{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IGR2QX6USTZZF47CVFLBCKBH4B","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":"4e8145551b26663c72128237f6fa253e0e1dcaed6a59de291d599f4376b9a241","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-18T14:55:14Z","title_canon_sha256":"3a5ee22f73ce49703a069dcae1dad6d0468ff6b89208e9f4ac94a2791f565da8"},"schema_version":"1.0","source":{"id":"2410.14516","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.14516","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"arxiv_version","alias_value":"2410.14516v5","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.14516","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"pith_short_12","alias_value":"IGR2QX6USTZZ","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"pith_short_16","alias_value":"IGR2QX6USTZZF47C","created_at":"2026-07-05T10:40:59Z"},{"alias_kind":"pith_short_8","alias_value":"IGR2QX6U","created_at":"2026-07-05T10:40:59Z"}],"graph_snapshots":[{"event_id":"sha256:2f14ec6c73c78439c2627b04c371c590e081d046b59e1656cd7d649dd03c2852","target":"graph","created_at":"2026-07-05T10:40:59Z","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/2410.14516/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-following is crucial for building AI agents with large language models (LLMs), as these models must adhere strictly to user-provided constraints and guidelines. However, LLMs often fail to follow even simple and clear instructions. To improve instruction-following behavior and prevent undesirable outputs, a deeper understanding of how LLMs' internal states relate to these outcomes is required. In this work, we investigate whether LLMs encode information in their representations that correlate with instruction-following success - a property we term knowing internally. Our analysis i","authors_text":"Andy Miller, Christina Heinze-Deml, Jaya Narain, Juyeon Heo, Kwan Ho Ryan Chan, Oussama Elachqar, Shirley Ren, Udhay Nallasamy","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-18T14:55:14Z","title":"Do LLMs \"know\" internally when they follow instructions?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.14516","kind":"arxiv","version":5},"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:ff8724e51ba42c17531c6b8449b2d16e00f435bddbfa76cc98ecee3b1fdf6d73","target":"record","created_at":"2026-07-05T10:40:59Z","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":"4e8145551b26663c72128237f6fa253e0e1dcaed6a59de291d599f4376b9a241","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-18T14:55:14Z","title_canon_sha256":"3a5ee22f73ce49703a069dcae1dad6d0468ff6b89208e9f4ac94a2791f565da8"},"schema_version":"1.0","source":{"id":"2410.14516","kind":"arxiv","version":5}},"canonical_sha256":"41a3a85fd494f392f3e2a956112827e052ede37e9632c10427ae8d2b6626ec73","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"41a3a85fd494f392f3e2a956112827e052ede37e9632c10427ae8d2b6626ec73","first_computed_at":"2026-07-05T10:40:59.064099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:40:59.064099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PsSlE4mIx3miz3u99cAs7zRx+GvYQxSc/8HDMVUndDvM4QSTKu++ahXSdx70DK0yACvnbKmd6BLhfN2wj0OBBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:40:59.064613Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.14516","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff8724e51ba42c17531c6b8449b2d16e00f435bddbfa76cc98ecee3b1fdf6d73","sha256:2f14ec6c73c78439c2627b04c371c590e081d046b59e1656cd7d649dd03c2852"],"state_sha256":"6cdcda19792532b83f03b4ecd1a3f12aba7b8620b86c61d5bdbb32196f6f84ba"}