{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZSHOEV2LLE5PNHVEGVYTRNXCWR","short_pith_number":"pith:ZSHOEV2L","canonical_record":{"source":{"id":"2303.14742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-26T14:49:37Z","cross_cats_sorted":[],"title_canon_sha256":"52d825d9da388203f9282401157e95dd0682656e664c17ae2435378f1d34f1cf","abstract_canon_sha256":"7c404860cdbfc0654988ca20f9577f10fe518c0e311898bfbe930e4d7c47ab02"},"schema_version":"1.0"},"canonical_sha256":"cc8ee2574b593af69ea4357138b6e2b46ff0636057b58dd65fcb689bab79fd2c","source":{"kind":"arxiv","id":"2303.14742","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14742","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14742v1","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14742","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZSHOEV2LLE5P","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"ZSHOEV2LLE5PNHVE","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"ZSHOEV2L","created_at":"2026-07-05T05:54:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZSHOEV2LLE5PNHVEGVYTRNXCWR","target":"record","payload":{"canonical_record":{"source":{"id":"2303.14742","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-26T14:49:37Z","cross_cats_sorted":[],"title_canon_sha256":"52d825d9da388203f9282401157e95dd0682656e664c17ae2435378f1d34f1cf","abstract_canon_sha256":"7c404860cdbfc0654988ca20f9577f10fe518c0e311898bfbe930e4d7c47ab02"},"schema_version":"1.0"},"canonical_sha256":"cc8ee2574b593af69ea4357138b6e2b46ff0636057b58dd65fcb689bab79fd2c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:54:45.578095Z","signature_b64":"ET3tBBzH+YMl9wE026CIZZxn+/esTKfd7+WnhZzsqr7FBKJkHj7Zw7w0mV564TU/b9H8vpt9jOllEvePyEOMAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc8ee2574b593af69ea4357138b6e2b46ff0636057b58dd65fcb689bab79fd2c","last_reissued_at":"2026-07-05T05:54:45.577604Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:54:45.577604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.14742","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":"2026-07-05T05:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CU5Lt2yee+YugCqpEFd+0nKnZQ7p+YUozqscC8RwyglXzwo5uEIHpnZFjNO/ug1GqVVBJGrfqoDReBDck7sGAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:15:10.382177Z"},"content_sha256":"b2832d3ba62785243736462ab86ff9b48a496c56017c4f817e3d9fa23e6d4d65","schema_version":"1.0","event_id":"sha256:b2832d3ba62785243736462ab86ff9b48a496c56017c4f817e3d9fa23e6d4d65"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZSHOEV2LLE5PNHVEGVYTRNXCWR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Baochang Ma, Lei Zhang, Qiang Niu, Xiangang Li, Yan Gong, Yiping Peng, Yong Deng, Yunjie Ji","submitted_at":"2023-03-26T14:49:37Z","abstract_excerpt":"The success of ChatGPT has recently attracted numerous efforts to replicate it, with instruction-tuning strategies being a key factor in achieving remarkable results. Instruction-tuning not only significantly enhances the model's performance and generalization but also makes the model's generated results more consistent with human speech patterns. However current research rarely studies the impact of different amounts of instruction data on model performance, especially in the real-world use cases. In this paper we explore the performance of large language models based on instruction tuning ac"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14742","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/2303.14742/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":"2026-07-05T05:54:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ysz5AXSXeu00PgXJ8VbYqJZ8GlBQ/8fxRabCRBCsenwzPp1G8XpbcBK+O3/kRQJIZwa+MYjSlfrmhNLPp3ALCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T18:15:10.382549Z"},"content_sha256":"dcc93fa55407df5af03d9983392fbe902ab47e6d544ece4a9ae040b86902e72c","schema_version":"1.0","event_id":"sha256:dcc93fa55407df5af03d9983392fbe902ab47e6d544ece4a9ae040b86902e72c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZSHOEV2LLE5PNHVEGVYTRNXCWR/bundle.json","state_url":"https://pith.science/pith/ZSHOEV2LLE5PNHVEGVYTRNXCWR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZSHOEV2LLE5PNHVEGVYTRNXCWR/