{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RJQFVFW77TKSJZJKCW3LH5TPKT","short_pith_number":"pith:RJQFVFW7","schema_version":"1.0","canonical_sha256":"8a605a96dffcd524e52a15b6b3f66f54e89ab05e64188992095a8acfb2cd211b","source":{"kind":"arxiv","id":"2410.09087","version":1},"attestation_state":"computed","paper":{"title":"Mechanistic?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Naomi Saphra, Sarah Wiegreffe","submitted_at":"2024-10-07T15:02:12Z","abstract_excerpt":"The rise of the term \"mechanistic interpretability\" has accompanied increasing interest in understanding neural models -- particularly language models. However, this jargon has also led to a fair amount of confusion. So, what does it mean to be \"mechanistic\"? We describe four uses of the term in interpretability research. The most narrow technical definition requires a claim of causality, while a broader technical definition allows for any exploration of a model's internals. However, the term also has a narrow cultural definition describing a cultural movement. To understand this semantic drif"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2410.09087","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-10-07T15:02:12Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"dc36a94f539c989ca42dfafc215bb0b15789ec92067421380b03028c27edbc81","abstract_canon_sha256":"ca80928ed04576027d3e0c4057e9c41eaef6d5928f59cdb7554efb1ffda8758d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:19:33.831535Z","signature_b64":"mh2RXklFofyNXUlBt3QLR1f33L3px/xsLky5swE0T3I0rJnBjQc7auQjpQxrPVOxoKCtds48bumAfoc8PNpaCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a605a96dffcd524e52a15b6b3f66f54e89ab05e64188992095a8acfb2cd211b","last_reissued_at":"2026-07-05T09:19:33.831060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:19:33.831060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mechanistic?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Naomi Saphra, Sarah Wiegreffe","submitted_at":"2024-10-07T15:02:12Z","abstract_excerpt":"The rise of the term \"mechanistic interpretability\" has accompanied increasing interest in understanding neural models -- particularly language models. However, this jargon has also led to a fair amount of confusion. So, what does it mean to be \"mechanistic\"? We describe four uses of the term in interpretability research. The most narrow technical definition requires a claim of causality, while a broader technical definition allows for any exploration of a model's internals. However, the term also has a narrow cultural definition describing a cultural movement. To understand this semantic drif"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.09087","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/2410.09087/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2410.09087","created_at":"2026-07-05T09:19:33.831128+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.09087v1","created_at":"2026-07-05T09:19:33.831128+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.09087","created_at":"2026-07-05T09:19:33.831128+00:00"},{"alias_kind":"pith_short_12","alias_value":"RJQFVFW77TKS","created_at":"2026-07-05T09:19:33.831128+00:00"},{"alias_kind":"pith_short_16","alias_value":"RJQFVFW77TKSJZJK","created_at":"2026-07-05T09:19:33.831128+00:00"},{"alias_kind":"pith_short_8","alias_value":"RJQFVFW7","created_at":"2026-07-05T09:19:33.831128+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26523","citing_title":"Radical AI Interpretability","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2506.18852","citing_title":"Mechanistic Interpretability Needs Philosophy","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2509.13316","citing_title":"Do Activation Verbalization Methods Convey Privileged Information?","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14004","citing_title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","ref_index":263,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12412","citing_title":"Stories in Space: In-Context Learning Trajectories in Conceptual Belief Space","ref_index":129,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14090","citing_title":"From Weights to Activations: Is Steering the Next Frontier of Adaptation?","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01148","citing_title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","ref_index":119,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05115","citing_title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","ref_index":114,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RJQFVFW77TKSJZJKCW3LH5TPKT","json":"https://pith.science/pith/RJQFVFW77TKSJZJKCW3LH5TPKT.json","graph_json":"https://pith.science/api/pith-number/RJQFVFW77TKSJZJKCW3LH5TPKT/graph.json","events_json":"https://pith.science/api/pith-number/RJQFVFW77TKSJZJKCW3LH5TPKT/events.json","paper":"https://pith.science/paper/RJQFVFW7"},"agent_actions":{"view_html":"https://pith.science/pith/RJQFVFW77TKSJZJKCW3LH5TPKT","download_json":"https://pith.science/pith/RJQFVFW77TKSJZJKCW3LH5TPKT.json","view_paper":"https://pith.science/paper/RJQFVFW7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.09087&json=true","fetch_graph":"https://pith.science/api/pith-number/RJQFVFW77TKSJZJKCW3LH5TPKT/graph.json","fetch_events":"https://pith.science/api/pith-number/RJQFVFW77TKSJZJKCW3LH5TPKT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RJQFVFW77TKSJZJKCW3LH5TPKT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RJQFVFW77TKSJZJKCW3LH5TPKT/action/storage_attestation","attest_author":"https://pith.science/pith/RJQFVFW77TKSJZJKCW3LH5TPKT/action/author_attestation","sign_citation":"https://pith.science/pith/RJQFVFW77TKSJZJKCW3LH5TPKT/action/citation_signature","submit_replication":"https://pith.science/pith/RJQFVFW77TKSJZJKCW3LH5TPKT/action/replication_record"}},"created_at":"2026-07-05T09:19:33.831128+00:00","updated_at":"2026-07-05T09:19:33.831128+00:00"}