{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:U4TIVLWKYNPSZPN72QZJL5ZEOA","short_pith_number":"pith:U4TIVLWK","canonical_record":{"source":{"id":"2505.12250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T06:10:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f7820879974b2644706103cb82e3ea900594f1dd6af460145b831027b71f8872","abstract_canon_sha256":"e8538bec679037ce08a3d367de0d1bf370df7132ec1b9c42e014797cbbb5bea9"},"schema_version":"1.0"},"canonical_sha256":"a7268aaecac35f2cbdbfd43295f7247028b131d3466efdcb30a137c6befb11a2","source":{"kind":"arxiv","id":"2505.12250","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12250","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12250v1","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12250","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"U4TIVLWKYNPS","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"U4TIVLWKYNPSZPN7","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"U4TIVLWK","created_at":"2026-07-05T11:05:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:U4TIVLWKYNPSZPN72QZJL5ZEOA","target":"record","payload":{"canonical_record":{"source":{"id":"2505.12250","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T06:10:08Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f7820879974b2644706103cb82e3ea900594f1dd6af460145b831027b71f8872","abstract_canon_sha256":"e8538bec679037ce08a3d367de0d1bf370df7132ec1b9c42e014797cbbb5bea9"},"schema_version":"1.0"},"canonical_sha256":"a7268aaecac35f2cbdbfd43295f7247028b131d3466efdcb30a137c6befb11a2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:05:00.895430Z","signature_b64":"VYXb1G1OPfgdWxvdUvUquImxnsEBfOLOD1aR7Zpi4pLMG8pDUCNWqMIqRRzd0SQVlbb7znmzpS5GPNRQ8gBHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7268aaecac35f2cbdbfd43295f7247028b131d3466efdcb30a137c6befb11a2","last_reissued_at":"2026-07-05T11:05:00.894848Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:05:00.894848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.12250","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":"2026-07-05T11:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SnHhwbKJDmT4108YCY4FkEdR9xYEo1OciyNB/oJPdyhwk2uV+GjjeHmNSg3E0FdCe2k7YZ1Ymb+Ta3B2bdsnBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:26:57.792160Z"},"content_sha256":"ccc206ae917e372b815f7ff220c440a40190fbb039a6550a451340bd423cf382","schema_version":"1.0","event_id":"sha256:ccc206ae917e372b815f7ff220c440a40190fbb039a6550a451340bd423cf382"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:U4TIVLWKYNPSZPN72QZJL5ZEOA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Not All Documents Are What You Need for Extracting Instruction Tuning Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chengliang Chai, Chi Zhang, Conghui He, Guoren Wang, Hongtao Li, Huaping Zhong, Jiacheng Wang, Jiantao Qiu, Jiawei Hong, Lei Cao, Tian Tan, Ye Yuan, Yizhou Yan, Yuhao Deng","submitted_at":"2025-05-18T06:10:08Z","abstract_excerpt":"Instruction tuning improves the performance of large language models (LLMs), but it heavily relies on high-quality training data. Recently, LLMs have been used to synthesize instruction data using seed question-answer (QA) pairs. However, these synthesized instructions often lack diversity and tend to be similar to the input seeds, limiting their applicability in real-world scenarios. To address this, we propose extracting instruction tuning data from web corpora that contain rich and diverse knowledge. A naive solution is to retrieve domain-specific documents and extract all QA pairs from the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12250","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/2505.12250/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":"2026-07-05T11:05:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ukkJzuVrLRPLTpISUJbR5eiuSDZ93x8AWa7vza4pFm+b0wgL47EKkdVDWlRd8cDMPUusbDsWDotFQznuk+p8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T13:26:57.793473Z"},"content_sha256":"dddd8d73f7eb10caf0b0391949f78cb54a7fb6b3693eefe3156b2fee1ec7aea3","schema_version":"1.0","event_id":"sha256:dddd8d73f7eb10caf0b0391949f78cb54a7fb6b3693eefe3156b2fee1ec7aea3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U4TIVLWKYNPSZPN72QZJL5ZEOA/bundle.json","state_url":"https://pith.science/pith/U4TIVLWKYNPSZPN72QZJL5ZEOA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U4TIVLWKYNPSZPN72QZJL5ZEOA/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":"2026-08-18T13:26:57Z","links":{"resolver":"https://pith.science/pith/U4TIVLWKYNPSZPN72QZJL5ZEOA","bundle":"https://pith.science/pith/U4TIVLWKYNPSZPN72QZJL5ZEOA/bundle.json","state":"https://pith.science/pith/U4TIVLWKYNPSZPN72QZJL5ZEOA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U4TIVLWKYNPSZPN72QZJL5ZEOA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:U4TIVLWKYNPSZPN72QZJL5ZEOA","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":"e8538bec679037ce08a3d367de0d1bf370df7132ec1b9c42e014797cbbb5bea9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T06:10:08Z","title_canon_sha256":"f7820879974b2644706103cb82e3ea900594f1dd6af460145b831027b71f8872"},"schema_version":"1.0","source":{"id":"2505.12250","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.12250","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.12250v1","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.12250","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_12","alias_value":"U4TIVLWKYNPS","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_16","alias_value":"U4TIVLWKYNPSZPN7","created_at":"2026-07-05T11:05:00Z"},{"alias_kind":"pith_short_8","alias_value":"U4TIVLWK","created_at":"2026-07-05T11:05:00Z"}],"graph_snapshots":[{"event_id":"sha256:dddd8d73f7eb10caf0b0391949f78cb54a7fb6b3693eefe3156b2fee1ec7aea3","target":"graph","created_at":"2026-07-05T11:05:00Z","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/2505.12250/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction tuning improves the performance of large language models (LLMs), but it heavily relies on high-quality training data. Recently, LLMs have been used to synthesize instruction data using seed question-answer (QA) pairs. However, these synthesized instructions often lack diversity and tend to be similar to the input seeds, limiting their applicability in real-world scenarios. To address this, we propose extracting instruction tuning data from web corpora that contain rich and diverse knowledge. A naive solution is to retrieve domain-specific documents and extract all QA pairs from the","authors_text":"Chengliang Chai, Chi Zhang, Conghui He, Guoren Wang, Hongtao Li, Huaping Zhong, Jiacheng Wang, Jiantao Qiu, Jiawei Hong, Lei Cao, Tian Tan, Ye Yuan, Yizhou Yan, Yuhao Deng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T06:10:08Z","title":"Not All Documents Are What You Need for Extracting Instruction Tuning Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.12250","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:ccc206ae917e372b815f7ff220c440a40190fbb039a6550a451340bd423cf382","target":"record","created_at":"2026-07-05T11:05:00Z","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":"e8538bec679037ce08a3d367de0d1bf370df7132ec1b9c42e014797cbbb5bea9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-18T06:10:08Z","title_canon_sha256":"f7820879974b2644706103cb82e3ea900594f1dd6af460145b831027b71f8872"},"schema_version":"1.0","source":{"id":"2505.12250","kind":"arxiv","version":1}},"canonical_sha256":"a7268aaecac35f2cbdbfd43295f7247028b131d3466efdcb30a137c6befb11a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7268aaecac35f2cbdbfd43295f7247028b131d3466efdcb30a137c6befb11a2","first_computed_at":"2026-07-05T11:05:00.894848Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:05:00.894848Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VYXb1G1OPfgdWxvdUvUquImxnsEBfOLOD1aR7Zpi4pLMG8pDUCNWqMIqRRzd0SQVlbb7znmzpS5GPNRQ8gBHCA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:05:00.895430Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.12250","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccc206ae917e372b815f7ff220c440a40190fbb039a6550a451340bd423cf382","sha256:dddd8d73f7eb10caf0b0391949f78cb54a7fb6b3693eefe3156b2fee1ec7aea3"],"state_sha256":"00705c089fa59ebdb40ab22a69cf4019046c58a3e667ea4e26d2984ea655f5de"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iOibF16toxSHC4J4di99alRn0oESR8p8N/mFBZYrspWPqXYneWTHyVftqkx8uJcwDNqop4VN8Eo07FDMEVOvAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T13:26:57.861776Z","bundle_sha256":"b5968355faa869380d4c61b5bc409de7f6451c7f20711795fe6b74d77a5ad386"}}