{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:76Z5JZS3RVCOBYZGCUMHLW7SF2","short_pith_number":"pith:76Z5JZS3","canonical_record":{"source":{"id":"2505.17470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:50:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"28534317ec710c7d1f3213c59a6d5b8a87f8ed35840f3d51fbc5203f98a023cb","abstract_canon_sha256":"d3696da6bb67837fcbb6f9679cf1218582c5b18d12c71cef118998fce6e8e59d"},"schema_version":"1.0"},"canonical_sha256":"ffb3d4e65b8d44e0e326151875dbf22ea5892778a11e6fe8c463e6209bfa903d","source":{"kind":"arxiv","id":"2505.17470","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17470","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17470v1","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17470","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"76Z5JZS3RVCO","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"76Z5JZS3RVCOBYZG","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"76Z5JZS3","created_at":"2026-07-05T11:08:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:76Z5JZS3RVCOBYZGCUMHLW7SF2","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17470","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:50:54Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"28534317ec710c7d1f3213c59a6d5b8a87f8ed35840f3d51fbc5203f98a023cb","abstract_canon_sha256":"d3696da6bb67837fcbb6f9679cf1218582c5b18d12c71cef118998fce6e8e59d"},"schema_version":"1.0"},"canonical_sha256":"ffb3d4e65b8d44e0e326151875dbf22ea5892778a11e6fe8c463e6209bfa903d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:08:26.575164Z","signature_b64":"r6T8jpsyPAhaYGU4Deyu9Gidnt/s+lwW3jGtdb2ppPwi9Wt5IXJKcUeGotmZoeC0l/d/kpzBf0V8X7cTc+C7Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffb3d4e65b8d44e0e326151875dbf22ea5892778a11e6fe8c463e6209bfa903d","last_reissued_at":"2026-07-05T11:08:26.574761Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:08:26.574761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17470","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":"2026-07-05T11:08:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"By0lh9uTsU5RmN932T4mClEDukPlq2294FxuElILKYBm84ucZpNFgX8wPFCb+8ggVIWbX0DcdruH6pXETckfCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:16:15.922201Z"},"content_sha256":"4a0ea77f256b2e508960934b96655bbfbe4483f0ba43f4b652b1400a19adca1d","schema_version":"1.0","event_id":"sha256:4a0ea77f256b2e508960934b96655bbfbe4483f0ba43f4b652b1400a19adca1d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:76Z5JZS3RVCOBYZGCUMHLW7SF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SLearnLLM: A Self-Learning Framework for Efficient Domain-Specific Adaptation of Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Huan Hu, Kai Wang, Kohou Wang, Peng Wang, Shiguo Lian, Xiang Liu, Zhaoxiang Liu","submitted_at":"2025-05-23T04:50:54Z","abstract_excerpt":"When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on the entire dataset due to limited information on the LLM's past training data. However, if the SFT dataset largely overlaps with the model's existing knowledge, the performance gains are minimal, leading to wasted computational resources. Identifying the unknown knowledge within the SFT dataset and using it to fine-tune the model could substantially improve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17470","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/2505.17470/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":"2026-07-05T11:08:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1cWkNJbR5WCuF+CMz2sC6OWFCu/erGir+R7K4Ml90LWIerWY95WX5/U6j1oXoBNbBuBqRSQuCgbVr1jVXkjHAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T12:16:15.923124Z"},"content_sha256":"18f460cf31f84314048fb6a328f20567c528d52f6bbbd275303709d9a5904a47","schema_version":"1.0","event_id":"sha256:18f460cf31f84314048fb6a328f20567c528d52f6bbbd275303709d9a5904a47"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/76Z5JZS3RVCOBYZGCUMHLW7SF2/bundle.json","state_url":"https://pith.science/pith/76Z5JZS3RVCOBYZGCUMHLW7SF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/76Z5JZS3RVCOBYZGCUMHLW7SF2/