{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:ZZ2YLUHILENJ6ORIC3NED3KVPA","short_pith_number":"pith:ZZ2YLUHI","canonical_record":{"source":{"id":"2507.18584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:03:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6195a8413b046aa8f22b0313d0624d849f735f336bb1f7be9e4dd2d7d14efda3","abstract_canon_sha256":"533224d627668c0a6b6a1d693985a18c830d9dde51b0eca0617f810c8212f482"},"schema_version":"1.0"},"canonical_sha256":"ce7585d0e8591a9f3a2816da41ed5578156338b7622dabdcfdcef1c2e4a7c2a0","source":{"kind":"arxiv","id":"2507.18584","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18584","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18584v1","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18584","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZZ2YLUHILENJ","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZZ2YLUHILENJ6ORI","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZZ2YLUHI","created_at":"2026-07-05T11:42:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:ZZ2YLUHILENJ6ORIC3NED3KVPA","target":"record","payload":{"canonical_record":{"source":{"id":"2507.18584","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:03:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"6195a8413b046aa8f22b0313d0624d849f735f336bb1f7be9e4dd2d7d14efda3","abstract_canon_sha256":"533224d627668c0a6b6a1d693985a18c830d9dde51b0eca0617f810c8212f482"},"schema_version":"1.0"},"canonical_sha256":"ce7585d0e8591a9f3a2816da41ed5578156338b7622dabdcfdcef1c2e4a7c2a0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:50.447144Z","signature_b64":"Q0eT4llSGkx7nQx5LcmSumYMGDxV2WgI4AjIHIRfCBi2PSuOx5dj91dCCzO2nfT59U4MqbWibD1Pt+ucwLZuAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce7585d0e8591a9f3a2816da41ed5578156338b7622dabdcfdcef1c2e4a7c2a0","last_reissued_at":"2026-07-05T11:42:50.446706Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:50.446706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.18584","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":"2026-07-05T11:42:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mJkUDoGUghPbMZNe90XySbIum9Y8PJFMSIPIytXChKSXarb+Y6Ug/AKr8nDcVoucchfdsvyXg6h+KhvLoWqrBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:39:15.613932Z"},"content_sha256":"d6ca58967af9c5e510ae196c7f674313819b4072646d34dfe8aac278bc453a12","schema_version":"1.0","event_id":"sha256:d6ca58967af9c5e510ae196c7f674313819b4072646d34dfe8aac278bc453a12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:ZZ2YLUHILENJ6ORIC3NED3KVPA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hexuan Deng, Jun Rao, Jun Yu, Min Zhang, Xiaopeng Ke, Xuebo Liu, Zhenxi Song","submitted_at":"2025-07-24T17:03:27Z","abstract_excerpt":"Despite the impressive performance of large language models (LLMs) in general domains, they often underperform in specialized domains. Existing approaches typically rely on data synthesis methods and yield promising results by using unlabeled data to capture domain-specific features. However, these methods either incur high computational costs or suffer from performance limitations, while also demonstrating insufficient generalization across different tasks. To address these challenges, we propose AQuilt, a framework for constructing instruction-tuning data for any specialized domains from cor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18584","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/2507.18584/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":"2026-07-05T11:42:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HDI4Yd7xXX98iQ3uq3thHs1rFRLiAOWGNFdsEKqWiYRg7Z5R7r5ZcMAf29pvH9ldXyJTzwPIaihX5ehAXUHqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:39:15.614451Z"},"content_sha256":"062552c7b268a4ae7a787b8c8eef3c85f0d736e9899eea6fbcfe8679e493f348","schema_version":"1.0","event_id":"sha256:062552c7b268a4ae7a787b8c8eef3c85f0d736e9899eea6fbcfe8679e493f348"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZZ2YLUHILENJ6ORIC3NED3KVPA/bundle.json","state_url":"https://pith.science/pith/ZZ2YLUHILENJ6ORIC3NED3KVPA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZZ2YLUHILENJ6ORIC3NED3KVPA/