{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5EI4AKGLB5W43RIBFIMBCYT4YI","short_pith_number":"pith:5EI4AKGL","canonical_record":{"source":{"id":"2304.14997","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T17:36:53Z","cross_cats_sorted":[],"title_canon_sha256":"967cdeb4ffeedab758609f81f8eeada1617f415252dbe3d6918ca893ccb723d9","abstract_canon_sha256":"44381c8c5d968c594073dcb6cc52e4e36874fa8d8b33d717b5b290392efaa115"},"schema_version":"1.0"},"canonical_sha256":"e911c028cb0f6dcdc5012a1811627cc225c6dce8db830d4a06414e33efadaf5c","source":{"kind":"arxiv","id":"2304.14997","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14997","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14997v4","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14997","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"5EI4AKGLB5W4","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"5EI4AKGLB5W43RIB","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"5EI4AKGL","created_at":"2026-07-05T07:06:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5EI4AKGLB5W43RIBFIMBCYT4YI","target":"record","payload":{"canonical_record":{"source":{"id":"2304.14997","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T17:36:53Z","cross_cats_sorted":[],"title_canon_sha256":"967cdeb4ffeedab758609f81f8eeada1617f415252dbe3d6918ca893ccb723d9","abstract_canon_sha256":"44381c8c5d968c594073dcb6cc52e4e36874fa8d8b33d717b5b290392efaa115"},"schema_version":"1.0"},"canonical_sha256":"e911c028cb0f6dcdc5012a1811627cc225c6dce8db830d4a06414e33efadaf5c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:06:26.203280Z","signature_b64":"XuFZ6ztGndwYE/y5tR7TqdgbgVb5tsk5mdZp9Vq0W1cY1eYKvHAeJEQfJMN6m0oXCZriYj3HhVMHus1fuHCOAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e911c028cb0f6dcdc5012a1811627cc225c6dce8db830d4a06414e33efadaf5c","last_reissued_at":"2026-07-05T07:06:26.202768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:06:26.202768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.14997","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iGkpjP85Cw4fBI2fZfzpraxc3/8rdid1cdbEbbwJA24Rc2oQ6t5HcI4l8q7Ps3LPGRjDdHvBUBI3qM/A0K7uBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:48:00.657550Z"},"content_sha256":"b0fb841aacd76f5d42638bd425b616f97dbf7a4944d05404b98270969c4b1d54","schema_version":"1.0","event_id":"sha256:b0fb841aacd76f5d42638bd425b616f97dbf7a4944d05404b98270969c4b1d54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5EI4AKGLB5W43RIBFIMBCYT4YI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Automated Circuit Discovery for Mechanistic Interpretability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adri\\`a Garriga-Alonso, Aengus Lynch, Arthur Conmy, Augustine N. Mavor-Parker, Stefan Heimersheim","submitted_at":"2023-04-28T17:36:53Z","abstract_excerpt":"Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, researchers choose a metric and dataset that elicit the desired model behavior. Then, they apply activation patching to find which abstract neural network units are involved in the behavior. By varying the dataset, metric, and units under investigation, researchers can understand the functionality of each component. We automate one of the process' steps: to identify the circuit "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14997","kind":"arxiv","version":4},"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/2304.14997/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":"2026-07-05T07:06:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8vAeMN770ic4+7HzMq78p0cQkRZRnIRagZVK6pOmza8R5qW54rMuFzK5n/7DAjYl1/tzZH/HDrx9CvC6OmdhBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T01:48:00.658051Z"},"content_sha256":"91f300bd2956e168b28ea396798da22da087e9e66c02653f6462aa0f57082c91","schema_version":"1.0","event_id":"sha256:91f300bd2956e168b28ea396798da22da087e9e66c02653f6462aa0f57082c91"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5EI4AKGLB5W43RIBFIMBCYT4YI/bundle.json","state_url":"https://pith.science/pith/5EI4AKGLB5W43RIBFIMBCYT4YI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5EI4AKGLB5W43RIBFIMBCYT4YI/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