{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YIWNUTXUYAH3MLDDTCKS2QCGYC","short_pith_number":"pith:YIWNUTXU","schema_version":"1.0","canonical_sha256":"c22cda4ef4c00fb62c6398952d4046c0b0a2fa6bf394507ebb9653a5097a9626","source":{"kind":"arxiv","id":"2507.04009","version":1},"attestation_state":"computed","paper":{"title":"Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jingyuan Wang, Qiyu Sun, Richong Zhang, Shiqi Li, Yaowei Zheng, Yuchen Gong, Ziyang Miao","submitted_at":"2025-07-05T11:38:59Z","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 "},"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":"2507.04009","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-05T11:38:59Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"f95d2efd690b0c17be9b5fdc93c0c426bb1c599787e180a97ddb6776a8aaffaf","abstract_canon_sha256":"e6a16e1d82d00bb4cdffc59a613d73948aabcafd00217c4d5bf9888d1c2c635b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:40.762871Z","signature_b64":"2QA8tEHGk1XG3FtqRh0cKMgtAaaZWy7PbecF0iDLFIeUUpEUcCL8t15HwPnlc6R5QtNNC9gkh7MmJ714EIc7BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c22cda4ef4c00fb62c6398952d4046c0b0a2fa6bf394507ebb9653a5097a9626","last_reissued_at":"2026-07-05T11:32:40.762402Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:40.762402Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Easy Dataset: A Unified and Extensible Framework for Synthesizing LLM Fine-Tuning Data from Unstructured Documents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jingyuan Wang, Qiyu Sun, Richong Zhang, Shiqi Li, Yaowei Zheng, Yuchen Gong, Ziyang Miao","submitted_at":"2025-07-05T11:38:59Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.04009","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/2507.04009/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":"2507.04009","created_at":"2026-07-05T11:32:40.762465+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.04009v1","created_at":"2026-07-05T11:32:40.762465+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.04009","created_at":"2026-07-05T11:32:40.762465+00:00"},{"alias_kind":"pith_short_12","alias_value":"YIWNUTXUYAH3","created_at":"2026-07-05T11:32:40.762465+00:00"},{"alias_kind":"pith_short_16","alias_value":"YIWNUTXUYAH3MLDD","created_at":"2026-07-05T11:32:40.762465+00:00"},{"alias_kind":"pith_short_8","alias_value":"YIWNUTXU","created_at":"2026-07-05T11:32:40.762465+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.02906","citing_title":"OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02906","citing_title":"OpsLLM: Construction of Large Language Model for Software Operations with Multi-stage Learning","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YIWNUTXUYAH3MLDDTCKS2QCGYC","json":"https://pith.science/pith/YIWNUTXUYAH3MLDDTCKS2QCGYC.json","graph_json":"https://pith.science/api/pith-number/YIWNUTXUYAH3MLDDTCKS2QCGYC/graph.json","events_json":"https://pith.science/api/pith-number/YIWNUTXUYAH3MLDDTCKS2QCGYC/events.json","paper":"https://pith.science/paper/YIWNUTXU"},"agent_actions":{"view_html":"https://pith.science/pith/YIWNUTXUYAH3MLDDTCKS2QCGYC","download_json":"https://pith.science/pith/YIWNUTXUYAH3MLDDTCKS2QCGYC.json","view_paper":"https://pith.science/paper/YIWNUTXU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.04009&json=true","fetch_graph":"https://pith.science/api/pith-number/YIWNUTXUYAH3MLDDTCKS2QCGYC/graph.json","fetch_events":"https://pith.science/api/pith-number/YIWNUTXUYAH3MLDDTCKS2QCGYC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YIWNUTXUYAH3MLDDTCKS2QCGYC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YIWNUTXUYAH3MLDDTCKS2QCGYC/action/storage_attestation","attest_author":"https://pith.science/pith/YIWNUTXUYAH3MLDDTCKS2QCGYC/action/author_attestation","sign_citation":"https://pith.science/pith/YIWNUTXUYAH3MLDDTCKS2QCGYC/action/citation_signature","submit_replication":"https://pith.science/pith/YIWNUTXUYAH3MLDDTCKS2QCGYC/action/replication_record"}},"created_at":"2026-07-05T11:32:40.762465+00:00","updated_at":"2026-07-05T11:32:40.762465+00:00"}