{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:WK73HPJO432IIDCHBFL6SUJMWG","short_pith_number":"pith:WK73HPJO","canonical_record":{"source":{"id":"2308.07074","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-14T11:16:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3e4177e83c95558b33c1010cbe651093b4deb52cd8a9532c51f700ec09ef11b1","abstract_canon_sha256":"bce5b843684cba570157a5a0e31d7ba89ba0c708114d61100df575fe7e2a6130"},"schema_version":"1.0"},"canonical_sha256":"b2bfb3bd2ee6f4840c470957e9512cb1bda5dce99dcaa46be18fc119c2cb2d71","source":{"kind":"arxiv","id":"2308.07074","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.07074","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"arxiv_version","alias_value":"2308.07074v2","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07074","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"pith_short_12","alias_value":"WK73HPJO432I","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"pith_short_16","alias_value":"WK73HPJO432IIDCH","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"pith_short_8","alias_value":"WK73HPJO","created_at":"2026-07-05T06:41:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:WK73HPJO432IIDCHBFL6SUJMWG","target":"record","payload":{"canonical_record":{"source":{"id":"2308.07074","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-14T11:16:28Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"3e4177e83c95558b33c1010cbe651093b4deb52cd8a9532c51f700ec09ef11b1","abstract_canon_sha256":"bce5b843684cba570157a5a0e31d7ba89ba0c708114d61100df575fe7e2a6130"},"schema_version":"1.0"},"canonical_sha256":"b2bfb3bd2ee6f4840c470957e9512cb1bda5dce99dcaa46be18fc119c2cb2d71","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:41:23.424857Z","signature_b64":"oMnS0QYMyDIU7YKtpP2ZVn5pc2wXBh8v+5S3KKO0tvUXN3BQzuQwN1c1q9oK+o88nHuQlqlghmBe0X8DVNuvAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2bfb3bd2ee6f4840c470957e9512cb1bda5dce99dcaa46be18fc119c2cb2d71","last_reissued_at":"2026-07-05T06:41:23.424345Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:41:23.424345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2308.07074","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":"2026-07-05T06:41:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gg5A4iUcrTQgk/Sp7u4PcXz5Ch7ig8pAwtD16Iy6yFFICFyYYS+scfZuLvcwWPe6DAa47acDaucTYfQmUstvCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:14:18.190362Z"},"content_sha256":"41d09bbd445ccba185367437f11e08d3f0dfc6c4bd5e557d58662eb645a52c30","schema_version":"1.0","event_id":"sha256:41d09bbd445ccba185367437f11e08d3f0dfc6c4bd5e557d58662eb645a52c30"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:WK73HPJO432IIDCHBFL6SUJMWG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chang Zhou, Chuanqi Tan, Hongyi Yuan, Jingren Zhou, Junyang Lin, Keming Lu, Runji Lin, Zheng Yuan","submitted_at":"2023-08-14T11:16:28Z","abstract_excerpt":"Foundation language models obtain the instruction-following ability through supervised fine-tuning (SFT). Diversity and complexity are considered critical factors of a successful SFT dataset, while their definitions remain obscure and lack quantitative analyses. In this work, we propose InsTag, an open-set fine-grained tagger, to tag samples within SFT datasets based on semantics and intentions and define instruction diversity and complexity regarding tags. We obtain 6.6K tags to describe comprehensive user queries. Then we analyze popular open-sourced SFT datasets and find that the model abil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07074","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/2308.07074/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":"2026-07-05T06:41:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Mv2P87fAucmLIQIfzNnzYVlI1PMsAEsmM6Y6cCvg3lemil+Va7Pao8vTKnEMzJVFIaEOowE9z+d60YO6j96cCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T22:14:18.190757Z"},"content_sha256":"b9d1d26c262fbd9282106ad1e0e4b139f0c6ff996155edccab7076a50d02fe55","schema_version":"1.0","event_id":"sha256:b9d1d26c262fbd9282106ad1e0e4b139f0c6ff996155edccab7076a50d02fe55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WK73HPJO432IIDCHBFL6SUJMWG/bundle.json","state_url":"https://pith.science/pith/WK73HPJO432IIDCHBFL6SUJMWG