{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CJM3E25JRRP4LKLWPVS6DSE665","short_pith_number":"pith:CJM3E25J","canonical_record":{"source":{"id":"2401.12631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T10:27:42Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"adaf62fec5b9727653f66186305b13991dd76946e513f400c24bd95e2dc172ec","abstract_canon_sha256":"216d06823dbd9fcf369f9837ac075d68b9c7baa6cac3091782dc26ce3d9dd101"},"schema_version":"1.0"},"canonical_sha256":"1259b26ba98c5fc5a9767d65e1c89ef7712366ea85c0292347adaf9655f01a11","source":{"kind":"arxiv","id":"2401.12631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12631","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12631v1","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12631","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"CJM3E25JRRP4","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"CJM3E25JRRP4LKLW","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"CJM3E25J","created_at":"2026-07-05T07:36:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CJM3E25JRRP4LKLWPVS6DSE665","target":"record","payload":{"canonical_record":{"source":{"id":"2401.12631","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T10:27:42Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"adaf62fec5b9727653f66186305b13991dd76946e513f400c24bd95e2dc172ec","abstract_canon_sha256":"216d06823dbd9fcf369f9837ac075d68b9c7baa6cac3091782dc26ce3d9dd101"},"schema_version":"1.0"},"canonical_sha256":"1259b26ba98c5fc5a9767d65e1c89ef7712366ea85c0292347adaf9655f01a11","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:36:33.491604Z","signature_b64":"nyyBtxRUYCNg1ToZbShZl+2i7QVDlX7xyuKR5wjyuKIlZ0OUMCwX9DMQNRJYo2/AfgxtUP8J0U0UGb7qVagdCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1259b26ba98c5fc5a9767d65e1c89ef7712366ea85c0292347adaf9655f01a11","last_reissued_at":"2026-07-05T07:36:33.491121Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:36:33.491121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.12631","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZdvOQ4fJJ8IF05fDLH+SXt7tAtAKgvrgh72Wb5B9qaRy8carkae+NiJ/DXxSGDlMaC7/VhCrIuw74n7COjiYAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:44:54.141628Z"},"content_sha256":"ff35a18c677c65f56d0c950766948bea2a67eccf8d8b7a45a2027b531eff6d2b","schema_version":"1.0","event_id":"sha256:ff35a18c677c65f56d0c950766948bea2a67eccf8d8b7a45a2027b531eff6d2b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CJM3E25JRRP4LKLWPVS6DSE665","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Reply to Makelov et al. (2023)'s \"Interpretability Illusion\" Arguments","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Aryaman Arora, Atticus Geiger, Christopher Potts, Jing Huang, Noah D. Goodman, Thomas Icard, Zhengxuan Wu","submitted_at":"2024-01-23T10:27:42Z","abstract_excerpt":"We respond to the recent paper by Makelov et al. (2023), which reviews subspace interchange intervention methods like distributed alignment search (DAS; Geiger et al. 2023) and claims that these methods potentially cause \"interpretability illusions\". We first review Makelov et al. (2023)'s technical notion of what an \"interpretability illusion\" is, and then we show that even intuitive and desirable explanations can qualify as illusions in this sense. As a result, their method of discovering \"illusions\" can reject explanations they consider \"non-illusory\". We then argue that the illusions Makel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12631","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2401.12631/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p0H8413PxYGr27aGFDGMPpfD5+VCnhrKGNbvzN5IaXh45I4MLi2/hLqlYqx9fNfWC8+Zrt6ml22aMAIJ5tz0Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T01:44:54.142234Z"},"content_sha256":"2484e5205a3b07449f74bcff383ae2413b7ee791fa824948c2a5cdb07199668e","schema_version":"1.0","event_id":"sha256:2484e5205a3b07449f74bcff383ae2413b7ee791fa824948c2a5cdb07199668e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CJM3E25JRRP4LKLWPVS6DSE665/bundle.json","state_url":"https://pith.science/pith/CJM3E25JRRP4LKLWPVS6DSE665/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