{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LMYV4P2H3VYCWGVB5RU273CV6C","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":"f52885caa7c152cea14b1e95eba941b2ee30c901ee3d3d34142f52a3d4cdb461","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T18:33:48Z","title_canon_sha256":"aa7f10ca25dc67537e51e885b31bd35b104dce99b93dadb90621c58c99a572db"},"schema_version":"1.0","source":{"id":"2401.06102","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.06102","created_at":"2026-07-05T08:28:36Z"},{"alias_kind":"arxiv_version","alias_value":"2401.06102v4","created_at":"2026-07-05T08:28:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.06102","created_at":"2026-07-05T08:28:36Z"},{"alias_kind":"pith_short_12","alias_value":"LMYV4P2H3VYC","created_at":"2026-07-05T08:28:36Z"},{"alias_kind":"pith_short_16","alias_value":"LMYV4P2H3VYCWGVB","created_at":"2026-07-05T08:28:36Z"},{"alias_kind":"pith_short_8","alias_value":"LMYV4P2H","created_at":"2026-07-05T08:28:36Z"}],"graph_snapshots":[{"event_id":"sha256:63c83d1740c619248b8b667e81403c578d874718d1a081956b578db8466e8e8a","target":"graph","created_at":"2026-07-05T08:28:36Z","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/2401.06102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding the internal representations of large language models (LLMs) can help explain models' behavior and verify their alignment with human values. Given the capabilities of LLMs in generating human-understandable text, we propose leveraging the model itself to explain its internal representations in natural language. We introduce a framework called Patchscopes and show how it can be used to answer a wide range of questions about an LLM's computation. We show that many prior interpretability methods based on projecting representations into the vocabulary space and intervening on the LLM","authors_text":"Adam Pearce, Asma Ghandeharioun, Avi Caciularu, Lucas Dixon, Mor Geva","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T18:33:48Z","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.06102","kind":"arxiv","version":4},"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":"sha256:9cad65c8ba5a0392d7a4fc840f6c70b46ef9484f3c84f0581a43366e897235fa","target":"record","created_at":"2026-07-05T08:28:36Z","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":"f52885caa7c152cea14b1e95eba941b2ee30c901ee3d3d34142f52a3d4cdb461","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-11T18:33:48Z","title_canon_sha256":"aa7f10ca25dc67537e51e885b31bd35b104dce99b93dadb90621c58c99a572db"},"schema_version":"1.0","source":{"id":"2401.06102","kind":"arxiv","version":4}},"canonical_sha256":"5b315e3f47dd702b1aa1ec69afec55f0ab6b88c36029c58f4bd2b815c129aea5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b315e3f47dd702b1aa1ec69afec55f0ab6b88c36029c58f4bd2b815c129aea5","first_computed_at":"2026-07-05T08:28:36.882411Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:28:36.882411Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1yNEmZPeNN8rkzTfPlxWozMBT99Ol2sKhvNlJkw4Zuj04oOwoem6t2hEETqsfoLGHLHyUKW9YcXy37wGDW6+BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:28:36.882852Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.06102","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9cad65c8ba5a0392d7a4fc840f6c70b46ef9484f3c84f0581a43366e897235fa","sha256:63c83d1740c619248b8b667e81403c578d874718d1a081956b578db8466e8e8a"],"state_sha256":"3ca833928f50866d21e2d2eb028c3c0fbcb8db37869663f31ff9feccbfacbbc1"}