{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GYDPBSIQ5W7FS3RIBYP677VZFS","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":"1815f3f05638a0c4aff7a0a69e5558d195546d03b3dc923ffcd10b503aedfa99","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T15:01:30Z","title_canon_sha256":"0ac165cbcf690c99f4ef863a6e2211b5f73fd510f340d0a8ca94f948959107dd"},"schema_version":"1.0","source":{"id":"2607.01033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01033","created_at":"2026-07-02T01:18:26Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01033v1","created_at":"2026-07-02T01:18:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01033","created_at":"2026-07-02T01:18:26Z"},{"alias_kind":"pith_short_12","alias_value":"GYDPBSIQ5W7F","created_at":"2026-07-02T01:18:26Z"},{"alias_kind":"pith_short_16","alias_value":"GYDPBSIQ5W7FS3RI","created_at":"2026-07-02T01:18:26Z"},{"alias_kind":"pith_short_8","alias_value":"GYDPBSIQ","created_at":"2026-07-02T01:18:26Z"}],"graph_snapshots":[{"event_id":"sha256:7f0f7e4d619da941004959b40ef87d4f9f9596696bf5c71eb87e24489aae783c","target":"graph","created_at":"2026-07-02T01:18:26Z","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/2607.01033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Model organisms (MOs) - language models trained to exhibit undesired or unnatural behaviours - are frequently used as testbeds for evaluating white-box interpretability techniques. Current MOs are typically constructed via post-hoc supervised fine-tuning (SFT) on behavioural transcripts or synthetic documents. Prior research has shown that interpretability methods can easily identify hidden behaviours in these MOs. However, recent work suggests that such post-hoc training methods may make interpretability unrealistically easy. We investigate this claim by constructing a suite of 54 $\\verb|OLMo","authors_text":"Andrzej Szablewski, Gabriel Konar-Steenberg, Nikita Menon, Raffaello Fornasiere, Stefan Heimersheim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T15:01:30Z","title":"The Model Organism Lottery: Model Organism Interpretability Strongly Depends on Training Methodology"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01033","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":"sha256:8eaba6e03aa9e1edfd5c1ee0ab8d323d45baf3d84b27f3d683166537eb4438cf","target":"record","created_at":"2026-07-02T01:18:26Z","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":"1815f3f05638a0c4aff7a0a69e5558d195546d03b3dc923ffcd10b503aedfa99","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-01T15:01:30Z","title_canon_sha256":"0ac165cbcf690c99f4ef863a6e2211b5f73fd510f340d0a8ca94f948959107dd"},"schema_version":"1.0","source":{"id":"2607.01033","kind":"arxiv","version":1}},"canonical_sha256":"3606f0c910edbe596e280e1feffeb92c8f3740ae703c29c111d7fb1df00c2b30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3606f0c910edbe596e280e1feffeb92c8f3740ae703c29c111d7fb1df00c2b30","first_computed_at":"2026-07-02T01:18:26.594021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T01:18:26.594021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"suVCz4wr9wA7nUgDyzEgVL/3aLdrttACPGN9y7H3yiWJ2j2Vb/4zb7IG69skSGfbOHIKu3rD1uMabCy7CcdvCA==","signature_status":"signed_v1","signed_at":"2026-07-02T01:18:26.594441Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8eaba6e03aa9e1edfd5c1ee0ab8d323d45baf3d84b27f3d683166537eb4438cf","sha256:7f0f7e4d619da941004959b40ef87d4f9f9596696bf5c71eb87e24489aae783c"],"state_sha256":"0f72049c5e909e84bb88c76cbb746bf65119b17e88c5b96b7d3ad651fb2ac0bb"}