{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:Z5UPBIAKMJABRL3W7NVGBA5BBW","short_pith_number":"pith:Z5UPBIAK","canonical_record":{"source":{"id":"2402.13064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T15:00:35Z","cross_cats_sorted":[],"title_canon_sha256":"26b0e05b2482ec374c6f8fc6a92ee75e735c34dc87fd5df382e53317c467ea36","abstract_canon_sha256":"9445e58ffd80bcb367acd5aeb6f2a832f0bbbc4480795acd0e9f69d4ed5e0127"},"schema_version":"1.0"},"canonical_sha256":"cf68f0a00a624018af76fb6a6083a10d9f86a52598701d30dfa6ac7bf70efee1","source":{"kind":"arxiv","id":"2402.13064","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13064","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13064v1","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13064","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"pith_short_12","alias_value":"Z5UPBIAKMJAB","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"pith_short_16","alias_value":"Z5UPBIAKMJABRL3W","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"pith_short_8","alias_value":"Z5UPBIAK","created_at":"2026-07-05T07:47:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:Z5UPBIAKMJABRL3W7NVGBA5BBW","target":"record","payload":{"canonical_record":{"source":{"id":"2402.13064","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T15:00:35Z","cross_cats_sorted":[],"title_canon_sha256":"26b0e05b2482ec374c6f8fc6a92ee75e735c34dc87fd5df382e53317c467ea36","abstract_canon_sha256":"9445e58ffd80bcb367acd5aeb6f2a832f0bbbc4480795acd0e9f69d4ed5e0127"},"schema_version":"1.0"},"canonical_sha256":"cf68f0a00a624018af76fb6a6083a10d9f86a52598701d30dfa6ac7bf70efee1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:47:20.457642Z","signature_b64":"aQioW8U+rsq2u3jjzSstOps1P7uLBb6zGJgDQRGbcjmKCxtM4VE+va3QFOXQsLPz2ongGAyVW1jKMhObqAknBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cf68f0a00a624018af76fb6a6083a10d9f86a52598701d30dfa6ac7bf70efee1","last_reissued_at":"2026-07-05T07:47:20.457137Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:47:20.457137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.13064","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":"2026-07-05T07:47:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uOhGFnZBmo2gDHNNiWw7egBA9YHyFx8ENEcvsSOgMx7PRlEz/r14sa3BavEOK0DtWYwIOk7YNDHlhuSO5MwmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:15:22.962440Z"},"content_sha256":"f17233f3e491c9e4d891a4c42ed1b0cca9d6a7aa055c22778b57b825c1fbe46e","schema_version":"1.0","event_id":"sha256:f17233f3e491c9e4d891a4c42ed1b0cca9d6a7aa055c22778b57b825c1fbe46e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:Z5UPBIAKMJABRL3W7NVGBA5BBW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benyou Wang, Chaojun Wang, Dongdong Zhang, Furu Wei, Haoran Li, Haoyang Huang, Li Dong, Qingxiu Dong, Shaohan Huang, Si-Qing Chen, Wai Lam, Wei Lu, Xiaolong Huang, Xin Cheng, Xingxing Zhang, Xun Wang, Yuxian Gu, Zeqiang Huang, Zhengyang Tang, Zhifang Sui","submitted_at":"2024-02-20T15:00:35Z","abstract_excerpt":"We introduce Generalized Instruction Tuning (called GLAN), a general and scalable method for instruction tuning of Large Language Models (LLMs). Unlike prior work that relies on seed examples or existing datasets to construct instruction tuning data, GLAN exclusively utilizes a pre-curated taxonomy of human knowledge and capabilities as input and generates large-scale synthetic instruction data across all disciplines. Specifically, inspired by the systematic structure in human education system, we build the taxonomy by decomposing human knowledge and capabilities to various fields, sub-fields "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13064","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/2402.13064/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":"2026-07-05T07:47:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"slIZgPiFZUwIOlotSvCM+M7y8yXQKLhfCEZPipcAPj8kPNGhk2NhDHBtBrQlhFgEOfn0kvFC5kl9mOkvWJqSAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T03:15:22.963351Z"},"content_sha256":"ac2c62d4050ac1857697f356a0538a70576594e50c5a31f9a5ba464e5655e173","schema_version":"1.0","event_id":"sha256:ac2c62d4050ac1857697f356a0538a70576594e50c5a31f9a5ba464e5655e173"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Z5UPBIAKMJABRL3W7NVGBA5BBW/bundle.json","state_url":"https://pith.science/pith/Z5UPBIAKMJABRL3W7NVGBA5BBW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