{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:SFZJRUGBV3ZB4ZUYVGKOB6C5YK","short_pith_number":"pith:SFZJRUGB","schema_version":"1.0","canonical_sha256":"917298d0c1aef21e6698a994e0f85dc281f9993a957c990bd1a71090403ad3f4","source":{"kind":"arxiv","id":"2407.08475","version":1},"attestation_state":"computed","paper":{"title":"Investigating Public Fine-Tuning Datasets: A Complex Review of Current Practices from a Construction Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fukai Shang, Runyuan Ma, Wei Li","submitted_at":"2024-07-11T13:11:16Z","abstract_excerpt":"With the rapid development of the large model domain, research related to fine-tuning has concurrently seen significant advancement, given that fine-tuning is a constituent part of the training process for large-scale models. Data engineering plays a fundamental role in the training process of models, which includes data infrastructure, data processing, etc. Data during fine-tuning likewise forms the base for large models. In order to embrace the power and explore new possibilities of fine-tuning datasets, this paper reviews current public fine-tuning datasets from the perspective of data cons"},"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":"2407.08475","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T13:11:16Z","cross_cats_sorted":[],"title_canon_sha256":"b233243e2de5dc2991ec9438ce9f112586a3c5e561db6e5d0be9bcab4c7b6a51","abstract_canon_sha256":"8fedbbd3e2916cd7f3685283cbfc4c63bc8906257f60f8f8d46502988214385f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:48.879409Z","signature_b64":"HQxgAc8ZlHRWSuiCpZ65cvybq4bJLTmBAoj3gGX6AO82WUdmOxR6qAASjLaWwJz/YAvzwgH6XIsxYX2gutKkDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"917298d0c1aef21e6698a994e0f85dc281f9993a957c990bd1a71090403ad3f4","last_reissued_at":"2026-07-05T08:42:48.878962Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:48.878962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Investigating Public Fine-Tuning Datasets: A Complex Review of Current Practices from a Construction Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fukai Shang, Runyuan Ma, Wei Li","submitted_at":"2024-07-11T13:11:16Z","abstract_excerpt":"With the rapid development of the large model domain, research related to fine-tuning has concurrently seen significant advancement, given that fine-tuning is a constituent part of the training process for large-scale models. Data engineering plays a fundamental role in the training process of models, which includes data infrastructure, data processing, etc. Data during fine-tuning likewise forms the base for large models. In order to embrace the power and explore new possibilities of fine-tuning datasets, this paper reviews current public fine-tuning datasets from the perspective of data cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08475","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/2407.08475/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":"2407.08475","created_at":"2026-07-05T08:42:48.879021+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.08475v1","created_at":"2026-07-05T08:42:48.879021+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08475","created_at":"2026-07-05T08:42:48.879021+00:00"},{"alias_kind":"pith_short_12","alias_value":"SFZJRUGBV3ZB","created_at":"2026-07-05T08:42:48.879021+00:00"},{"alias_kind":"pith_short_16","alias_value":"SFZJRUGBV3ZB4ZUY","created_at":"2026-07-05T08:42:48.879021+00:00"},{"alias_kind":"pith_short_8","alias_value":"SFZJRUGB","created_at":"2026-07-05T08:42:48.879021+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03527","citing_title":"MoKA: Mixture of Kronecker Adapters","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK","json":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK.json","graph_json":"https://pith.science/api/pith-number/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/graph.json","events_json":"https://pith.science/api/pith-number/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/events.json","paper":"https://pith.science/paper/SFZJRUGB"},"agent_actions":{"view_html":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK","download_json":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK.json","view_paper":"https://pith.science/paper/SFZJRUGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.08475&json=true","fetch_graph":"https://pith.science/api/pith-number/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/graph.json","fetch_events":"https://pith.science/api/pith-number/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/action/storage_attestation","attest_author":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/action/author_attestation","sign_citation":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/action/citation_signature","submit_replication":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/action/replication_record"}},"created_at":"2026-07-05T08:42:48.879021+00:00","updated_at":"2026-07-05T08:42:48.879021+00:00"}