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WK73HPJO432IIDCHBFL6SUJMWG/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":"2026-08-17T22:14:18Z","links":{"resolver":"https://pith.science/pith/WK73HPJO432IIDCHBFL6SUJMWG","bundle":"https://pith.science/pith/WK73HPJO432IIDCHBFL6SUJMWG/bundle.json","state":"https://pith.science/pith/WK73HPJO432IIDCHBFL6SUJMWG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WK73HPJO432IIDCHBFL6SUJMWG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:WK73HPJO432IIDCHBFL6SUJMWG","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":"bce5b843684cba570157a5a0e31d7ba89ba0c708114d61100df575fe7e2a6130","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-14T11:16:28Z","title_canon_sha256":"3e4177e83c95558b33c1010cbe651093b4deb52cd8a9532c51f700ec09ef11b1"},"schema_version":"1.0","source":{"id":"2308.07074","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.07074","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"arxiv_version","alias_value":"2308.07074v2","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.07074","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"pith_short_12","alias_value":"WK73HPJO432I","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"pith_short_16","alias_value":"WK73HPJO432IIDCH","created_at":"2026-07-05T06:41:23Z"},{"alias_kind":"pith_short_8","alias_value":"WK73HPJO","created_at":"2026-07-05T06:41:23Z"}],"graph_snapshots":[{"event_id":"sha256:b9d1d26c262fbd9282106ad1e0e4b139f0c6ff996155edccab7076a50d02fe55","target":"graph","created_at":"2026-07-05T06:41:23Z","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/2308.07074/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation language models obtain the instruction-following ability through supervised fine-tuning (SFT). Diversity and complexity are considered critical factors of a successful SFT dataset, while their definitions remain obscure and lack quantitative analyses. In this work, we propose InsTag, an open-set fine-grained tagger, to tag samples within SFT datasets based on semantics and intentions and define instruction diversity and complexity regarding tags. We obtain 6.6K tags to describe comprehensive user queries. Then we analyze popular open-sourced SFT datasets and find that the model abil","authors_text":"Chang Zhou, Chuanqi Tan, Hongyi Yuan, Jingren Zhou, Junyang Lin, Keming Lu, Runji Lin, Zheng Yuan","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-14T11:16:28Z","title":"#InsTag: Instruction Tagging for Analyzing Supervised Fine-tuning of Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.07074","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":"sha256:41d09bbd445ccba185367437f11e08d3f0dfc6c4bd5e557d58662eb645a52c30","target":"record","created_at":"2026-07-05T06:41:23Z","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":"bce5b843684cba570157a5a0e31d7ba89ba0c708114d61100df575fe7e2a6130","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-08-14T11:16:28Z","title_canon_sha256":"3e4177e83c95558b33c1010cbe651093b4deb52cd8a9532c51f700ec09ef11b1"},"schema_version":"1.0","source":{"id":"2308.07074","kind":"arxiv","version":2}},"canonical_sha256":"b2bfb3bd2ee6f4840c470957e9512cb1bda5dce99dcaa46be18fc119c2cb2d71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2bfb3bd2ee6f4840c470957e9512cb1bda5dce99dcaa46be18fc119c2cb2d71","first_computed_at":"2026-07-05T06:41:23.424345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:41:23.424345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oMnS0QYMyDIU7YKtpP2ZVn5pc2wXBh8v+5S3KKO0tvUXN3BQzuQwN1c1q9oK+o88nHuQlqlghmBe0X8DVNuvAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:41:23.424857Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.07074","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41d09bbd445ccba185367437f11e08d3f0dfc6c4bd5e557d58662eb645a52c30","sha256:b9d1d26c262fbd9282106ad1e0e4b139f0c6ff996155edccab7076a50d02fe55"],"state_sha256":"21852597fbc280c6045f71e412df906cc055f745934f3ade68b91281a4556790"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"teNhO0OYtHa0j2KsfhqMqOWthwNnMVoFz5EncTH/RWdiD/6aX7UZWL0PFOUCDN5B6d2yq6UFTeCVZnZQEVWxCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T22:14:18.194775Z","bundle_sha256":"21cf97bf930165716ce4019b094c2c54aba53e814521360bf141ef9a2b3292b7"}}