Z5UPBIAKMJABRL3W7NVGBA5BBW/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":"2026-08-04T03:15:22Z","links":{"resolver":"https://pith.science/pith/Z5UPBIAKMJABRL3W7NVGBA5BBW","bundle":"https://pith.science/pith/Z5UPBIAKMJABRL3W7NVGBA5BBW/bundle.json","state":"https://pith.science/pith/Z5UPBIAKMJABRL3W7NVGBA5BBW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Z5UPBIAKMJABRL3W7NVGBA5BBW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Z5UPBIAKMJABRL3W7NVGBA5BBW","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":"9445e58ffd80bcb367acd5aeb6f2a832f0bbbc4480795acd0e9f69d4ed5e0127","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T15:00:35Z","title_canon_sha256":"26b0e05b2482ec374c6f8fc6a92ee75e735c34dc87fd5df382e53317c467ea36"},"schema_version":"1.0","source":{"id":"2402.13064","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.13064","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"arxiv_version","alias_value":"2402.13064v1","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.13064","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"pith_short_12","alias_value":"Z5UPBIAKMJAB","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"pith_short_16","alias_value":"Z5UPBIAKMJABRL3W","created_at":"2026-07-05T07:47:20Z"},{"alias_kind":"pith_short_8","alias_value":"Z5UPBIAK","created_at":"2026-07-05T07:47:20Z"}],"graph_snapshots":[{"event_id":"sha256:ac2c62d4050ac1857697f356a0538a70576594e50c5a31f9a5ba464e5655e173","target":"graph","created_at":"2026-07-05T07:47:20Z","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/2402.13064/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce Generalized Instruction Tuning (called GLAN), a general and scalable method for instruction tuning of Large Language Models (LLMs). Unlike prior work that relies on seed examples or existing datasets to construct instruction tuning data, GLAN exclusively utilizes a pre-curated taxonomy of human knowledge and capabilities as input and generates large-scale synthetic instruction data across all disciplines. Specifically, inspired by the systematic structure in human education system, we build the taxonomy by decomposing human knowledge and capabilities to various fields, sub-fields ","authors_text":"Benyou Wang, Chaojun Wang, Dongdong Zhang, Furu Wei, Haoran Li, Haoyang Huang, Li Dong, Qingxiu Dong, Shaohan Huang, Si-Qing Chen, Wai Lam, Wei Lu, Xiaolong Huang, Xin Cheng, Xingxing Zhang, Xun Wang, Yuxian Gu, Zeqiang Huang, Zhengyang Tang, Zhifang Sui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T15:00:35Z","title":"Synthetic Data (Almost) from Scratch: Generalized Instruction Tuning for Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.13064","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:f17233f3e491c9e4d891a4c42ed1b0cca9d6a7aa055c22778b57b825c1fbe46e","target":"record","created_at":"2026-07-05T07:47:20Z","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":"9445e58ffd80bcb367acd5aeb6f2a832f0bbbc4480795acd0e9f69d4ed5e0127","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-20T15:00:35Z","title_canon_sha256":"26b0e05b2482ec374c6f8fc6a92ee75e735c34dc87fd5df382e53317c467ea36"},"schema_version":"1.0","source":{"id":"2402.13064","kind":"arxiv","version":1}},"canonical_sha256":"cf68f0a00a624018af76fb6a6083a10d9f86a52598701d30dfa6ac7bf70efee1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cf68f0a00a624018af76fb6a6083a10d9f86a52598701d30dfa6ac7bf70efee1","first_computed_at":"2026-07-05T07:47:20.457137Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:47:20.457137Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aQioW8U+rsq2u3jjzSstOps1P7uLBb6zGJgDQRGbcjmKCxtM4VE+va3QFOXQsLPz2ongGAyVW1jKMhObqAknBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:47:20.457642Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.13064","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f17233f3e491c9e4d891a4c42ed1b0cca9d6a7aa055c22778b57b825c1fbe46e","sha256:ac2c62d4050ac1857697f356a0538a70576594e50c5a31f9a5ba464e5655e173"],"state_sha256":"97ccdd2e2bf470b22df9839d1704a6a4fae7693c408a30ee4257d48279e280b4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MWGoVPjfhEhUkNufdZWnxkfg5EjsH1qYy3NTkxjPujrtBliGPYrM2SlzEQPikRLC9gj/uPmesrUr1GnsXh1lAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T03:15:22.967732Z","bundle_sha256":"341793548058e1e71d94eda347b7fea525dd23735d57e5200b4619a8ccdf1f36"}}