{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5V4IJFRK5QCAKRNHZDUCQOOHIG","short_pith_number":"pith:5V4IJFRK","canonical_record":{"source":{"id":"2410.14745","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T16:59:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"284cef47ec7bb1793f2fec8619c0276abac649662915da5d115cd2bd9e0d3b3b","abstract_canon_sha256":"dd53ebbd0f6d5d0b46bc441610126042e643cf465dc831101b4768533dafeac5"},"schema_version":"1.0"},"canonical_sha256":"ed7884962aec040545a7c8e82839c7419ee145456cc87bbd8e0a4a72a3e5a765","source":{"kind":"arxiv","id":"2410.14745","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14745","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14745v2","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14745","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"5V4IJFRK5QCA","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"5V4IJFRK5QCAKRNH","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"5V4IJFRK","created_at":"2026-07-05T10:16:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5V4IJFRK5QCAKRNHZDUCQOOHIG","target":"record","payload":{"canonical_record":{"source":{"id":"2410.14745","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T16:59:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"284cef47ec7bb1793f2fec8619c0276abac649662915da5d115cd2bd9e0d3b3b","abstract_canon_sha256":"dd53ebbd0f6d5d0b46bc441610126042e643cf465dc831101b4768533dafeac5"},"schema_version":"1.0"},"canonical_sha256":"ed7884962aec040545a7c8e82839c7419ee145456cc87bbd8e0a4a72a3e5a765","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:59.164021Z","signature_b64":"bpYPCDFqMPjcQ08xDMRYCGIfj79c2x4aT/YUoFAoei9YjUtRSOAVOyze2CIzUdFzgIHvZ1y1MEXD/3FBJKmSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ed7884962aec040545a7c8e82839c7419ee145456cc87bbd8e0a4a72a3e5a765","last_reissued_at":"2026-07-05T10:16:59.163602Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:59.163602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.14745","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L7o1AVjsVUiwH+XgWXmyn2Bo6cj9c94/o5qNzNklmUZLeKcNTaj6P7nr4ouRdnidVLqQBA+X1OqfwPUXJtVUAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:26:37.884681Z"},"content_sha256":"1ef67331f8e9a69c8d993c6a5072cffaac852d721862e6b45b7407086399abd2","schema_version":"1.0","event_id":"sha256:1ef67331f8e9a69c8d993c6a5072cffaac852d721862e6b45b7407086399abd2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5V4IJFRK5QCAKRNHZDUCQOOHIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Semi-supervised Fine-tuning for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Junyu Luo, Ming Zhang, Wei Ju, Xiao Luo, Xiusi Chen, Zhiping Xiao","submitted_at":"2024-10-17T16:59:46Z","abstract_excerpt":"Supervised fine-tuning (SFT) is crucial in adapting large language model (LLMs) to a specific domain or task. However, only a limited amount of labeled data is available in practical applications, which poses a severe challenge for SFT in yielding satisfactory results. Therefore, a data-efficient framework that can fully exploit labeled and unlabeled data for LLM fine-tuning is highly anticipated.Towards this end, we introduce a semi-supervised fine-tuning(SemiFT) task and a framework named SemiEvol for LLM alignment from a propagate-and-select manner. For knowledge propagation, SemiEvol adopt"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14745","kind":"arxiv","version":2},"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/2410.14745/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":"2026-07-05T10:16:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FmmuwNpVBoEDTusg4LE5rorlvoAyh0P/sEeXwUJjrEur684kpZTYWR7Q6+TMe0oDOwwaSHnY3BALelR9AwI5Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T23:26:37.885633Z"},"content_sha256":"5f430feb4cd90d5b9e0953a1907361f3f39687127df6235381c87db660dfa68a","schema_version":"1.0","event_id":"sha256:5f430feb4cd90d5b9e0953a1907361f3f39687127df6235381c87db660dfa68a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/bundle.json","state_url":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/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":"2026-08-17T23:26:37Z","links":{"resolver":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG","bundle":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/bundle.json","state":"https://pith.science/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5V4IJFRK5QCAKRNHZDUCQOOHIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5V4IJFRK5QCAKRNHZDUCQOOHIG","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":"dd53ebbd0f6d5d0b46bc441610126042e643cf465dc831101b4768533dafeac5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T16:59:46Z","title_canon_sha256":"284cef47ec7bb1793f2fec8619c0276abac649662915da5d115cd2bd9e0d3b3b"},"schema_version":"1.0","source":{"id":"2410.14745","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14745","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14745v2","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14745","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_12","alias_value":"5V4IJFRK5QCA","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_16","alias_value":"5V4IJFRK5QCAKRNH","created_at":"2026-07-05T10:16:59Z"},{"alias_kind":"pith_short_8","alias_value":"5V4IJFRK","created_at":"2026-07-05T10:16:59Z"}],"graph_snapshots":[{"event_id":"sha256:5f430feb4cd90d5b9e0953a1907361f3f39687127df6235381c87db660dfa68a","target":"graph","created_at":"2026-07-05T10:16:59Z","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/2410.14745/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised fine-tuning (SFT) is crucial in adapting large language model (LLMs) to a specific domain or task. However, only a limited amount of labeled data is available in practical applications, which poses a severe challenge for SFT in yielding satisfactory results. Therefore, a data-efficient framework that can fully exploit labeled and unlabeled data for LLM fine-tuning is highly anticipated.Towards this end, we introduce a semi-supervised fine-tuning(SemiFT) task and a framework named SemiEvol for LLM alignment from a propagate-and-select manner. For knowledge propagation, SemiEvol adopt","authors_text":"Junyu Luo, Ming Zhang, Wei Ju, Xiao Luo, Xiusi Chen, Zhiping Xiao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T16:59:46Z","title":"Semi-supervised Fine-tuning for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14745","kind":"arxiv","version":2},"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":"sha256:1ef67331f8e9a69c8d993c6a5072cffaac852d721862e6b45b7407086399abd2","target":"record","created_at":"2026-07-05T10:16:59Z","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":"dd53ebbd0f6d5d0b46bc441610126042e643cf465dc831101b4768533dafeac5","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-17T16:59:46Z","title_canon_sha256":"284cef47ec7bb1793f2fec8619c0276abac649662915da5d115cd2bd9e0d3b3b"},"schema_version":"1.0","source":{"id":"2410.14745","kind":"arxiv","version":2}},"canonical_sha256":"ed7884962aec040545a7c8e82839c7419ee145456cc87bbd8e0a4a72a3e5a765","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ed7884962aec040545a7c8e82839c7419ee145456cc87bbd8e0a4a72a3e5a765","first_computed_at":"2026-07-05T10:16:59.163602Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:16:59.163602Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bpYPCDFqMPjcQ08xDMRYCGIfj79c2x4aT/YUoFAoei9YjUtRSOAVOyze2CIzUdFzgIHvZ1y1MEXD/3FBJKmSBw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:16:59.164021Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14745","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1ef67331f8e9a69c8d993c6a5072cffaac852d721862e6b45b7407086399abd2","sha256:5f430feb4cd90d5b9e0953a1907361f3f39687127df6235381c87db660dfa68a"],"state_sha256":"5b11ba2989dcc1348b3555e47f9cb8f1e005e1d54b64d1ef490d5b2b968a0a91"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Wus4MarNQh3Dm9chyr5pyEJwU3Q+HtRUe63gDc9I/QFt/x9YaS6ZbFjfijq4aInTnoxnRwVihKCmX6lx3NzuBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T23:26:37.973892Z","bundle_sha256":"1df4cb7333d4052d70521482b4bf199d62b4f651f619978f4f42f2c1ea21f0dc"}}