{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:4AY2SK4VA2WWMBJDAOSLUYP7SB","short_pith_number":"pith:4AY2SK4V","canonical_record":{"source":{"id":"2412.20382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T07:02:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"88d1e3cccf6780991430d10e0e3c56d49266ada33eff7569af7715440b3ed06b","abstract_canon_sha256":"a2daec6651129b1d30d58030f7f1430ccfd9767f9f36f880339494dd46e1e945"},"schema_version":"1.0"},"canonical_sha256":"e031a92b9506ad66052303a4ba61ff9042c0b6b8feb35f8579ad044a388f2432","source":{"kind":"arxiv","id":"2412.20382","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20382","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20382v1","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20382","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"4AY2SK4VA2WW","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_16","alias_value":"4AY2SK4VA2WWMBJD","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_8","alias_value":"4AY2SK4V","created_at":"2026-07-05T09:54:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:4AY2SK4VA2WWMBJDAOSLUYP7SB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.20382","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T07:02:45Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"88d1e3cccf6780991430d10e0e3c56d49266ada33eff7569af7715440b3ed06b","abstract_canon_sha256":"a2daec6651129b1d30d58030f7f1430ccfd9767f9f36f880339494dd46e1e945"},"schema_version":"1.0"},"canonical_sha256":"e031a92b9506ad66052303a4ba61ff9042c0b6b8feb35f8579ad044a388f2432","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:54:58.526088Z","signature_b64":"zQ8AYDS57H1tAkLgpVikO/g4yVdeXHdPOlpTPzh6LEjrlDrJhK7YPJTSVPfVVLdbXYYoYoeLmFBPUWrLs17wBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e031a92b9506ad66052303a4ba61ff9042c0b6b8feb35f8579ad044a388f2432","last_reissued_at":"2026-07-05T09:54:58.525625Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:54:58.525625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.20382","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":"2026-07-05T09:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c0xxNnURi3t95N6tuz7PyCcSqOej4aNtTBRC791qAAWHFthVZzh4ckq0EQVEZ19GlzG/aoRZEmMMgM+R1sm3DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:12:58.465359Z"},"content_sha256":"de3e7efa40dcaab312ce590df0090a875dcbfe73b2ac667922a7f5ec533e45b9","schema_version":"1.0","event_id":"sha256:de3e7efa40dcaab312ce590df0090a875dcbfe73b2ac667922a7f5ec533e45b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:4AY2SK4VA2WWMBJDAOSLUYP7SB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Natural Language Fine-Tuning","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jia Liu, Long Hu, Min Chen, Yixue Hao, Yue Wang, Zhiqi Lin","submitted_at":"2024-12-29T07:02:45Z","abstract_excerpt":"Large language model fine-tuning techniques typically depend on extensive labeled data, external guidance, and feedback, such as human alignment, scalar rewards, and demonstration. However, in practical application, the scarcity of specific knowledge poses unprecedented challenges to existing fine-tuning techniques. In this paper, focusing on fine-tuning tasks in specific domains with limited data, we introduce Natural Language Fine-Tuning (NLFT), which utilizes natural language for fine-tuning for the first time. By leveraging the strong language comprehension capability of the target LM, NLF"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20382","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/2412.20382/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":"2026-07-05T09:54:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ldkKQVEiPGzefPG8Imp4srKd5NtToLjUZ9QbI45q3/75IPgFajPI+9YErI2dRmjO/xsCqbPaKENTT+o0HRPlBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T08:12:58.465937Z"},"content_sha256":"d639aa5f332cc4e316174171defca01949728a0c0235d860bb0459a58176df23","schema_version":"1.0","event_id":"sha256:d639aa5f332cc4e316174171defca01949728a0c0235d860bb0459a58176df23"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4AY2SK4VA2WWMBJDAOSLUYP7SB/bundle.json","state_url":"https://pith.science/pith/4AY2SK4VA2WWMBJDAOSLUYP7SB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4AY2SK4VA2WWMBJDAOSLUYP7SB/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":"2026-08-11T08:12:58Z","links":{"resolver":"https://pith.science/pith/4AY2SK4VA2WWMBJDAOSLUYP7SB","bundle":"https://pith.science/pith/4AY2SK4VA2WWMBJDAOSLUYP7SB/bundle.json","state":"https://pith.science/pith/4AY2SK4VA2WWMBJDAOSLUYP7SB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4AY2SK4VA2WWMBJDAOSLUYP7SB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4AY2SK4VA2WWMBJDAOSLUYP7SB","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":"a2daec6651129b1d30d58030f7f1430ccfd9767f9f36f880339494dd46e1e945","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T07:02:45Z","title_canon_sha256":"88d1e3cccf6780991430d10e0e3c56d49266ada33eff7569af7715440b3ed06b"},"schema_version":"1.0","source":{"id":"2412.20382","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.20382","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"arxiv_version","alias_value":"2412.20382v1","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.20382","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_12","alias_value":"4AY2SK4VA2WW","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_16","alias_value":"4AY2SK4VA2WWMBJD","created_at":"2026-07-05T09:54:58Z"},{"alias_kind":"pith_short_8","alias_value":"4AY2SK4V","created_at":"2026-07-05T09:54:58Z"}],"graph_snapshots":[{"event_id":"sha256:d639aa5f332cc4e316174171defca01949728a0c0235d860bb0459a58176df23","target":"graph","created_at":"2026-07-05T09:54:58Z","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/2412.20382/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language model fine-tuning techniques typically depend on extensive labeled data, external guidance, and feedback, such as human alignment, scalar rewards, and demonstration. However, in practical application, the scarcity of specific knowledge poses unprecedented challenges to existing fine-tuning techniques. In this paper, focusing on fine-tuning tasks in specific domains with limited data, we introduce Natural Language Fine-Tuning (NLFT), which utilizes natural language for fine-tuning for the first time. By leveraging the strong language comprehension capability of the target LM, NLF","authors_text":"Jia Liu, Long Hu, Min Chen, Yixue Hao, Yue Wang, Zhiqi Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T07:02:45Z","title":"Natural Language Fine-Tuning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.20382","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:de3e7efa40dcaab312ce590df0090a875dcbfe73b2ac667922a7f5ec533e45b9","target":"record","created_at":"2026-07-05T09:54:58Z","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":"a2daec6651129b1d30d58030f7f1430ccfd9767f9f36f880339494dd46e1e945","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-29T07:02:45Z","title_canon_sha256":"88d1e3cccf6780991430d10e0e3c56d49266ada33eff7569af7715440b3ed06b"},"schema_version":"1.0","source":{"id":"2412.20382","kind":"arxiv","version":1}},"canonical_sha256":"e031a92b9506ad66052303a4ba61ff9042c0b6b8feb35f8579ad044a388f2432","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e031a92b9506ad66052303a4ba61ff9042c0b6b8feb35f8579ad044a388f2432","first_computed_at":"2026-07-05T09:54:58.525625Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:54:58.525625Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zQ8AYDS57H1tAkLgpVikO/g4yVdeXHdPOlpTPzh6LEjrlDrJhK7YPJTSVPfVVLdbXYYoYoeLmFBPUWrLs17wBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:54:58.526088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.20382","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de3e7efa40dcaab312ce590df0090a875dcbfe73b2ac667922a7f5ec533e45b9","sha256:d639aa5f332cc4e316174171defca01949728a0c0235d860bb0459a58176df23"],"state_sha256":"f397820f736fce885d30d52574ef6dad5535e3c77c28da208801d11e26370d1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8SQHKnUF8Ho2b2pa0R+UmSquLQiaAa+wlYQolW4s9hjIPrGU4F4yO+ZGd2w7VPfrtRovxDGwu5VIFUYFpMKpCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T08:12:58.471303Z","bundle_sha256":"942e25f68528f34f7e607c585291b0d559e3aa5d5436e8f20c80e5053f3ef135"}}