{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:Q2WALCE7VVGVPQEIZN42KHQTMT","short_pith_number":"pith:Q2WALCE7","canonical_record":{"source":{"id":"2503.23714","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T04:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"f72e1b8a876d3b0f8600c778f3faded5b76e632ccb5c617398518c79666f38b2","abstract_canon_sha256":"eef06e9ea4113169aacc0c9f0dcfe8f9e684c35f718dec0b15db955768090133"},"schema_version":"1.0"},"canonical_sha256":"86ac05889fad4d57c088cb79a51e1364c85b067fc43bb5345422210a72e48afc","source":{"kind":"arxiv","id":"2503.23714","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23714","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23714v2","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23714","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"Q2WALCE7VVGV","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"Q2WALCE7VVGVPQEI","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"Q2WALCE7","created_at":"2026-07-05T11:53:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:Q2WALCE7VVGVPQEIZN42KHQTMT","target":"record","payload":{"canonical_record":{"source":{"id":"2503.23714","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T04:28:38Z","cross_cats_sorted":[],"title_canon_sha256":"f72e1b8a876d3b0f8600c778f3faded5b76e632ccb5c617398518c79666f38b2","abstract_canon_sha256":"eef06e9ea4113169aacc0c9f0dcfe8f9e684c35f718dec0b15db955768090133"},"schema_version":"1.0"},"canonical_sha256":"86ac05889fad4d57c088cb79a51e1364c85b067fc43bb5345422210a72e48afc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:45.219153Z","signature_b64":"yHIccrQjKnoyBDGzJKFH9M7Soksy0m4wowqCCKWhoSgNnGNCOtuvJKhhIeG5ClfPVMhbJkEUeCnpRa64OiQqDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86ac05889fad4d57c088cb79a51e1364c85b067fc43bb5345422210a72e48afc","last_reissued_at":"2026-07-05T11:53:45.218647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:45.218647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.23714","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":"2026-07-05T11:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ci71oJesGURdJlqsYXcjolNCGgqi7yWsgROgijDDqn4dpD1YGgEN2dWv0HfomQCeh0ZR2dP9pan5UkqDnZXPDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:29:46.194156Z"},"content_sha256":"2c8421e9a466a790e3f1b68d411ffc091700885721147b60659af04587751ec4","schema_version":"1.0","event_id":"sha256:2c8421e9a466a790e3f1b68d411ffc091700885721147b60659af04587751ec4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:Q2WALCE7VVGVPQEIZN42KHQTMT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hinari Shimada, Hiroya Takamura, Kakeru Hattori, Kazuki Fujii, Koki Maeda, Koshiro Saito, Masanari Ohi, Naoaki Okazaki, Rio Yokota, Sakae Mizuki, Shigeki Ishida, Taihei Shiotani, Taishi Nakamura, Takumi Okamoto, Youmi Ma","submitted_at":"2025-03-31T04:28:38Z","abstract_excerpt":"Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still need human-originated signals for instruction tuning? This work answers the question affirmatively: we build state-of-the-art instruction-tuning datasets sourced from human-written instructions, by simply pairing them with LLM-generated responses. LLMs fine-tuned on our datasets consistently outperform those fine-tuned on existing ones. Our data construction "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23714","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/2503.23714/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":"2026-07-05T11:53:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3hV5HRQf6Pi4A3XlhjXuLCNwpZmrIeCOgSPMyUa3ZVMCLopIX+GQlIlU9j+xSZAdtGTiXvG+2VmECCJyYEflAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T18:29:46.194685Z"},"content_sha256":"1273a1e4c3b9a9495f571fb222ac8bbc9f8a37bde7ff7932494e90a7da1cfe0d","schema_version":"1.0","event_id":"sha256:1273a1e4c3b9a9495f571fb222ac8bbc9f8a37bde7ff7932494e90a7da1cfe0d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q2WALCE7VVGVPQEIZN42KHQTMT/bundle.json","state_url":"https://pith.science/pith/Q2WALCE7VVGVPQEIZN42KHQTMT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q2WALCE7VVGVPQEIZN42KHQTMT/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":"2026-08-09T18:29:46Z","links":{"resolver":"https://pith.science/pith/Q2WALCE7VVGVPQEIZN42KHQTMT","bundle":"https://pith.science/pith/Q2WALCE7VVGVPQEIZN42KHQTMT/bundle.json","state":"https://pith.science/pith/Q2WALCE7VVGVPQEIZN42KHQTMT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q2WALCE7VVGVPQEIZN42KHQTMT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:Q2WALCE7VVGVPQEIZN42KHQTMT","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":"eef06e9ea4113169aacc0c9f0dcfe8f9e684c35f718dec0b15db955768090133","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T04:28:38Z","title_canon_sha256":"f72e1b8a876d3b0f8600c778f3faded5b76e632ccb5c617398518c79666f38b2"},"schema_version":"1.0","source":{"id":"2503.23714","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.23714","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"arxiv_version","alias_value":"2503.23714v2","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23714","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_12","alias_value":"Q2WALCE7VVGV","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_16","alias_value":"Q2WALCE7VVGVPQEI","created_at":"2026-07-05T11:53:45Z"},{"alias_kind":"pith_short_8","alias_value":"Q2WALCE7","created_at":"2026-07-05T11:53:45Z"}],"graph_snapshots":[{"event_id":"sha256:1273a1e4c3b9a9495f571fb222ac8bbc9f8a37bde7ff7932494e90a7da1cfe0d","target":"graph","created_at":"2026-07-05T11:53:45Z","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/2503.23714/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning is crucial for enabling Large Language Models (LLMs) to solve real-world tasks. Prior work has shown the effectiveness of instruction-tuning data synthesized solely from LLMs, raising a fundamental question: Do we still need human-originated signals for instruction tuning? This work answers the question affirmatively: we build state-of-the-art instruction-tuning datasets sourced from human-written instructions, by simply pairing them with LLM-generated responses. LLMs fine-tuned on our datasets consistently outperform those fine-tuned on existing ones. Our data construction ","authors_text":"Hinari Shimada, Hiroya Takamura, Kakeru Hattori, Kazuki Fujii, Koki Maeda, Koshiro Saito, Masanari Ohi, Naoaki Okazaki, Rio Yokota, Sakae Mizuki, Shigeki Ishida, Taihei Shiotani, Taishi Nakamura, Takumi Okamoto, Youmi Ma","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T04:28:38Z","title":"Building Instruction-Tuning Datasets from Human-Written Instructions with Open-Weight Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23714","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":"sha256:2c8421e9a466a790e3f1b68d411ffc091700885721147b60659af04587751ec4","target":"record","created_at":"2026-07-05T11:53:45Z","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":"eef06e9ea4113169aacc0c9f0dcfe8f9e684c35f718dec0b15db955768090133","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T04:28:38Z","title_canon_sha256":"f72e1b8a876d3b0f8600c778f3faded5b76e632ccb5c617398518c79666f38b2"},"schema_version":"1.0","source":{"id":"2503.23714","kind":"arxiv","version":2}},"canonical_sha256":"86ac05889fad4d57c088cb79a51e1364c85b067fc43bb5345422210a72e48afc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86ac05889fad4d57c088cb79a51e1364c85b067fc43bb5345422210a72e48afc","first_computed_at":"2026-07-05T11:53:45.218647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:53:45.218647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yHIccrQjKnoyBDGzJKFH9M7Soksy0m4wowqCCKWhoSgNnGNCOtuvJKhhIeG5ClfPVMhbJkEUeCnpRa64OiQqDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:53:45.219153Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.23714","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c8421e9a466a790e3f1b68d411ffc091700885721147b60659af04587751ec4","sha256:1273a1e4c3b9a9495f571fb222ac8bbc9f8a37bde7ff7932494e90a7da1cfe0d"],"state_sha256":"0cfcb89f5f5301e72204d0e8bd0bd88534999932faa85ac6823500b87884ddf2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BpJ2H7iH8pMFYWhASBA/pRUL5en45WBY+6uX3H+749bE/09Ehj7PcfnlNqGvDnI6scC7+e6EzbozLXZVvZpSDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T18:29:46.199383Z","bundle_sha256":"7ad9b0cec8c6f16d6e108cddb399e56534012ab241d007202f7e578ce850dbb7"}}