{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UOF4TODXXHOE6AP42KHSBIVNMQ","short_pith_number":"pith:UOF4TODX","canonical_record":{"source":{"id":"2505.15480","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T12:55:28Z","cross_cats_sorted":[],"title_canon_sha256":"bf14e79ec72fb46a3343602d402299d3819f6d6b2d6871320cdab9abb466a190","abstract_canon_sha256":"4e07325b52e560fda99cf597905e13d043af598007921c528e08399b6c68a0a5"},"schema_version":"1.0"},"canonical_sha256":"a38bc9b877b9dc4f01fcd28f20a2ad640385be68f2ff6560ecc941c343087909","source":{"kind":"arxiv","id":"2505.15480","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15480","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15480v2","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15480","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"UOF4TODXXHOE","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"UOF4TODXXHOE6AP4","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"UOF4TODX","created_at":"2026-07-05T11:10:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UOF4TODXXHOE6AP42KHSBIVNMQ","target":"record","payload":{"canonical_record":{"source":{"id":"2505.15480","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T12:55:28Z","cross_cats_sorted":[],"title_canon_sha256":"bf14e79ec72fb46a3343602d402299d3819f6d6b2d6871320cdab9abb466a190","abstract_canon_sha256":"4e07325b52e560fda99cf597905e13d043af598007921c528e08399b6c68a0a5"},"schema_version":"1.0"},"canonical_sha256":"a38bc9b877b9dc4f01fcd28f20a2ad640385be68f2ff6560ecc941c343087909","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:57.274700Z","signature_b64":"oCjnEjmuD9g9SnbHV19GO+k4RQ1DAPmdU/ssyYuDDkFZoz4GRYySKgRZGqgBkcv/8brZmxGIrdqK9zStoDFBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a38bc9b877b9dc4f01fcd28f20a2ad640385be68f2ff6560ecc941c343087909","last_reissued_at":"2026-07-05T11:10:57.274184Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:57.274184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.15480","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":"2026-07-05T11:10:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5NQdpQBRbWUrLLFEsEA+6yuGTyS+Jz5NztCR+rSFsjx/cXJEOwzpsRis2e3QofS4k+meh4Mp2dFB9ZE1Z8FeCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:05:16.751674Z"},"content_sha256":"b5ac637463c44f85f4e67a0f9e408b7da53ade414f9b06bbc5b4484e058d68b3","schema_version":"1.0","event_id":"sha256:b5ac637463c44f85f4e67a0f9e408b7da53ade414f9b06bbc5b4484e058d68b3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UOF4TODXXHOE6AP42KHSBIVNMQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bo Du, Dacheng Tao, Juhua Liu, Liang Ding, Qihuang Zhong, Xiantao Cai","submitted_at":"2025-05-21T12:55:28Z","abstract_excerpt":"Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs). However, recent literature reveals that due to the conflicts between LLMs' internal knowledge and the context knowledge of training data, vanilla SFT using the full QA training set is usually suboptimal. In this paper, we first design a query diversification strategy for robust conflict detection and then conduct a series of experiments to analyze the impact of knowledge conflict. We find that 1) training samples with varied conflicts contribute "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15480","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/2505.15480/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":"2026-07-05T11:10:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DbC3ixR5ImH7eUIUJuMFFv6jfWVCpPSOO+Gqp57wkYIp+8tVk/FMdTthT0+cw3OD9eRxzVNpQk3bcmiXAwwIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:05:16.752564Z"},"content_sha256":"13b8b67fec3923c0e326c5a22a4667d430af8e7573b6b44051d0af3d8f9aa4af","schema_version":"1.0","event_id":"sha256:13b8b67fec3923c0e326c5a22a4667d430af8e7573b6b44051d0af3d8f9aa4af"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UOF4TODXXHOE6AP42KHSBIVNMQ/bundle.json","state_url":"https://pith.science/pith/UOF4TODXXHOE6AP42KHSBIVNMQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UOF4TODXXHOE6AP42KHSBIVNMQ/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