{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YDY5DVI6CDCCKUST3WYTEHBLFE","short_pith_number":"pith:YDY5DVI6","canonical_record":{"source":{"id":"2407.08734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-11T17:59:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bca4202fcc3d5d0e9515fdfaa639c3ea400515fe1bf83be6dd99bc740a3a6e0c","abstract_canon_sha256":"8cd3df5d8992a44260c45739899dadde047caf1ebd6c984c8d09f8266ac09a40"},"schema_version":"1.0"},"canonical_sha256":"c0f1d1d51e10c4255253ddb1321c2b291ffb3d0a9e7d88b6b03f1520159c559a","source":{"kind":"arxiv","id":"2407.08734","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08734","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08734v1","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08734","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"YDY5DVI6CDCC","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"pith_short_16","alias_value":"YDY5DVI6CDCCKUST","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"pith_short_8","alias_value":"YDY5DVI6","created_at":"2026-07-05T08:42:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YDY5DVI6CDCCKUST3WYTEHBLFE","target":"record","payload":{"canonical_record":{"source":{"id":"2407.08734","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-11T17:59:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"bca4202fcc3d5d0e9515fdfaa639c3ea400515fe1bf83be6dd99bc740a3a6e0c","abstract_canon_sha256":"8cd3df5d8992a44260c45739899dadde047caf1ebd6c984c8d09f8266ac09a40"},"schema_version":"1.0"},"canonical_sha256":"c0f1d1d51e10c4255253ddb1321c2b291ffb3d0a9e7d88b6b03f1520159c559a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:42:52.125942Z","signature_b64":"tvGtM5J8zm74Uo/4C88Y8qYb5kTXdgv30/plwCwktpXE8aufAF3d53jOFcQuyGFj4eJkNlRxuISsSbzKstHFDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0f1d1d51e10c4255253ddb1321c2b291ffb3d0a9e7d88b6b03f1520159c559a","last_reissued_at":"2026-07-05T08:42:52.125543Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:42:52.125543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.08734","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":"2026-07-05T08:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SwNgd1KT8pdsj3vozCnKdlP8k4FTJ6XbG31rjR9+DxjbV2TTOw2o9XbjYoGyOIVQRIZL59kDco0j6msgaPepDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:39:48.199334Z"},"content_sha256":"155042f3e1edb1b762bc91ae5de238d787da8150626b4fdc599c7b0490fdb6ed","schema_version":"1.0","event_id":"sha256:155042f3e1edb1b762bc91ae5de238d787da8150626b4fdc599c7b0490fdb6ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YDY5DVI6CDCCKUST3WYTEHBLFE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transformer Circuit Faithfulness Metrics are not Robust","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Bilal Chughtai, Joseph Miller, William Saunders","submitted_at":"2024-07-11T17:59:00Z","abstract_excerpt":"Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subgraphs of the full model that explain behaviour on specific tasks. But how do we measure the performance of such circuits? Prior work has attempted to measure circuit 'faithfulness' -- the degree to which the circuit replicates the performance of the full model. In this work, we survey many considerations for designing experiments that measure circuit faithfulness by ablating portions of the model's computation. Conce"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08734","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/2407.08734/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":"2026-07-05T08:42:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EccWtn/mSUoOs0qwmij/JZvcjxuJF1GxsrriznEdoZpbCpUkR/IgpD8E6tWvE13dTTOvs0l9kq3g/giM5ypmBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T19:39:48.199856Z"},"content_sha256":"393204ec8e5e63f8931a60fb786f05188f135ec0e593a5e11d869418a96c84cc","schema_version":"1.0","event_id":"sha256:393204ec8e5e63f8931a60fb786f05188f135ec0e593a5e11d869418a96c84cc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDY5DVI6CDCCKUST3WYTEHBLFE/bundle.json","state_url":"https://pith.science/pith/YDY5DVI6CDCCKUST3WYTEHBLFE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDY5DVI