{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KLZE2VHL2GDTGN22BQOWN27ORS","short_pith_number":"pith:KLZE2VHL","canonical_record":{"source":{"id":"2502.03843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:53:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9f5079fbbfbff3f3db782848442a2da73c4d1f42ddb980bad9a1fee4cb69bb1","abstract_canon_sha256":"a4ee7025c35d7e49c5f87a7551da8395ba371b5cd741d83c5fde87ce3e4c445a"},"schema_version":"1.0"},"canonical_sha256":"52f24d54ebd18733375a0c1d66ebee8cbcaae4e93a281f3f6675879e6ff45644","source":{"kind":"arxiv","id":"2502.03843","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03843","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03843v1","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03843","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"KLZE2VHL2GDT","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"KLZE2VHL2GDTGN22","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"KLZE2VHL","created_at":"2026-07-05T10:10:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KLZE2VHL2GDTGN22BQOWN27ORS","target":"record","payload":{"canonical_record":{"source":{"id":"2502.03843","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:53:40Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e9f5079fbbfbff3f3db782848442a2da73c4d1f42ddb980bad9a1fee4cb69bb1","abstract_canon_sha256":"a4ee7025c35d7e49c5f87a7551da8395ba371b5cd741d83c5fde87ce3e4c445a"},"schema_version":"1.0"},"canonical_sha256":"52f24d54ebd18733375a0c1d66ebee8cbcaae4e93a281f3f6675879e6ff45644","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:10:15.773734Z","signature_b64":"8NlK4DTpHllSb1WiAUe3gkQ4hIhwdUO4ylhTs83w45qCCTbBiFTmsQC+09BJSU+v8uKB+fowAOSHFOlXEXWTDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52f24d54ebd18733375a0c1d66ebee8cbcaae4e93a281f3f6675879e6ff45644","last_reissued_at":"2026-07-05T10:10:15.773274Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:10:15.773274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.03843","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":"2026-07-05T10:10:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rA1k3/liW9BfJ0U3xea1oV6qjQWGR8o+UOMZhXZKWhjf1995yMqghrzU87IH3L78ElKYuhLcRIB/A7Mtj/TiAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:03:48.598865Z"},"content_sha256":"0bf36ffa6ed43e847c759178cbc76f669340d15136582121a4cb37d42777808e","schema_version":"1.0","event_id":"sha256:0bf36ffa6ed43e847c759178cbc76f669340d15136582121a4cb37d42777808e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KLZE2VHL2GDTGN22BQOWN27ORS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Honghao Gui, Jun Xu, Jun Zhou, Lei Liang, Lin Yuan, Mengshu Sun, Zhiqiang Zhang","submitted_at":"2025-02-06T07:53:40Z","abstract_excerpt":"High-quality, large-scale instructions are crucial for aligning large language models (LLMs), however, there is a severe shortage of instruction in the field of natural language understanding (NLU). Previous works on constructing NLU instructions mainly focus on information extraction (IE), neglecting tasks such as machine reading comprehension, question answering, and text classification. Furthermore, the lack of diversity in the data has led to a decreased generalization ability of trained LLMs in other NLU tasks and a noticeable decline in the fundamental model's general capabilities. To ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03843","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/2502.03843/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":"2026-07-05T10:10:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c+28M3e2wTrijIFyd28tazotwKTQYyOYgxZUlkI8Yi23fuJkgJVztSqlhPr7nEAptSYobyenC1Oh2s8qdTZKCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T02:03:48.599489Z"},"content_sha256":"9c34dc89fa98a4f20707bd4338a4ec4fbc143f4d3b9d37547f244fbf67e2b30d","schema_version":"1.0","event_id":"sha256:9c34dc89fa98a4f20707bd4338a4ec4fbc143f4d3b9d37547f244fbf67e2b30d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KLZE2VHL2GDTGN22BQOWN27ORS/bundle.json","state_url":"https://pith.science/pith/KLZE2VHL2GDTGN22BQOWN27ORS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KLZE2VHL2GDTGN22BQOWN27ORS/