and evaluation tailored to generative language models. Unitxt natively integrates with common libraries like HuggingFace ","authors_text":"Ariel Gera, Dafna Sheinwald, Elad Venezian, Elron Bandel, Leshem Choshen, Matan Orbach, Michal Shmueli-Scheuer, Ofir Arviv, Roni Friedman-Melamed, Shachar Don-Yehyia, Yoav Katz, Yotam Perlitz","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-25T08:57:33Z","title":"Unitxt: Flexible, Shareable and Reusable Data Preparation and Evaluation for Generative AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.14019","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":"sha256:82ce60b46bce69f2f5fdb2c8c5ce3cd7671408f9916708ce29ad6b330812e159","target":"record","created_at":"2026-07-05T07:37:21Z","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":"cff86f03eef1de02c8a66395ce7410869c590d94613871f3ff572a56609da88a","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-25T08:57:33Z","title_canon_sha256":"a3347a60c99ba038b3fca9ea1cea08bdb6f3c6e946a04a814719c7c95abef7b5"},"schema_version":"1.0","source":{"id":"2401.14019","kind":"arxiv","version":1}},"canonical_sha256":"2eb2b864d7c9b0b9c9bcead6bf095b4893ffb147ff26bae178b697b0be63da6c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2eb2b864d7c9b0b9c9bcead6bf095b4893ffb147ff26bae178b697b0be63da6c","first_computed_at":"2026-07-05T07:37:21.012677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:37:21.012677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ai7efFzl+kOnAB82pq2fMnhmr2NOUQ6TwKJd1XuBqFTD7uITSSaFX53KRCUZdsQ1XeFbY3Ca/5G5DEafEK/qBA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:37:21.013208Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.14019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:82ce60b46bce69f2f5fdb2c8c5ce3cd7671408f9916708ce29ad6b330812e159","sha256:691fb0866947e3990cb40cbcd4050a094678c46e2b737fdb11cd31f6d5126788"],"state_sha256":"1f3f2a790f62cf2bc9644c463cf249c9aa996acdd6bee9d187199c05907cb46c"}