":"2026-08-04T01:48:00Z","links":{"resolver":"https://pith.science/pith/5EI4AKGLB5W43RIBFIMBCYT4YI","bundle":"https://pith.science/pith/5EI4AKGLB5W43RIBFIMBCYT4YI/bundle.json","state":"https://pith.science/pith/5EI4AKGLB5W43RIBFIMBCYT4YI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5EI4AKGLB5W43RIBFIMBCYT4YI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5EI4AKGLB5W43RIBFIMBCYT4YI","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":"44381c8c5d968c594073dcb6cc52e4e36874fa8d8b33d717b5b290392efaa115","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T17:36:53Z","title_canon_sha256":"967cdeb4ffeedab758609f81f8eeada1617f415252dbe3d6918ca893ccb723d9"},"schema_version":"1.0","source":{"id":"2304.14997","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.14997","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"arxiv_version","alias_value":"2304.14997v4","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14997","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_12","alias_value":"5EI4AKGLB5W4","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_16","alias_value":"5EI4AKGLB5W43RIB","created_at":"2026-07-05T07:06:26Z"},{"alias_kind":"pith_short_8","alias_value":"5EI4AKGL","created_at":"2026-07-05T07:06:26Z"}],"graph_snapshots":[{"event_id":"sha256:91f300bd2956e168b28ea396798da22da087e9e66c02653f6462aa0f57082c91","target":"graph","created_at":"2026-07-05T07:06:26Z","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/2304.14997/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Through considerable effort and intuition, several recent works have reverse-engineered nontrivial behaviors of transformer models. This paper systematizes the mechanistic interpretability process they followed. First, researchers choose a metric and dataset that elicit the desired model behavior. Then, they apply activation patching to find which abstract neural network units are involved in the behavior. By varying the dataset, metric, and units under investigation, researchers can understand the functionality of each component. We automate one of the process' steps: to identify the circuit ","authors_text":"Adri\\`a Garriga-Alonso, Aengus Lynch, Arthur Conmy, Augustine N. Mavor-Parker, Stefan Heimersheim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T17:36:53Z","title":"Towards Automated Circuit Discovery for Mechanistic Interpretability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14997","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:b0fb841aacd76f5d42638bd425b616f97dbf7a4944d05404b98270969c4b1d54","target":"record","created_at":"2026-07-05T07:06:26Z","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":"44381c8c5d968c594073dcb6cc52e4e36874fa8d8b33d717b5b290392efaa115","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T17:36:53Z","title_canon_sha256":"967cdeb4ffeedab758609f81f8eeada1617f415252dbe3d6918ca893ccb723d9"},"schema_version":"1.0","source":{"id":"2304.14997","kind":"arxiv","version":4}},"canonical_sha256":"e911c028cb0f6dcdc5012a1811627cc225c6dce8db830d4a06414e33efadaf5c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e911c028cb0f6dcdc5012a1811627cc225c6dce8db830d4a06414e33efadaf5c","first_computed_at":"2026-07-05T07:06:26.202768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:06:26.202768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XuFZ6ztGndwYE/y5tR7TqdgbgVb5tsk5mdZp9Vq0W1cY1eYKvHAeJEQfJMN6m0oXCZriYj3HhVMHus1fuHCOAw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:06:26.203280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.14997","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0fb841aacd76f5d42638bd425b616f97dbf7a4944d05404b98270969c4b1d54","sha256:91f300bd2956e168b28ea396798da22da087e9e66c02653f6462aa0f57082c91"],"state_sha256":"87cae487fa732828bfb6c5c2a94c304b0e33390b85a9f8b78e481a6e0cf18417"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rIXEYbhka0oAhv/V07r+urx53GpotstrWhuVDMJ+FFLNUBToFu/McObkUNsbmf7mGKxNBCrfa6yli5rD+WIDAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T01:48:00.663205Z","bundle_sha256":"117b50b3250e19e85db42bf2b402c3496e8840ebbff659f444e516748d63aedc"}}