{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:DYBJEQEERP6HHQPWJB2RA6EP3O","short_pith_number":"pith:DYBJEQEE","canonical_record":{"source":{"id":"2509.10708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T21:50:39Z","cross_cats_sorted":[],"title_canon_sha256":"e7015a4daeec5b47ac34f95cef2bcf8f8f7f0d991b2168469a99d338c0e81110","abstract_canon_sha256":"da48009522339d66669924c554335b3e7be960d1e89a01447f17deb1a994082f"},"schema_version":"1.0"},"canonical_sha256":"1e029240848bfc73c1f6487510788fdbbfca305f4d427b580ee7a8ef0b2cf22c","source":{"kind":"arxiv","id":"2509.10708","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.10708","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2509.10708v1","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10708","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"DYBJEQEERP6H","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"DYBJEQEERP6HHQPW","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"DYBJEQEE","created_at":"2026-07-05T12:11:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:DYBJEQEERP6HHQPWJB2RA6EP3O","target":"record","payload":{"canonical_record":{"source":{"id":"2509.10708","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T21:50:39Z","cross_cats_sorted":[],"title_canon_sha256":"e7015a4daeec5b47ac34f95cef2bcf8f8f7f0d991b2168469a99d338c0e81110","abstract_canon_sha256":"da48009522339d66669924c554335b3e7be960d1e89a01447f17deb1a994082f"},"schema_version":"1.0"},"canonical_sha256":"1e029240848bfc73c1f6487510788fdbbfca305f4d427b580ee7a8ef0b2cf22c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:26.415067Z","signature_b64":"JypawfIOCI3oIRRzR8Z4nrpYI5THFOcCyRz43Ygl1HqHw01bTiwEYufmGkWHTajm65V8ENBFf6eqBvfRLnABCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1e029240848bfc73c1f6487510788fdbbfca305f4d427b580ee7a8ef0b2cf22c","last_reissued_at":"2026-07-05T12:11:26.414493Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:26.414493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.10708","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":"2026-07-05T12:11:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wxch/Q/BzIUE2A9gasuEfte4bDfTFtxXcOBZ+I/hLtl9FRAOL8zOH3XCJPkhH1dKXAmwDoTjlvN2zGugYusQBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:39:59.521634Z"},"content_sha256":"c1f0c033d183faf892b86559d6fdbe6b23a0ead90e69cbbb645f28115f81853f","schema_version":"1.0","event_id":"sha256:c1f0c033d183faf892b86559d6fdbe6b23a0ead90e69cbbb645f28115f81853f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:DYBJEQEERP6HHQPWJB2RA6EP3O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Heshaam Faili, Iman Barati, Mostafa Amiri","submitted_at":"2025-09-12T21:50:39Z","abstract_excerpt":"Supervised Fine-Tuning (SFT) is essential for training large language models (LLMs), significantly enhancing critical capabilities such as instruction following and in-context learning. Nevertheless, creating suitable training datasets tailored for specific domains remains challenging due to unique domain constraints and data scarcity. In this paper, we propose SearchInstruct, an innovative method explicitly designed to construct high quality instruction datasets for SFT. Our approach begins with a limited set of domain specific, human generated questions, which are systematically expanded usi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10708","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/2509.10708/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":"2026-07-05T12:11:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+jWI3n1FhKMWEhPyvCThsD5EG0XIYDWzVys4+vNwASxTgJ6vjUXgEjQLBHQ8fEtLlYTHH2e5jyudZE6b/HaeDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:39:59.522531Z"},"content_sha256":"59c98cfe8f927c5b63b41ab3051d538acc1a0f83610c5f552d06018a8d035fa9","schema_version":"1.0","event_id":"sha256:59c98cfe8f927c5b63b41ab3051d538acc1a0f83610c5f552d06018a8d035fa9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DYBJEQEERP6HHQPWJB2RA6EP3O/bundle.json","state_url":"https://pith.science/pith/DYBJEQEERP6HHQPWJB2RA6EP3O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DYBJEQEERP6HHQPWJB2RA6EP3O/