{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GBQE5S2WZOHZRVELO34XEPFRP7","short_pith_number":"pith:GBQE5S2W","schema_version":"1.0","canonical_sha256":"30604ecb56cb8f98d48b76f9723cb17fd8669c2222b770c73655e5e1fa4ce103","source":{"kind":"arxiv","id":"1806.00400","version":2},"attestation_state":"computed","paper":{"title":"Inverting Supervised Representations with Autoregressive Neural Density Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Charlie Nash, Christopher K. I. Williams, Nate Kushman","submitted_at":"2018-06-01T15:38:58Z","abstract_excerpt":"We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative inversion models to express a distribution over input features conditioned on intermediate model representations. Insights into the invariances learned by supervised models can be gained by viewing samples from these inversion models. In addition, we can use these inversion models to estimate the mutual information between a model's inputs and its intermediate representations, thus quantifying the amount of information"},"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":"1806.00400","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2018-06-01T15:38:58Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"677aa842fbb2e54ca16445dcea28502354965a46b3424a960df99c72d3f1b2ef","abstract_canon_sha256":"11db5a23540defa565714c96983b5379e71cddb0ef58373e8392e8fa5691ce62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:07.532961Z","signature_b64":"brrCYv725oboUi8XrfawRSP+DxOy+NSpbLpkwSyTL+rCcubMJy+thgr4YLAxSBmbLeArt4uO8e7w3mi+jliZDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30604ecb56cb8f98d48b76f9723cb17fd8669c2222b770c73655e5e1fa4ce103","last_reissued_at":"2026-05-17T23:57:07.532387Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:07.532387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inverting Supervised Representations with Autoregressive Neural Density Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Charlie Nash, Christopher K. I. Williams, Nate Kushman","submitted_at":"2018-06-01T15:38:58Z","abstract_excerpt":"We present a method for feature interpretation that makes use of recent advances in autoregressive density estimation models to invert model representations. We train generative inversion models to express a distribution over input features conditioned on intermediate model representations. Insights into the invariances learned by supervised models can be gained by viewing samples from these inversion models. In addition, we can use these inversion models to estimate the mutual information between a model's inputs and its intermediate representations, thus quantifying the amount of information"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1806.00400","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1806.00400","created_at":"2026-05-17T23:57:07.532478+00:00"},{"alias_kind":"arxiv_version","alias_value":"1806.00400v2","created_at":"2026-05-17T23:57:07.532478+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1806.00400","created_at":"2026-05-17T23:57:07.532478+00:00"},{"alias_kind":"pith_short_12","alias_value":"GBQE5S2WZOHZ","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_16","alias_value":"GBQE5S2WZOHZRVEL","created_at":"2026-05-18T12:32:25.280505+00:00"},{"alias_kind":"pith_short_8","alias_value":"GBQE5S2W","created_at":"2026-05-18T12:32:25.280505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GBQE5S2WZOHZRVELO34XEPFRP7","json":"https://pith.science/pith/GBQE5S2WZOHZRVELO34XEPFRP7.json","graph_json":"https://pith.science/api/pith-number/GBQE5S2WZOHZRVELO34XEPFRP7/graph.json","events_json":"https://pith.science/api/pith-number/GBQE5S2WZOHZRVELO34XEPFRP7/events.json","paper":"https://pith.science/paper/GBQE5S2W"},"agent_actions":{"view_html":"https://pith.science/pith/GBQE5S2WZOHZRVELO34XEPFRP7","download_json":"https://pith.science/pith/GBQE5S2WZOHZRVELO34XEPFRP7.json","view_paper":"https://pith.science/paper/GBQE5S2W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1806.00400&json=true","fetch_graph":"https://pith.science/api/pith-number/GBQE5S2WZOHZRVELO34XEPFRP7/graph.json","fetch_events":"https://pith.science/api/pith-number/GBQE5S2WZOHZRVELO34XEPFRP7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GBQE5S2WZOHZRVELO34XEPFRP7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GBQE5S2WZOHZRVELO34XEPFRP7/action/storage_attestation","attest_author":"https://pith.science/pith/GBQE5S2WZOHZRVELO34XEPFRP7/action/author_attestation","sign_citation":"https://pith.science/pith/GBQE5S2WZOHZRVELO34XEPFRP7/action/citation_signature","submit_replication":"https://pith.science/pith/GBQE5S2WZOHZRVELO34XEPFRP7/action/replication_record"}},"created_at":"2026-05-17T23:57:07.532478+00:00","updated_at":"2026-05-17T23:57:07.532478+00:00"}