{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:HDS6VKIQFEZPJHCHE4FVVZ2DQI","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":"8420feeef92efbc8f600ee0c8addc8d65866f6e2273d48fe433b5a629e11f16a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:51:03Z","title_canon_sha256":"831a1cad0ab1b5a095c9d835728cbe1c39ecf6c0be882621e8667c7f0c35e64f"},"schema_version":"1.0","source":{"id":"2505.18557","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.18557","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.18557v2","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18557","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"pith_short_12","alias_value":"HDS6VKIQFEZP","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"pith_short_16","alias_value":"HDS6VKIQFEZPJHCH","created_at":"2026-07-05T11:14:07Z"},{"alias_kind":"pith_short_8","alias_value":"HDS6VKIQ","created_at":"2026-07-05T11:14:07Z"}],"graph_snapshots":[{"event_id":"sha256:94aa2e4e31d66aff7e31063350c0430947095a1757475477b2697d359ff2c2de","target":"graph","created_at":"2026-07-05T11:14:07Z","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/2505.18557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"High-quality instruction data is crucial for developing large language models (LLMs), yet existing approaches struggle to effectively control instruction complexity. We present TAG-INSTRUCT, a novel framework that enhances instruction complexity through structured semantic compression and controlled difficulty augmentation. Unlike previous prompt-based methods operating on raw text, TAG-INSTRUCT compresses instructions into a compact tag space and systematically enhances complexity through RL-guided tag expansion. Through extensive experiments, we show that TAG-INSTRUCT outperforms existing in","authors_text":"Guanhua Chen, He Zhu, Junyou Su, Wenjia Zhang, Xingwei He, Yun Chen, Zhiwen Ruan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:51:03Z","title":"TAG-INSTRUCT: Controlled Instruction Complexity Enhancement through Structure-based Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18557","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:c908f14af35cd3239bd344ccc7b765e4c655d614be0dbbea69390246ff8fb6ff","target":"record","created_at":"2026-07-05T11:14:07Z","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":"8420feeef92efbc8f600ee0c8addc8d65866f6e2273d48fe433b5a629e11f16a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-24T06:51:03Z","title_canon_sha256":"831a1cad0ab1b5a095c9d835728cbe1c39ecf6c0be882621e8667c7f0c35e64f"},"schema_version":"1.0","source":{"id":"2505.18557","kind":"arxiv","version":2}},"canonical_sha256":"38e5eaa9102932f49c47270b5ae74382230dbe62afef41d961383d1998bb6528","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38e5eaa9102932f49c47270b5ae74382230dbe62afef41d961383d1998bb6528","first_computed_at":"2026-07-05T11:14:07.802797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:14:07.802797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ei+oGDoEhiK7g2Bqnl/30JJVcqsEQyxIztHwfKC3WQ9MJMqZDtrV+BqmcugfgIRzWSH86yg6OO5V6TVvrgEzBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:14:07.803333Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.18557","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c908f14af35cd3239bd344ccc7b765e4c655d614be0dbbea69390246ff8fb6ff","sha256:94aa2e4e31d66aff7e31063350c0430947095a1757475477b2697d359ff2c2de"],"state_sha256":"a20b68f6d0dab6b375b035a7a756b2c25f70d8c386376121088b8c9c1db81f2e"}