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":"2026-08-19T02:03:48Z","links":{"resolver":"https://pith.science/pith/KLZE2VHL2GDTGN22BQOWN27ORS","bundle":"https://pith.science/pith/KLZE2VHL2GDTGN22BQOWN27ORS/bundle.json","state":"https://pith.science/pith/KLZE2VHL2GDTGN22BQOWN27ORS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KLZE2VHL2GDTGN22BQOWN27ORS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KLZE2VHL2GDTGN22BQOWN27ORS","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":"a4ee7025c35d7e49c5f87a7551da8395ba371b5cd741d83c5fde87ce3e4c445a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:53:40Z","title_canon_sha256":"e9f5079fbbfbff3f3db782848442a2da73c4d1f42ddb980bad9a1fee4cb69bb1"},"schema_version":"1.0","source":{"id":"2502.03843","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.03843","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"arxiv_version","alias_value":"2502.03843v1","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.03843","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"pith_short_12","alias_value":"KLZE2VHL2GDT","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"pith_short_16","alias_value":"KLZE2VHL2GDTGN22","created_at":"2026-07-05T10:10:15Z"},{"alias_kind":"pith_short_8","alias_value":"KLZE2VHL","created_at":"2026-07-05T10:10:15Z"}],"graph_snapshots":[{"event_id":"sha256:9c34dc89fa98a4f20707bd4338a4ec4fbc143f4d3b9d37547f244fbf67e2b30d","target":"graph","created_at":"2026-07-05T10:10:15Z","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/2502.03843/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality, large-scale instructions are crucial for aligning large language models (LLMs), however, there is a severe shortage of instruction in the field of natural language understanding (NLU). Previous works on constructing NLU instructions mainly focus on information extraction (IE), neglecting tasks such as machine reading comprehension, question answering, and text classification. Furthermore, the lack of diversity in the data has led to a decreased generalization ability of trained LLMs in other NLU tasks and a noticeable decline in the fundamental model's general capabilities. To ad","authors_text":"Honghao Gui, Jun Xu, Jun Zhou, Lei Liang, Lin Yuan, Mengshu Sun, Zhiqiang Zhang","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:53:40Z","title":"Improving Natural Language Understanding for LLMs via Large-Scale Instruction Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.03843","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":"sha256:0bf36ffa6ed43e847c759178cbc76f669340d15136582121a4cb37d42777808e","target":"record","created_at":"2026-07-05T10:10:15Z","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":"a4ee7025c35d7e49c5f87a7551da8395ba371b5cd741d83c5fde87ce3e4c445a","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-06T07:53:40Z","title_canon_sha256":"e9f5079fbbfbff3f3db782848442a2da73c4d1f42ddb980bad9a1fee4cb69bb1"},"schema_version":"1.0","source":{"id":"2502.03843","kind":"arxiv","version":1}},"canonical_sha256":"52f24d54ebd18733375a0c1d66ebee8cbcaae4e93a281f3f6675879e6ff45644","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"52f24d54ebd18733375a0c1d66ebee8cbcaae4e93a281f3f6675879e6ff45644","first_computed_at":"2026-07-05T10:10:15.773274Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:10:15.773274Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8NlK4DTpHllSb1WiAUe3gkQ4hIhwdUO4ylhTs83w45qCCTbBiFTmsQC+09BJSU+v8uKB+fowAOSHFOlXEXWTDg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:10:15.773734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.03843","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0bf36ffa6ed43e847c759178cbc76f669340d15136582121a4cb37d42777808e","sha256:9c34dc89fa98a4f20707bd4338a4ec4fbc143f4d3b9d37547f244fbf67e2b30d"],"state_sha256":"923c2afd690dd372b109cec66d05eb9fc2ad4e3d276c8780ab3caaccf55fd319"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FNX0NcZyJKex7oK9vw+7PwM9X1yEWrikBI2qHRpL1gqCNOO0/2iQ1Q32NhEQjUP/VV7jMxlw8uNkj/Z7ngWfDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T02:03:48.604852Z","bundle_sha256":"614822dd664d73555544131263bd32cdeb54459236638bb88e3ba995dc22409c"}}