{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YIWNUTXUYAH3MLDDTCKS2QCGYC","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":"e6a16e1d82d00bb4cdffc59a613d73948aabcafd00217c4d5bf9888d1c2c635b","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-05T11:38:59Z","title_canon_sha256":"f95d2efd690b0c17be9b5fdc93c0c426bb1c599787e180a97ddb6776a8aaffaf"},"schema_version":"1.0","source":{"id":"2507.04009","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.04009","created_at":"2026-07-05T11:32:40Z"},{"alias_kind":"arxiv_version","alias_value":"2507.04009v1","created_at":"2026-07-05T11:32:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04009","created_at":"2026-07-05T11:32:40Z"},{"alias_kind":"pith_short_12","alias_value":"YIWNUTXUYAH3","created_at":"2026-07-05T11:32:40Z"},{"alias_kind":"pith_short_16","alias_value":"YIWNUTXUYAH3MLDD","created_at":"2026-07-05T11:32:40Z"},{"alias_kind":"pith_short_8","alias_value":"YIWNUTXU","created_at":"2026-07-05T11:32:40Z"}],"graph_snapshots":[{"event_id":"sha256:c9396a0c3857214fef88e916d1c16534c32e24c13d245fc8901714e6b9558a92","target":"graph","created_at":"2026-07-05T11:32:40Z","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/2507.04009/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have shown impressive performance on general-purpose tasks, yet adapting them to specific domains remains challenging due to the scarcity of high-quality domain data. Existing data synthesis tools often struggle to extract reliable fine-tuning data from heterogeneous documents effectively. To address this limitation, we propose Easy Dataset, a unified framework for synthesizing fine-tuning data from unstructured documents via an intuitive graphical user interface (GUI). Specifically, Easy Dataset allows users to easily configure text extraction models and chunking ","authors_text":"Jingyuan Wang, Qiyu Sun, Richong Zhang, Shiqi Li, Yaowei Zheng, Yuchen Gong, Ziyang Miao","cross_cats":["cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-05T11:38:59Z","title":"Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04009","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:dfdb86a7ec2df25b2eb5da3c2e6bcf64e575560351c608146b3817ae9a4bf83e","target":"record","created_at":"2026-07-05T11:32:40Z","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":"e6a16e1d82d00bb4cdffc59a613d73948aabcafd00217c4d5bf9888d1c2c635b","cross_cats_sorted":["cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-05T11:38:59Z","title_canon_sha256":"f95d2efd690b0c17be9b5fdc93c0c426bb1c599787e180a97ddb6776a8aaffaf"},"schema_version":"1.0","source":{"id":"2507.04009","kind":"arxiv","version":1}},"canonical_sha256":"c22cda4ef4c00fb62c6398952d4046c0b0a2fa6bf394507ebb9653a5097a9626","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c22cda4ef4c00fb62c6398952d4046c0b0a2fa6bf394507ebb9653a5097a9626","first_computed_at":"2026-07-05T11:32:40.762402Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:40.762402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2QA8tEHGk1XG3FtqRh0cKMgtAaaZWy7PbecF0iDLFIeUUpEUcCL8t15HwPnlc6R5QtNNC9gkh7MmJ714EIc7BA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:40.762871Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.04009","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dfdb86a7ec2df25b2eb5da3c2e6bcf64e575560351c608146b3817ae9a4bf83e","sha256:c9396a0c3857214fef88e916d1c16534c32e24c13d245fc8901714e6b9558a92"],"state_sha256":"d72c8a8d37b135883a95c0effb508769cbf320a09942c04abd100dec37238fad"}