{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2016:6TTY4KSFGCD4YQAANZPRGRVXG6","short_pith_number":"pith:6TTY4KSF","schema_version":"1.0","canonical_sha256":"f4e78e2a453087cc40006e5f1346b737ad190329abdff469b9a2b6309fddf51c","source":{"kind":"arxiv","id":"1602.03264","version":3},"attestation_state":"computed","paper":{"title":"A Theory of Generative ConvNet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jianwen Xie, Song-Chun Zhu, Yang Lu, Ying Nian Wu","submitted_at":"2016-02-10T04:46:45Z","abstract_excerpt":"We show that a generative random field model, which we call generative ConvNet, can be derived from the commonly used discriminative ConvNet, by assuming a ConvNet for multi-category classification and assuming one of the categories is a base category generated by a reference distribution. If we further assume that the non-linearity in the ConvNet is Rectified Linear Unit (ReLU) and the reference distribution is Gaussian white noise, then we obtain a generative ConvNet model that is unique among energy-based models: The model is piecewise Gaussian, and the means of the Gaussian pieces are defi"},"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":"1602.03264","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2016-02-10T04:46:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ffcbee280eda92727cfd7c78b4e1cd67042b739f9db0d7f43e326f666c89295c","abstract_canon_sha256":"beea3e921f0070b15d38c8037b0a2631cbe3c17b333d61baa26f0dfaa444413f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:13:15.369103Z","signature_b64":"x93iDnrOQzTb2YphE2Fm3cgSTsCQobH9EXPIhKOi8c5sdrYwAsKnqylNLkzBLha9KqXE0/GvSEeRzMYxs1z5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4e78e2a453087cc40006e5f1346b737ad190329abdff469b9a2b6309fddf51c","last_reissued_at":"2026-05-18T01:13:15.368646Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:13:15.368646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Theory of Generative ConvNet","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jianwen Xie, Song-Chun Zhu, Yang Lu, Ying Nian Wu","submitted_at":"2016-02-10T04:46:45Z","abstract_excerpt":"We show that a generative random field model, which we call generative ConvNet, can be derived from the commonly used discriminative ConvNet, by assuming a ConvNet for multi-category classification and assuming one of the categories is a base category generated by a reference distribution. If we further assume that the non-linearity in the ConvNet is Rectified Linear Unit (ReLU) and the reference distribution is Gaussian white noise, then we obtain a generative ConvNet model that is unique among energy-based models: The model is piecewise Gaussian, and the means of the Gaussian pieces are defi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1602.03264","kind":"arxiv","version":3},"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":"1602.03264","created_at":"2026-05-18T01:13:15.368719+00:00"},{"alias_kind":"arxiv_version","alias_value":"1602.03264v3","created_at":"2026-05-18T01:13:15.368719+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1602.03264","created_at":"2026-05-18T01:13:15.368719+00:00"},{"alias_kind":"pith_short_12","alias_value":"6TTY4KSFGCD4","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_16","alias_value":"6TTY4KSFGCD4YQAA","created_at":"2026-05-18T12:30:04.600751+00:00"},{"alias_kind":"pith_short_8","alias_value":"6TTY4KSF","created_at":"2026-05-18T12:30:04.600751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2105.05233","citing_title":"Diffusion Models Beat GANs on Image Synthesis","ref_index":70,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6TTY4KSFGCD4YQAANZPRGRVXG6","json":"https://pith.science/pith/6TTY4KSFGCD4YQAANZPRGRVXG6.json","graph_json":"https://pith.science/api/pith-number/6TTY4KSFGCD4YQAANZPRGRVXG6/graph.json","events_json":"https://pith.science/api/pith-number/6TTY4KSFGCD4YQAANZPRGRVXG6/events.json","paper":"https://pith.science/paper/6TTY4KSF"},"agent_actions":{"view_html":"https://pith.science/pith/6TTY4KSFGCD4YQAANZPRGRVXG6","download_json":"https://pith.science/pith/6TTY4KSFGCD4YQAANZPRGRVXG6.json","view_paper":"https://pith.science/paper/6TTY4KSF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1602.03264&json=true","fetch_graph":"https://pith.science/api/pith-number/6TTY4KSFGCD4YQAANZPRGRVXG6/graph.json","fetch_events":"https://pith.science/api/pith-number/6TTY4KSFGCD4YQAANZPRGRVXG6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6TTY4KSFGCD4YQAANZPRGRVXG6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6TTY4KSFGCD4YQAANZPRGRVXG6/action/storage_attestation","attest_author":"https://pith.science/pith/6TTY4KSFGCD4YQAANZPRGRVXG6/action/author_attestation","sign_citation":"https://pith.science/pith/6TTY4KSFGCD4YQAANZPRGRVXG6/action/citation_signature","submit_replication":"https://pith.science/pith/6TTY4KSFGCD4YQAANZPRGRVXG6/action/replication_record"}},"created_at":"2026-05-18T01:13:15.368719+00:00","updated_at":"2026-05-18T01:13:15.368719+00:00"}