6CDCCKUST3WYTEHBLFE/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":"2026-08-08T19:39:48Z","links":{"resolver":"https://pith.science/pith/YDY5DVI6CDCCKUST3WYTEHBLFE","bundle":"https://pith.science/pith/YDY5DVI6CDCCKUST3WYTEHBLFE/bundle.json","state":"https://pith.science/pith/YDY5DVI6CDCCKUST3WYTEHBLFE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDY5DVI6CDCCKUST3WYTEHBLFE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YDY5DVI6CDCCKUST3WYTEHBLFE","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":"8cd3df5d8992a44260c45739899dadde047caf1ebd6c984c8d09f8266ac09a40","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-11T17:59:00Z","title_canon_sha256":"bca4202fcc3d5d0e9515fdfaa639c3ea400515fe1bf83be6dd99bc740a3a6e0c"},"schema_version":"1.0","source":{"id":"2407.08734","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.08734","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"arxiv_version","alias_value":"2407.08734v1","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.08734","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"pith_short_12","alias_value":"YDY5DVI6CDCC","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"pith_short_16","alias_value":"YDY5DVI6CDCCKUST","created_at":"2026-07-05T08:42:52Z"},{"alias_kind":"pith_short_8","alias_value":"YDY5DVI6","created_at":"2026-07-05T08:42:52Z"}],"graph_snapshots":[{"event_id":"sha256:393204ec8e5e63f8931a60fb786f05188f135ec0e593a5e11d869418a96c84cc","target":"graph","created_at":"2026-07-05T08:42:52Z","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/2407.08734/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mechanistic interpretability work attempts to reverse engineer the learned algorithms present inside neural networks. One focus of this work has been to discover 'circuits' -- subgraphs of the full model that explain behaviour on specific tasks. But how do we measure the performance of such circuits? Prior work has attempted to measure circuit 'faithfulness' -- the degree to which the circuit replicates the performance of the full model. In this work, we survey many considerations for designing experiments that measure circuit faithfulness by ablating portions of the model's computation. Conce","authors_text":"Bilal Chughtai, Joseph Miller, William Saunders","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-11T17:59:00Z","title":"Transformer Circuit Faithfulness Metrics are not Robust"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.08734","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":"sha256:155042f3e1edb1b762bc91ae5de238d787da8150626b4fdc599c7b0490fdb6ed","target":"record","created_at":"2026-07-05T08:42:52Z","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":"8cd3df5d8992a44260c45739899dadde047caf1ebd6c984c8d09f8266ac09a40","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-11T17:59:00Z","title_canon_sha256":"bca4202fcc3d5d0e9515fdfaa639c3ea400515fe1bf83be6dd99bc740a3a6e0c"},"schema_version":"1.0","source":{"id":"2407.08734","kind":"arxiv","version":1}},"canonical_sha256":"c0f1d1d51e10c4255253ddb1321c2b291ffb3d0a9e7d88b6b03f1520159c559a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0f1d1d51e10c4255253ddb1321c2b291ffb3d0a9e7d88b6b03f1520159c559a","first_computed_at":"2026-07-05T08:42:52.125543Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:42:52.125543Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvGtM5J8zm74Uo/4C88Y8qYb5kTXdgv30/plwCwktpXE8aufAF3d53jOFcQuyGFj4eJkNlRxuISsSbzKstHFDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:42:52.125942Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.08734","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:155042f3e1edb1b762bc91ae5de238d787da8150626b4fdc599c7b0490fdb6ed","sha256:393204ec8e5e63f8931a60fb786f05188f135ec0e593a5e11d869418a96c84cc"],"state_sha256":"0412a2728c666797db1d08f3603b998e41ba445bcc3af3f86ac979c35d19eed1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"D1+0dLCkUAUop2KN01oTiJB25+t1gJXEPFX1YCFnwXvPk/yJwKQovItIjgQZbKE67ScYqwUYlhGyED+Vx5+sCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T19:39:48.204608Z","bundle_sha256":"a39bd87b68438869799e02ff2d0445ad9dd53697e8e042b80167d23d697f48ee"}}