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":"2026-08-09T20:39:15Z","links":{"resolver":"https://pith.science/pith/ZZ2YLUHILENJ6ORIC3NED3KVPA","bundle":"https://pith.science/pith/ZZ2YLUHILENJ6ORIC3NED3KVPA/bundle.json","state":"https://pith.science/pith/ZZ2YLUHILENJ6ORIC3NED3KVPA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZZ2YLUHILENJ6ORIC3NED3KVPA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZZ2YLUHILENJ6ORIC3NED3KVPA","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":"533224d627668c0a6b6a1d693985a18c830d9dde51b0eca0617f810c8212f482","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:03:27Z","title_canon_sha256":"6195a8413b046aa8f22b0313d0624d849f735f336bb1f7be9e4dd2d7d14efda3"},"schema_version":"1.0","source":{"id":"2507.18584","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.18584","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"arxiv_version","alias_value":"2507.18584v1","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18584","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"pith_short_12","alias_value":"ZZ2YLUHILENJ","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"pith_short_16","alias_value":"ZZ2YLUHILENJ6ORI","created_at":"2026-07-05T11:42:50Z"},{"alias_kind":"pith_short_8","alias_value":"ZZ2YLUHI","created_at":"2026-07-05T11:42:50Z"}],"graph_snapshots":[{"event_id":"sha256:062552c7b268a4ae7a787b8c8eef3c85f0d736e9899eea6fbcfe8679e493f348","target":"graph","created_at":"2026-07-05T11:42:50Z","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/2507.18584/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite the impressive performance of large language models (LLMs) in general domains, they often underperform in specialized domains. Existing approaches typically rely on data synthesis methods and yield promising results by using unlabeled data to capture domain-specific features. However, these methods either incur high computational costs or suffer from performance limitations, while also demonstrating insufficient generalization across different tasks. To address these challenges, we propose AQuilt, a framework for constructing instruction-tuning data for any specialized domains from cor","authors_text":"Hexuan Deng, Jun Rao, Jun Yu, Min Zhang, Xiaopeng Ke, Xuebo Liu, Zhenxi Song","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:03:27Z","title":"AQuilt: Weaving Logic and Self-Inspection into Low-Cost, High-Relevance Data Synthesis for Specialist LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18584","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:d6ca58967af9c5e510ae196c7f674313819b4072646d34dfe8aac278bc453a12","target":"record","created_at":"2026-07-05T11:42:50Z","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":"533224d627668c0a6b6a1d693985a18c830d9dde51b0eca0617f810c8212f482","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-24T17:03:27Z","title_canon_sha256":"6195a8413b046aa8f22b0313d0624d849f735f336bb1f7be9e4dd2d7d14efda3"},"schema_version":"1.0","source":{"id":"2507.18584","kind":"arxiv","version":1}},"canonical_sha256":"ce7585d0e8591a9f3a2816da41ed5578156338b7622dabdcfdcef1c2e4a7c2a0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce7585d0e8591a9f3a2816da41ed5578156338b7622dabdcfdcef1c2e4a7c2a0","first_computed_at":"2026-07-05T11:42:50.446706Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:42:50.446706Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Q0eT4llSGkx7nQx5LcmSumYMGDxV2WgI4AjIHIRfCBi2PSuOx5dj91dCCzO2nfT59U4MqbWibD1Pt+ucwLZuAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:42:50.447144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.18584","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d6ca58967af9c5e510ae196c7f674313819b4072646d34dfe8aac278bc453a12","sha256:062552c7b268a4ae7a787b8c8eef3c85f0d736e9899eea6fbcfe8679e493f348"],"state_sha256":"ee6ff5699235aa93a61593eab86eae6b600869238dec7501529cda82c97f2bea"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6u6HZGNDg7mPFPosZElSD2SsZG2aHzUbfyClJAhhwfcE9C04SqjWC0m/GA5tmrUorSZAfG6tdiXzgI9cpNK7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:39:15.619471Z","bundle_sha256":"c6b3977c0cce6fd5b8e6c556eaf8ebdb34c058abd30e5ce7177da355fa346869"}}