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":"2026-08-05T10:39:59Z","links":{"resolver":"https://pith.science/pith/DYBJEQEERP6HHQPWJB2RA6EP3O","bundle":"https://pith.science/pith/DYBJEQEERP6HHQPWJB2RA6EP3O/bundle.json","state":"https://pith.science/pith/DYBJEQEERP6HHQPWJB2RA6EP3O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DYBJEQEERP6HHQPWJB2RA6EP3O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DYBJEQEERP6HHQPWJB2RA6EP3O","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":"da48009522339d66669924c554335b3e7be960d1e89a01447f17deb1a994082f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T21:50:39Z","title_canon_sha256":"e7015a4daeec5b47ac34f95cef2bcf8f8f7f0d991b2168469a99d338c0e81110"},"schema_version":"1.0","source":{"id":"2509.10708","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.10708","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"arxiv_version","alias_value":"2509.10708v1","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.10708","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"pith_short_12","alias_value":"DYBJEQEERP6H","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"pith_short_16","alias_value":"DYBJEQEERP6HHQPW","created_at":"2026-07-05T12:11:26Z"},{"alias_kind":"pith_short_8","alias_value":"DYBJEQEE","created_at":"2026-07-05T12:11:26Z"}],"graph_snapshots":[{"event_id":"sha256:59c98cfe8f927c5b63b41ab3051d538acc1a0f83610c5f552d06018a8d035fa9","target":"graph","created_at":"2026-07-05T12:11:26Z","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/2509.10708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Supervised Fine-Tuning (SFT) is essential for training large language models (LLMs), significantly enhancing critical capabilities such as instruction following and in-context learning. Nevertheless, creating suitable training datasets tailored for specific domains remains challenging due to unique domain constraints and data scarcity. In this paper, we propose SearchInstruct, an innovative method explicitly designed to construct high quality instruction datasets for SFT. Our approach begins with a limited set of domain specific, human generated questions, which are systematically expanded usi","authors_text":"Heshaam Faili, Iman Barati, Mostafa Amiri","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T21:50:39Z","title":"SearchInstruct: Enhancing Domain Adaptation via Retrieval-Based Instruction Dataset Creation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.10708","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:c1f0c033d183faf892b86559d6fdbe6b23a0ead90e69cbbb645f28115f81853f","target":"record","created_at":"2026-07-05T12:11:26Z","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":"da48009522339d66669924c554335b3e7be960d1e89a01447f17deb1a994082f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-12T21:50:39Z","title_canon_sha256":"e7015a4daeec5b47ac34f95cef2bcf8f8f7f0d991b2168469a99d338c0e81110"},"schema_version":"1.0","source":{"id":"2509.10708","kind":"arxiv","version":1}},"canonical_sha256":"1e029240848bfc73c1f6487510788fdbbfca305f4d427b580ee7a8ef0b2cf22c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1e029240848bfc73c1f6487510788fdbbfca305f4d427b580ee7a8ef0b2cf22c","first_computed_at":"2026-07-05T12:11:26.414493Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:26.414493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JypawfIOCI3oIRRzR8Z4nrpYI5THFOcCyRz43Ygl1HqHw01bTiwEYufmGkWHTajm65V8ENBFf6eqBvfRLnABCA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:26.415067Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.10708","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c1f0c033d183faf892b86559d6fdbe6b23a0ead90e69cbbb645f28115f81853f","sha256:59c98cfe8f927c5b63b41ab3051d538acc1a0f83610c5f552d06018a8d035fa9"],"state_sha256":"87880721efd43210327214db414a00978e55ebf9db9b03de293ef05fb3ef2250"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ScBt6GKH0KyJte1bLg0oIIcOcE9C9Wcl/S/a9KI+GngvNeHFa0XEDWNw2OWs80yj4kJBpJEZH50OjpoT6pKDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:39:59.527559Z","bundle_sha256":"f1a438ec74ab9c3ae584d3cec41333a08603185788b696f2c1976dccd51566cb"}}