{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SX6F7LLLSTWW3NABL2XDWRYM6U","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":"a71bef9e850bc5ecd87a1be96d021484947e254abeeb8c50fdaecb07a6634057","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T17:43:44Z","title_canon_sha256":"a4f8f93df4c32b48ff9c882f5d1926604f25814ee4e1bf22f5196d7e33aa6d31"},"schema_version":"1.0","source":{"id":"2606.32008","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.32008","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"arxiv_version","alias_value":"2606.32008v1","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.32008","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"pith_short_12","alias_value":"SX6F7LLLSTWW","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"pith_short_16","alias_value":"SX6F7LLLSTWW3NAB","created_at":"2026-07-01T01:18:28Z"},{"alias_kind":"pith_short_8","alias_value":"SX6F7LLL","created_at":"2026-07-01T01:18:28Z"}],"graph_snapshots":[{"event_id":"sha256:54c1d95ed8ed3ea378c8698fce5dd37a1de6a3c6d9521057f2726fb0c9ad89e0","target":"graph","created_at":"2026-07-01T01:18:28Z","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/2606.32008/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mechanistic interpretability (MI) requires full access to model internals, yet the APIs for most widely deployed language models at best expose log-probabilities over output tokens. This creates a surrogate problem: when do measurements made on open models allow us to make claims about a closed model? We evaluate surrogate fidelity at the prediction, attribution, and representation levels. For binary classification tasks, log-odds provide an API-compatible scalar readout of the model's representation space, and leave-one-out attributions provide insight into model behavior. Across eleven model","authors_text":"Aobo Yang, Ayush Warikoo, Chia-Tse Shao, Nehal Bandi, Philippe Chlenski, Vivek Miglani, Yingxiao Ye, Zachariah Carmichael","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T17:43:44Z","title":"Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.32008","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:e56ed100b1140c7879efc3f25ac6a3a0a6022c2ddb37cb495412b04f55a10200","target":"record","created_at":"2026-07-01T01:18:28Z","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":"a71bef9e850bc5ecd87a1be96d021484947e254abeeb8c50fdaecb07a6634057","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-30T17:43:44Z","title_canon_sha256":"a4f8f93df4c32b48ff9c882f5d1926604f25814ee4e1bf22f5196d7e33aa6d31"},"schema_version":"1.0","source":{"id":"2606.32008","kind":"arxiv","version":1}},"canonical_sha256":"95fc5fad6b94ed6db4015eae3b470cf50167147d39fb354c1250a3925fd04464","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"95fc5fad6b94ed6db4015eae3b470cf50167147d39fb354c1250a3925fd04464","first_computed_at":"2026-07-01T01:18:28.938899Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-01T01:18:28.938899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7vwR1j0+Nxyd4tcvkWhLs9F8nT5kzAouIO32czFSCXCjHbRsXDRHIzTWWoOfB6CGaXJ+goUBMHqSKDzBCbn/Cg==","signature_status":"signed_v1","signed_at":"2026-07-01T01:18:28.939346Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.32008","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e56ed100b1140c7879efc3f25ac6a3a0a6022c2ddb37cb495412b04f55a10200","sha256:54c1d95ed8ed3ea378c8698fce5dd37a1de6a3c6d9521057f2726fb0c9ad89e0"],"state_sha256":"72ab65dd196a39f1afaf6611f2686815496e17c7dd6c18a0a4bee8992f2ff140"}