{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Y7BSR5VZTDYMWJUCUW2CM54PUV","short_pith_number":"pith:Y7BSR5VZ","canonical_record":{"source":{"id":"2312.15603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T03:53:33Z","cross_cats_sorted":[],"title_canon_sha256":"89b02d9de18ae251409a43ee65b031409ab902829e1441738cf52ea9fcb18799","abstract_canon_sha256":"1f14b07e591d8abb7285909ffc424b06eb3fd070fb978b4a61f0451596e187fc"},"schema_version":"1.0"},"canonical_sha256":"c7c328f6b998f0cb2682a5b426778fa561d014034512c2d44cddecf233988f8a","source":{"kind":"arxiv","id":"2312.15603","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15603","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15603v1","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15603","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_12","alias_value":"Y7BSR5VZTDYM","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_16","alias_value":"Y7BSR5VZTDYMWJUC","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_8","alias_value":"Y7BSR5VZ","created_at":"2026-07-05T07:27:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Y7BSR5VZTDYMWJUCUW2CM54PUV","target":"record","payload":{"canonical_record":{"source":{"id":"2312.15603","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T03:53:33Z","cross_cats_sorted":[],"title_canon_sha256":"89b02d9de18ae251409a43ee65b031409ab902829e1441738cf52ea9fcb18799","abstract_canon_sha256":"1f14b07e591d8abb7285909ffc424b06eb3fd070fb978b4a61f0451596e187fc"},"schema_version":"1.0"},"canonical_sha256":"c7c328f6b998f0cb2682a5b426778fa561d014034512c2d44cddecf233988f8a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:27:58.500423Z","signature_b64":"5SBAxIIXEI5lEI8q3jm4Pxx1nMgJignr4XtkHvX/YWurIGqRiURMflgtVdvOzRJAIQIHVFNIwRVvpnqOTJ6pDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7c328f6b998f0cb2682a5b426778fa561d014034512c2d44cddecf233988f8a","last_reissued_at":"2026-07-05T07:27:58.499927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:27:58.499927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.15603","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":"2026-07-05T07:27:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ug0NLz6GmSr1Sp+QSERMZqYCSBHnAUE9+kC7hFh04J8/gGPaAw0Jrd6K50ygsnHhq/UR1+AnMnzVMjJJYqCNDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:47:42.401911Z"},"content_sha256":"911196ec37fb130c5a587142569137792f0d1ee7212cd08e6bcffbc97ecfef5d","schema_version":"1.0","event_id":"sha256:911196ec37fb130c5a587142569137792f0d1ee7212cd08e6bcffbc97ecfef5d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Y7BSR5VZTDYMWJUCUW2CM54PUV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Split-and-Privatize Framework for Large Language Model Fine-Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Duan, Di Wu, Huiqi Liu, Jue Hong, Xicong Shen, Yang Liu, Ye Wu, Yunlong Mao, Zirui Huang","submitted_at":"2023-12-25T03:53:33Z","abstract_excerpt":"Fine-tuning is a prominent technique to adapt a pre-trained language model to downstream scenarios. In parameter-efficient fine-tuning, only a small subset of modules are trained over the downstream datasets, while leaving the rest of the pre-trained model frozen to save computation resources. In recent years, a popular productization form arises as Model-as-a-Service (MaaS), in which vendors provide abundant pre-trained language models, server resources and core functions, and customers can fine-tune, deploy and invoke their customized model by accessing the one-stop MaaS with their own priva"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15603","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/2312.15603/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":"2026-07-05T07:27:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKatIipzna8wabOX4zRvNIdbYDeN9Mz+2UiVpP0zwuH+rrSmRg4bxn570zSNGKKZzRkm2RF5UJNfx3uKDo2yBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T08:47:42.402819Z"},"content_sha256":"6edf9ad1c64a10a3506c7477594ba3a82ede5b365840d338e9e62a356e76c7c8","schema_version":"1.0","event_id":"sha256:6edf9ad1c64a10a3506c7477594ba3a82ede5b365840d338e9e62a356e76c7c8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7BSR5VZTDYMWJUCUW2CM54PUV/bundle.json","state_url":"https://pith.science/pith/Y7BSR5VZTDYMWJUCUW2CM54PUV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7BSR5VZTDYMWJUCUW2CM54PUV/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":"2026-08-10T08:47:42Z","links":{"resolver":"https://pith.science/pith/Y7BSR5VZTDYMWJUCUW2CM54PUV","bundle":"https://pith.science/pith/Y7BSR5VZTDYMWJUCUW2CM54PUV/bundle.json","state":"https://pith.science/pith/Y7BSR5VZTDYMWJUCUW2CM54PUV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7BSR5VZTDYMWJUCUW2CM54PUV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Y7BSR5VZTDYMWJUCUW2CM54PUV","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":"1f14b07e591d8abb7285909ffc424b06eb3fd070fb978b4a61f0451596e187fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T03:53:33Z","title_canon_sha256":"89b02d9de18ae251409a43ee65b031409ab902829e1441738cf52ea9fcb18799"},"schema_version":"1.0","source":{"id":"2312.15603","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.15603","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"arxiv_version","alias_value":"2312.15603v1","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.15603","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_12","alias_value":"Y7BSR5VZTDYM","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_16","alias_value":"Y7BSR5VZTDYMWJUC","created_at":"2026-07-05T07:27:58Z"},{"alias_kind":"pith_short_8","alias_value":"Y7BSR5VZ","created_at":"2026-07-05T07:27:58Z"}],"graph_snapshots":[{"event_id":"sha256:6edf9ad1c64a10a3506c7477594ba3a82ede5b365840d338e9e62a356e76c7c8","target":"graph","created_at":"2026-07-05T07:27:58Z","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/2312.15603/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning is a prominent technique to adapt a pre-trained language model to downstream scenarios. In parameter-efficient fine-tuning, only a small subset of modules are trained over the downstream datasets, while leaving the rest of the pre-trained model frozen to save computation resources. In recent years, a popular productization form arises as Model-as-a-Service (MaaS), in which vendors provide abundant pre-trained language models, server resources and core functions, and customers can fine-tune, deploy and invoke their customized model by accessing the one-stop MaaS with their own priva","authors_text":"Bing Duan, Di Wu, Huiqi Liu, Jue Hong, Xicong Shen, Yang Liu, Ye Wu, Yunlong Mao, Zirui Huang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T03:53:33Z","title":"A Split-and-Privatize Framework for Large Language Model Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.15603","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":"sha256:911196ec37fb130c5a587142569137792f0d1ee7212cd08e6bcffbc97ecfef5d","target":"record","created_at":"2026-07-05T07:27:58Z","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":"1f14b07e591d8abb7285909ffc424b06eb3fd070fb978b4a61f0451596e187fc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-12-25T03:53:33Z","title_canon_sha256":"89b02d9de18ae251409a43ee65b031409ab902829e1441738cf52ea9fcb18799"},"schema_version":"1.0","source":{"id":"2312.15603","kind":"arxiv","version":1}},"canonical_sha256":"c7c328f6b998f0cb2682a5b426778fa561d014034512c2d44cddecf233988f8a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7c328f6b998f0cb2682a5b426778fa561d014034512c2d44cddecf233988f8a","first_computed_at":"2026-07-05T07:27:58.499927Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:27:58.499927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5SBAxIIXEI5lEI8q3jm4Pxx1nMgJignr4XtkHvX/YWurIGqRiURMflgtVdvOzRJAIQIHVFNIwRVvpnqOTJ6pDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:27:58.500423Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.15603","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:911196ec37fb130c5a587142569137792f0d1ee7212cd08e6bcffbc97ecfef5d","sha256:6edf9ad1c64a10a3506c7477594ba3a82ede5b365840d338e9e62a356e76c7c8"],"state_sha256":"38d8db90b246a714bc04934e2d25c65716f78372dbd9085c7e33bfd378f2fe26"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gfJT6Q54syDUGSmfROti54JOZGEoDSi5irQcdTBpmsYVkV1nWA1I9z8ms2uZ/vRu/BGvGYEP9jyUTxw9O40oDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T08:47:42.410449Z","bundle_sha256":"39d43fba2979b4bfe037a659b6725cbabf7e878150d743e10a0bed4e710d687b"}}