{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:NK6FYN4WD2Z4FVFFFLX2DZBPOU","short_pith_number":"pith:NK6FYN4W","schema_version":"1.0","canonical_sha256":"6abc5c37961eb3c2d4a52aefa1e42f7537bfac6c5e99878e0c21f2cb6991707e","source":{"kind":"arxiv","id":"2207.13243","version":6},"attestation_state":"computed","paper":{"title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Anson Ho, Dylan Hadfield-Menell, Stephen Casper, Tilman R\\\"auker","submitted_at":"2022-07-27T01:59:13Z","abstract_excerpt":"The last decade of machine learning has seen drastic increases in scale and capabilities. Deep neural networks (DNNs) are increasingly being deployed in the real world. However, they are difficult to analyze, raising concerns about using them without a rigorous understanding of how they function. Effective tools for interpreting them will be important for building more trustworthy AI by helping to identify problems, fix bugs, and improve basic understanding. In particular, \"inner\" interpretability techniques, which focus on explaining the internal components of DNNs, are well-suited for develo"},"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":"2207.13243","kind":"arxiv","version":6},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-07-27T01:59:13Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"8feecdd199583d56fb32ac4fc2f4914c98b63fa13d09db1c3776301567100323","abstract_canon_sha256":"82bbdc6515f371f8b13fdf3cc3ee5629b6d470acff7e1249cd35f9ee226c9cc6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:42:39.768584Z","signature_b64":"TWrh3p14JvFdN79SJgfwZ5r60DPLoDElCDGL9qG/aLojUSqPhGZw0Hvsp/1sPFqPlEhuQm2Cy5gDIzxU7MmGBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6abc5c37961eb3c2d4a52aefa1e42f7537bfac6c5e99878e0c21f2cb6991707e","last_reissued_at":"2026-07-05T06:42:39.768106Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:42:39.768106Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networks","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.LG","authors_text":"Anson Ho, Dylan Hadfield-Menell, Stephen Casper, Tilman R\\\"auker","submitted_at":"2022-07-27T01:59:13Z","abstract_excerpt":"The last decade of machine learning has seen drastic increases in scale and capabilities. Deep neural networks (DNNs) are increasingly being deployed in the real world. However, they are difficult to analyze, raising concerns about using them without a rigorous understanding of how they function. Effective tools for interpreting them will be important for building more trustworthy AI by helping to identify problems, fix bugs, and improve basic understanding. In particular, \"inner\" interpretability techniques, which focus on explaining the internal components of DNNs, are well-suited for develo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2207.13243","kind":"arxiv","version":6},"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/2207.13243/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":"2207.13243","created_at":"2026-07-05T06:42:39.768156+00:00"},{"alias_kind":"arxiv_version","alias_value":"2207.13243v6","created_at":"2026-07-05T06:42:39.768156+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2207.13243","created_at":"2026-07-05T06:42:39.768156+00:00"},{"alias_kind":"pith_short_12","alias_value":"NK6FYN4WD2Z4","created_at":"2026-07-05T06:42:39.768156+00:00"},{"alias_kind":"pith_short_16","alias_value":"NK6FYN4WD2Z4FVFF","created_at":"2026-07-05T06:42:39.768156+00:00"},{"alias_kind":"pith_short_8","alias_value":"NK6FYN4W","created_at":"2026-07-05T06:42:39.768156+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07127","citing_title":"Weight-Space Physics: Interpretable Hypernetworks for Lattice Quantum Field Theories","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12809","citing_title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2211.00593","citing_title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2211.00593","citing_title":"Interpretability in the Wild: a Circuit for Indirect Object Identification in GPT-2 small","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11920","citing_title":"Domain Restriction via Multi SAE Layer Transitions","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NK6FYN4WD2Z4FVFFFLX2DZBPOU","json":"https://pith.science/pith/NK6FYN4WD2Z4FVFFFLX2DZBPOU.json","graph_json":"https://pith.science/api/pith-number/NK6FYN4WD2Z4FVFFFLX2DZBPOU/graph.json","events_json":"https://pith.science/api/pith-number/NK6FYN4WD2Z4FVFFFLX2DZBPOU/events.json","paper":"https://pith.science/paper/NK6FYN4W"},"agent_actions":{"view_html":"https://pith.science/pith/NK6FYN4WD2Z4FVFFFLX2DZBPOU","download_json":"https://pith.science/pith/NK6FYN4WD2Z4FVFFFLX2DZBPOU.json","view_paper":"https://pith.science/paper/NK6FYN4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2207.13243&json=true","fetch_graph":"https://pith.science/api/pith-number/NK6FYN4WD2Z4FVFFFLX2DZBPOU/graph.json","fetch_events":"https://pith.science/api/pith-number/NK6FYN4WD2Z4FVFFFLX2DZBPOU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NK6FYN4WD2Z4FVFFFLX2DZBPOU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NK6FYN4WD2Z4FVFFFLX2DZBPOU/action/storage_attestation","attest_author":"https://pith.science/pith/NK6FYN4WD2Z4FVFFFLX2DZBPOU/action/author_attestation","sign_citation":"https://pith.science/pith/NK6FYN4WD2Z4FVFFFLX2DZBPOU/action/citation_signature","submit_replication":"https://pith.science/pith/NK6FYN4WD2Z4FVFFFLX2DZBPOU/action/replication_record"}},"created_at":"2026-07-05T06:42:39.768156+00:00","updated_at":"2026-07-05T06:42:39.768156+00:00"}