CJM3E25JRRP4LKLWPVS6DSE665/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-17T01:44:54Z","links":{"resolver":"https://pith.science/pith/CJM3E25JRRP4LKLWPVS6DSE665","bundle":"https://pith.science/pith/CJM3E25JRRP4LKLWPVS6DSE665/bundle.json","state":"https://pith.science/pith/CJM3E25JRRP4LKLWPVS6DSE665/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CJM3E25JRRP4LKLWPVS6DSE665/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CJM3E25JRRP4LKLWPVS6DSE665","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":"216d06823dbd9fcf369f9837ac075d68b9c7baa6cac3091782dc26ce3d9dd101","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T10:27:42Z","title_canon_sha256":"adaf62fec5b9727653f66186305b13991dd76946e513f400c24bd95e2dc172ec"},"schema_version":"1.0","source":{"id":"2401.12631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.12631","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2401.12631v1","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.12631","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"CJM3E25JRRP4","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"CJM3E25JRRP4LKLW","created_at":"2026-07-05T07:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"CJM3E25J","created_at":"2026-07-05T07:36:33Z"}],"graph_snapshots":[{"event_id":"sha256:2484e5205a3b07449f74bcff383ae2413b7ee791fa824948c2a5cdb07199668e","target":"graph","created_at":"2026-07-05T07:36:33Z","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/2401.12631/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We respond to the recent paper by Makelov et al. (2023), which reviews subspace interchange intervention methods like distributed alignment search (DAS; Geiger et al. 2023) and claims that these methods potentially cause \"interpretability illusions\". We first review Makelov et al. (2023)'s technical notion of what an \"interpretability illusion\" is, and then we show that even intuitive and desirable explanations can qualify as illusions in this sense. As a result, their method of discovering \"illusions\" can reject explanations they consider \"non-illusory\". We then argue that the illusions Makel","authors_text":"Aryaman Arora, Atticus Geiger, Christopher Potts, Jing Huang, Noah D. Goodman, Thomas Icard, Zhengxuan Wu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T10:27:42Z","title":"A Reply to Makelov et al. (2023)'s \"Interpretability Illusion\" Arguments"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.12631","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:ff35a18c677c65f56d0c950766948bea2a67eccf8d8b7a45a2027b531eff6d2b","target":"record","created_at":"2026-07-05T07:36:33Z","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":"216d06823dbd9fcf369f9837ac075d68b9c7baa6cac3091782dc26ce3d9dd101","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-01-23T10:27:42Z","title_canon_sha256":"adaf62fec5b9727653f66186305b13991dd76946e513f400c24bd95e2dc172ec"},"schema_version":"1.0","source":{"id":"2401.12631","kind":"arxiv","version":1}},"canonical_sha256":"1259b26ba98c5fc5a9767d65e1c89ef7712366ea85c0292347adaf9655f01a11","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1259b26ba98c5fc5a9767d65e1c89ef7712366ea85c0292347adaf9655f01a11","first_computed_at":"2026-07-05T07:36:33.491121Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:36:33.491121Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nyyBtxRUYCNg1ToZbShZl+2i7QVDlX7xyuKR5wjyuKIlZ0OUMCwX9DMQNRJYo2/AfgxtUP8J0U0UGb7qVagdCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:36:33.491604Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.12631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff35a18c677c65f56d0c950766948bea2a67eccf8d8b7a45a2027b531eff6d2b","sha256:2484e5205a3b07449f74bcff383ae2413b7ee791fa824948c2a5cdb07199668e"],"state_sha256":"86161fa72dd6e232cc57375540c171e2b0eacd3f5d3604cb2387eab21f5b095e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QEUHXvXDWFVM3aGkR0/aN8RzGj6SuiEEAwp9Cct/vG3hIUmskO5LTABaKl1+BckAOFZWFY32GhjEQhKaERo1Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T01:44:54.146561Z","bundle_sha256":"6320f79b05b26ac093d94cb53a1d83db4e88b605fb82518f2d2e1fe3d0c25463"}}