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":"2026-08-09T12:16:15Z","links":{"resolver":"https://pith.science/pith/76Z5JZS3RVCOBYZGCUMHLW7SF2","bundle":"https://pith.science/pith/76Z5JZS3RVCOBYZGCUMHLW7SF2/bundle.json","state":"https://pith.science/pith/76Z5JZS3RVCOBYZGCUMHLW7SF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/76Z5JZS3RVCOBYZGCUMHLW7SF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:76Z5JZS3RVCOBYZGCUMHLW7SF2","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":"d3696da6bb67837fcbb6f9679cf1218582c5b18d12c71cef118998fce6e8e59d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:50:54Z","title_canon_sha256":"28534317ec710c7d1f3213c59a6d5b8a87f8ed35840f3d51fbc5203f98a023cb"},"schema_version":"1.0","source":{"id":"2505.17470","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17470","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17470v1","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17470","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_12","alias_value":"76Z5JZS3RVCO","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_16","alias_value":"76Z5JZS3RVCOBYZG","created_at":"2026-07-05T11:08:26Z"},{"alias_kind":"pith_short_8","alias_value":"76Z5JZS3","created_at":"2026-07-05T11:08:26Z"}],"graph_snapshots":[{"event_id":"sha256:18f460cf31f84314048fb6a328f20567c528d52f6bbbd275303709d9a5904a47","target":"graph","created_at":"2026-07-05T11:08:26Z","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/2505.17470/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"When using supervised fine-tuning (SFT) to adapt large language models (LLMs) to specific domains, a significant challenge arises: should we use the entire SFT dataset for fine-tuning? Common practice often involves fine-tuning directly on the entire dataset due to limited information on the LLM's past training data. However, if the SFT dataset largely overlaps with the model's existing knowledge, the performance gains are minimal, leading to wasted computational resources. Identifying the unknown knowledge within the SFT dataset and using it to fine-tune the model could substantially improve ","authors_text":"Huan Hu, Kai Wang, Kohou Wang, Peng Wang, Shiguo Lian, Xiang Liu, Zhaoxiang Liu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:50:54Z","title":"SLearnLLM: A Self-Learning Framework for Efficient Domain-Specific Adaptation of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17470","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":"sha256:4a0ea77f256b2e508960934b96655bbfbe4483f0ba43f4b652b1400a19adca1d","target":"record","created_at":"2026-07-05T11:08:26Z","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":"d3696da6bb67837fcbb6f9679cf1218582c5b18d12c71cef118998fce6e8e59d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-05-23T04:50:54Z","title_canon_sha256":"28534317ec710c7d1f3213c59a6d5b8a87f8ed35840f3d51fbc5203f98a023cb"},"schema_version":"1.0","source":{"id":"2505.17470","kind":"arxiv","version":1}},"canonical_sha256":"ffb3d4e65b8d44e0e326151875dbf22ea5892778a11e6fe8c463e6209bfa903d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ffb3d4e65b8d44e0e326151875dbf22ea5892778a11e6fe8c463e6209bfa903d","first_computed_at":"2026-07-05T11:08:26.574761Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:08:26.574761Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r6T8jpsyPAhaYGU4Deyu9Gidnt/s+lwW3jGtdb2ppPwi9Wt5IXJKcUeGotmZoeC0l/d/kpzBf0V8X7cTc+C7Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:08:26.575164Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17470","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a0ea77f256b2e508960934b96655bbfbe4483f0ba43f4b652b1400a19adca1d","sha256:18f460cf31f84314048fb6a328f20567c528d52f6bbbd275303709d9a5904a47"],"state_sha256":"93b73727b06d07828d8fa00ab4413c2d5a5d8dd1622de4d7c4bd9ef3ee0081a7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"shgHzj/uuLVwHS5EcMp4ueSlbAUVOv8NEDjXm1PjWvsEomR0R0dxAJ0HkK5ZjEerczix6gxZD/EtWe+BplU4Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T12:16:15.929152Z","bundle_sha256":"e979c3bce8ff521eafa1485dabbf42efd9d0141246729e5c5eb79961130d8ec2"}}