{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:Q2FXXASX2DCBLAKRVDYJ3DWYJL","short_pith_number":"pith:Q2FXXASX","schema_version":"1.0","canonical_sha256":"868b7b8257d0c4158151a8f09d8ed84acefa88314182653673b2e6d807a51bb8","source":{"kind":"arxiv","id":"1611.02767","version":1},"attestation_state":"computed","paper":{"title":"A backward pass through a CNN using a generative model of its activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Chen, Dileep George, D. Scott Phoenix, Huayan Wang, Yi Liu","submitted_at":"2016-11-08T23:18:50Z","abstract_excerpt":"Neural networks have shown to be a practical way of building a very complex mapping between a pre-specified input space and output space. For example, a convolutional neural network (CNN) mapping an image into one of a thousand object labels is approaching human performance in this particular task. However the mapping (neural network) does not automatically lend itself to other forms of queries, for example, to detect/reconstruct object instances, to enforce top-down signal on ambiguous inputs, or to recover object instances from occlusion. One way to address these queries is a backward pass t"},"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":"1611.02767","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2016-11-08T23:18:50Z","cross_cats_sorted":[],"title_canon_sha256":"27112317a1b9251cc9161e6ea22fd448906e59d768fa89fb1cebc12e0ae2269d","abstract_canon_sha256":"54b2c946b8b65512e4a7dfd0624c30d01841932a3dcee5a7150dc19fb717738a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:59:43.743281Z","signature_b64":"j/eitg3NYhFIx25wIEzSzo6jOcPJCAduXWV5runtse6B06mTHtWbagiBxu/GGKXqP67RQniS/ZPL7VMYpfEICQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"868b7b8257d0c4158151a8f09d8ed84acefa88314182653673b2e6d807a51bb8","last_reissued_at":"2026-05-18T00:59:43.742450Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:59:43.742450Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A backward pass through a CNN using a generative model of its activations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anna Chen, Dileep George, D. Scott Phoenix, Huayan Wang, Yi Liu","submitted_at":"2016-11-08T23:18:50Z","abstract_excerpt":"Neural networks have shown to be a practical way of building a very complex mapping between a pre-specified input space and output space. For example, a convolutional neural network (CNN) mapping an image into one of a thousand object labels is approaching human performance in this particular task. However the mapping (neural network) does not automatically lend itself to other forms of queries, for example, to detect/reconstruct object instances, to enforce top-down signal on ambiguous inputs, or to recover object instances from occlusion. One way to address these queries is a backward pass t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1611.02767","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":""},"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":"1611.02767","created_at":"2026-05-18T00:59:43.742593+00:00"},{"alias_kind":"arxiv_version","alias_value":"1611.02767v1","created_at":"2026-05-18T00:59:43.742593+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1611.02767","created_at":"2026-05-18T00:59:43.742593+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q2FXXASX2DCB","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q2FXXASX2DCBLAKR","created_at":"2026-05-18T12:30:39.010887+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q2FXXASX","created_at":"2026-05-18T12:30:39.010887+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/Q2FXXASX2DCBLAKRVDYJ3DWYJL","json":"https://pith.science/pith/Q2FXXASX2DCBLAKRVDYJ3DWYJL.json","graph_json":"https://pith.science/api/pith-number/Q2FXXASX2DCBLAKRVDYJ3DWYJL/graph.json","events_json":"https://pith.science/api/pith-number/Q2FXXASX2DCBLAKRVDYJ3DWYJL/events.json","paper":"https://pith.science/paper/Q2FXXASX"},"agent_actions":{"view_html":"https://pith.science/pith/Q2FXXASX2DCBLAKRVDYJ3DWYJL","download_json":"https://pith.science/pith/Q2FXXASX2DCBLAKRVDYJ3DWYJL.json","view_paper":"https://pith.science/paper/Q2FXXASX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1611.02767&json=true","fetch_graph":"https://pith.science/api/pith-number/Q2FXXASX2DCBLAKRVDYJ3DWYJL/graph.json","fetch_events":"https://pith.science/api/pith-number/Q2FXXASX2DCBLAKRVDYJ3DWYJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q2FXXASX2DCBLAKRVDYJ3DWYJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q2FXXASX2DCBLAKRVDYJ3DWYJL/action/storage_attestation","attest_author":"https://pith.science/pith/Q2FXXASX2DCBLAKRVDYJ3DWYJL/action/author_attestation","sign_citation":"https://pith.science/pith/Q2FXXASX2DCBLAKRVDYJ3DWYJL/action/citation_signature","submit_replication":"https://pith.science/pith/Q2FXXASX2DCBLAKRVDYJ3DWYJL/action/replication_record"}},"created_at":"2026-05-18T00:59:43.742593+00:00","updated_at":"2026-05-18T00:59:43.742593+00:00"}