{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:SFZJRUGBV3ZB4ZUYVGKOB6C5YK","short_pith_number":"pith:SFZJRUGB","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"},"canonical_sha256":"917298d0c1aef21e6698a994e0f85dc281f9993a957c990bd1a71090403ad3f4","source":{"kind":"arxiv","id":"2407.08475","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08475","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08475v1","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08475","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"pith_short_12","alias_value":"SFZJRUGBV3ZB","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"pith_short_16","alias_value":"SFZJRUGBV3ZB4ZUY","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"pith_short_8","alias_value":"SFZJRUGB","created_at":"2026-07-05T08:42:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:SFZJRUGBV3ZB4ZUYVGKOB6C5YK","target":"record","payload":{"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"},"canonical_sha256":"917298d0c1aef21e6698a994e0f85dc281f9993a957c990bd1a71090403ad3f4","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"},"source_kind":"arxiv","source_id":"2407.08475","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/Fd8Y7eRIegitSUYB8LdbD5UGsmcwKdGF44mr0nrRY7Cx8XYQo1jL0BvjXBfQMZCu0FPMmhkNQCiG09m/rg/BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:08:31.924897Z"},"content_sha256":"b735420b3ff949868494f710830b4a5de9edfb67d2b5a8f9a8df209ddaf961f8","schema_version":"1.0","event_id":"sha256:b735420b3ff949868494f710830b4a5de9edfb67d2b5a8f9a8df209ddaf961f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:SFZJRUGBV3ZB4ZUYVGKOB6C5YK","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:42:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zB8v1F1U6QLbqlvgAiyL4zhchwrD2SMZ1F1VDzLeKMI27a4F6IgPRkVLaK0xVNMk9w62dO99TxKJGf02tBPPCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:08:31.925450Z"},"content_sha256":"1fa5ca7c839f199129e6b7f7e12f73e8b02c7d888d8905137ea52a4e0b0b3d70","schema_version":"1.0","event_id":"sha256:1fa5ca7c839f199129e6b7f7e12f73e8b02c7d888d8905137ea52a4e0b0b3d70"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/bundle.json","state_url":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-12T13:08:31Z","links":{"resolver":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK","bundle":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/bundle.json","state":"https://pith.science/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SFZJRUGBV3ZB4ZUYVGKOB6C5YK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:SFZJRUGBV3ZB4ZUYVGKOB6C5YK","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":"8fedbbd3e2916cd7f3685283cbfc4c63bc8906257f60f8f8d46502988214385f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T13:11:16Z","title_canon_sha256":"b233243e2de5dc2991ec9438ce9f112586a3c5e561db6e5d0be9bcab4c7b6a51"},"schema_version":"1.0","source":{"id":"2407.08475","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08475","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08475v1","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08475","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"pith_short_12","alias_value":"SFZJRUGBV3ZB","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"pith_short_16","alias_value":"SFZJRUGBV3ZB4ZUY","created_at":"2026-07-05T08:42:48Z"},{"alias_kind":"pith_short_8","alias_value":"SFZJRUGB","created_at":"2026-07-05T08:42:48Z"}],"graph_snapshots":[{"event_id":"sha256:1fa5ca7c839f199129e6b7f7e12f73e8b02c7d888d8905137ea52a4e0b0b3d70","target":"graph","created_at":"2026-07-05T08:42:48Z","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/2407.08475/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fukai Shang, Runyuan Ma, Wei Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T13:11:16Z","title":"Investigating Public Fine-Tuning Datasets: A Complex Review of Current Practices from a Construction Perspective"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08475","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:b735420b3ff949868494f710830b4a5de9edfb67d2b5a8f9a8df209ddaf961f8","target":"record","created_at":"2026-07-05T08:42:48Z","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":"8fedbbd3e2916cd7f3685283cbfc4c63bc8906257f60f8f8d46502988214385f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-11T13:11:16Z","title_canon_sha256":"b233243e2de5dc2991ec9438ce9f112586a3c5e561db6e5d0be9bcab4c7b6a51"},"schema_version":"1.0","source":{"id":"2407.08475","kind":"arxiv","version":1}},"canonical_sha256":"917298d0c1aef21e6698a994e0f85dc281f9993a957c990bd1a71090403ad3f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"917298d0c1aef21e6698a994e0f85dc281f9993a957c990bd1a71090403ad3f4","first_computed_at":"2026-07-05T08:42:48.878962Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:48.878962Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HQxgAc8ZlHRWSuiCpZ65cvybq4bJLTmBAoj3gGX6AO82WUdmOxR6qAASjLaWwJz/YAvzwgH6XIsxYX2gutKkDA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:48.879409Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08475","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b735420b3ff949868494f710830b4a5de9edfb67d2b5a8f9a8df209ddaf961f8","sha256:1fa5ca7c839f199129e6b7f7e12f73e8b02c7d888d8905137ea52a4e0b0b3d70"],"state_sha256":"fddf730144a7ca9319578ea7db784c04fce415414ae8e5fa0b259ac8dba01eeb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t7dmIJaJvQXjAAFysl+MekP5/RHXbk/9w2hRJWKK6JJWm1icS+RZduwEfgOSCKp8C0wv2PzOihFnBB1dWbRqBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:08:31.930633Z","bundle_sha256":"0792502a21541028acd2a4a5e71bee5c67693d61f2b8a1a28d5a88295702d69c"}}