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":"2026-07-06T18:15:10Z","links":{"resolver":"https://pith.science/pith/ZSHOEV2LLE5PNHVEGVYTRNXCWR","bundle":"https://pith.science/pith/ZSHOEV2LLE5PNHVEGVYTRNXCWR/bundle.json","state":"https://pith.science/pith/ZSHOEV2LLE5PNHVEGVYTRNXCWR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZSHOEV2LLE5PNHVEGVYTRNXCWR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZSHOEV2LLE5PNHVEGVYTRNXCWR","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":"7c404860cdbfc0654988ca20f9577f10fe518c0e311898bfbe930e4d7c47ab02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-26T14:49:37Z","title_canon_sha256":"52d825d9da388203f9282401157e95dd0682656e664c17ae2435378f1d34f1cf"},"schema_version":"1.0","source":{"id":"2303.14742","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.14742","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"arxiv_version","alias_value":"2303.14742v1","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.14742","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"pith_short_12","alias_value":"ZSHOEV2LLE5P","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"pith_short_16","alias_value":"ZSHOEV2LLE5PNHVE","created_at":"2026-07-05T05:54:45Z"},{"alias_kind":"pith_short_8","alias_value":"ZSHOEV2L","created_at":"2026-07-05T05:54:45Z"}],"graph_snapshots":[{"event_id":"sha256:dcc93fa55407df5af03d9983392fbe902ab47e6d544ece4a9ae040b86902e72c","target":"graph","created_at":"2026-07-05T05:54:45Z","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/2303.14742/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of ChatGPT has recently attracted numerous efforts to replicate it, with instruction-tuning strategies being a key factor in achieving remarkable results. Instruction-tuning not only significantly enhances the model's performance and generalization but also makes the model's generated results more consistent with human speech patterns. However current research rarely studies the impact of different amounts of instruction data on model performance, especially in the real-world use cases. In this paper we explore the performance of large language models based on instruction tuning ac","authors_text":"Baochang Ma, Lei Zhang, Qiang Niu, Xiangang Li, Yan Gong, Yiping Peng, Yong Deng, Yunjie Ji","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-26T14:49:37Z","title":"Exploring the Impact of Instruction Data Scaling on Large Language Models: An Empirical Study on Real-World Use Cases"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.14742","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:b2832d3ba62785243736462ab86ff9b48a496c56017c4f817e3d9fa23e6d4d65","target":"record","created_at":"2026-07-05T05:54:45Z","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":"7c404860cdbfc0654988ca20f9577f10fe518c0e311898bfbe930e4d7c47ab02","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-26T14:49:37Z","title_canon_sha256":"52d825d9da388203f9282401157e95dd0682656e664c17ae2435378f1d34f1cf"},"schema_version":"1.0","source":{"id":"2303.14742","kind":"arxiv","version":1}},"canonical_sha256":"cc8ee2574b593af69ea4357138b6e2b46ff0636057b58dd65fcb689bab79fd2c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cc8ee2574b593af69ea4357138b6e2b46ff0636057b58dd65fcb689bab79fd2c","first_computed_at":"2026-07-05T05:54:45.577604Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:54:45.577604Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ET3tBBzH+YMl9wE026CIZZxn+/esTKfd7+WnhZzsqr7FBKJkHj7Zw7w0mV564TU/b9H8vpt9jOllEvePyEOMAw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:54:45.578095Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.14742","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b2832d3ba62785243736462ab86ff9b48a496c56017c4f817e3d9fa23e6d4d65","sha256:dcc93fa55407df5af03d9983392fbe902ab47e6d544ece4a9ae040b86902e72c"],"state_sha256":"58d090a70fe88bc42519e962f5d0ae0996043e163d7b836aa5f9cccd0668807e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Bua5k9+BPCp0SP2FjUCW11uC6v6PvI5Pgu5j7xgUYMZg3IuMi7a6frssx2lnWbpO22nMAtSMMxgBZZFqddTXCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T18:15:10.384467Z","bundle_sha256":"8859e1d6b5b81077d3e43cb235f8c34b18ab6f635e1d571940205518b140f515"}}