":"2026-08-09T04:05:16Z","links":{"resolver":"https://pith.science/pith/UOF4TODXXHOE6AP42KHSBIVNMQ","bundle":"https://pith.science/pith/UOF4TODXXHOE6AP42KHSBIVNMQ/bundle.json","state":"https://pith.science/pith/UOF4TODXXHOE6AP42KHSBIVNMQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UOF4TODXXHOE6AP42KHSBIVNMQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UOF4TODXXHOE6AP42KHSBIVNMQ","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":"4e07325b52e560fda99cf597905e13d043af598007921c528e08399b6c68a0a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T12:55:28Z","title_canon_sha256":"bf14e79ec72fb46a3343602d402299d3819f6d6b2d6871320cdab9abb466a190"},"schema_version":"1.0","source":{"id":"2505.15480","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15480","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15480v2","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15480","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_12","alias_value":"UOF4TODXXHOE","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_16","alias_value":"UOF4TODXXHOE6AP4","created_at":"2026-07-05T11:10:57Z"},{"alias_kind":"pith_short_8","alias_value":"UOF4TODX","created_at":"2026-07-05T11:10:57Z"}],"graph_snapshots":[{"event_id":"sha256:13b8b67fec3923c0e326c5a22a4667d430af8e7573b6b44051d0af3d8f9aa4af","target":"graph","created_at":"2026-07-05T11:10:57Z","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/2505.15480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised fine-tuning (SFT) is a common approach to improve the domain-specific question-answering (QA) performance of large language models (LLMs). However, recent literature reveals that due to the conflicts between LLMs' internal knowledge and the context knowledge of training data, vanilla SFT using the full QA training set is usually suboptimal. In this paper, we first design a query diversification strategy for robust conflict detection and then conduct a series of experiments to analyze the impact of knowledge conflict. We find that 1) training samples with varied conflicts contribute ","authors_text":"Bo Du, Dacheng Tao, Juhua Liu, Liang Ding, Qihuang Zhong, Xiantao Cai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T12:55:28Z","title":"KaFT: Knowledge-aware Fine-tuning for Boosting LLMs' Domain-specific Question-Answering Performance"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15480","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:b5ac637463c44f85f4e67a0f9e408b7da53ade414f9b06bbc5b4484e058d68b3","target":"record","created_at":"2026-07-05T11:10:57Z","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":"4e07325b52e560fda99cf597905e13d043af598007921c528e08399b6c68a0a5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-21T12:55:28Z","title_canon_sha256":"bf14e79ec72fb46a3343602d402299d3819f6d6b2d6871320cdab9abb466a190"},"schema_version":"1.0","source":{"id":"2505.15480","kind":"arxiv","version":2}},"canonical_sha256":"a38bc9b877b9dc4f01fcd28f20a2ad640385be68f2ff6560ecc941c343087909","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a38bc9b877b9dc4f01fcd28f20a2ad640385be68f2ff6560ecc941c343087909","first_computed_at":"2026-07-05T11:10:57.274184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:10:57.274184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oCjnEjmuD9g9SnbHV19GO+k4RQ1DAPmdU/ssyYuDDkFZoz4GRYySKgRZGqgBkcv/8brZmxGIrdqK9zStoDFBAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:10:57.274700Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15480","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b5ac637463c44f85f4e67a0f9e408b7da53ade414f9b06bbc5b4484e058d68b3","sha256:13b8b67fec3923c0e326c5a22a4667d430af8e7573b6b44051d0af3d8f9aa4af"],"state_sha256":"3ce0aa0a6c955c9842311cd6b7f81f4fd97cb89e8c8f358d7d4980a9474810e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SFOT2RnCMl1902DwNX90TmuHWD5mo9pzYB97HnT7c5Xb3fsWnFEA6dhNAemNuX54rSA+mu0llfh0+1LOiZzoAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:05:16.759317Z","bundle_sha256":"95363c3d46f3d5cb2d5d931b68b3a0d773c2f740893391a5be881657be0acab5"}}