{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:UYZPBMSDPFO5WASAZCU6NVL3QO","short_pith_number":"pith:UYZPBMSD","schema_version":"1.0","canonical_sha256":"a632f0b243795ddb0240c8a9e6d57b8398fd1de9dc2810f0a062d9ca64e0b869","source":{"kind":"arxiv","id":"1902.03361","version":1},"attestation_state":"computed","paper":{"title":"Image Decomposition and Classification through a Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Houpu Yao, Malcolm Regan, Yezhou Yang, Yi Ren","submitted_at":"2019-02-09T02:40:04Z","abstract_excerpt":"We demonstrate in this paper that a generative model can be designed to perform classification tasks under challenging settings, including adversarial attacks and input distribution shifts. Specifically, we propose a conditional variational autoencoder that learns both the decomposition of inputs and the distributions of the resulting components. During test, we jointly optimize the latent variables of the generator and the relaxed component labels to find the best match between the given input and the output of the generator. The model demonstrates promising performance at recognizing overlap"},"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":"1902.03361","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-02-09T02:40:04Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"02f03856551ffe8990b7102af09024c23bd8b38e0598feee6c5fd1192b2bfc65","abstract_canon_sha256":"92e2f42d842660535cc0105ea35bb45bf643db8f72f3eab5088fae8f1c9f8e09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:54:21.093782Z","signature_b64":"G3ObWW7Li6arFnVCx7y3iPtif2vDuMiAW23+STI+FZcOXexnvVNOcTKQPsva9ofSDjASuQeFU6Wh8PgiPRrBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a632f0b243795ddb0240c8a9e6d57b8398fd1de9dc2810f0a062d9ca64e0b869","last_reissued_at":"2026-05-17T23:54:21.093340Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:54:21.093340Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Decomposition and Classification through a Generative Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Houpu Yao, Malcolm Regan, Yezhou Yang, Yi Ren","submitted_at":"2019-02-09T02:40:04Z","abstract_excerpt":"We demonstrate in this paper that a generative model can be designed to perform classification tasks under challenging settings, including adversarial attacks and input distribution shifts. Specifically, we propose a conditional variational autoencoder that learns both the decomposition of inputs and the distributions of the resulting components. During test, we jointly optimize the latent variables of the generator and the relaxed component labels to find the best match between the given input and the output of the generator. The model demonstrates promising performance at recognizing overlap"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.03361","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":"1902.03361","created_at":"2026-05-17T23:54:21.093400+00:00"},{"alias_kind":"arxiv_version","alias_value":"1902.03361v1","created_at":"2026-05-17T23:54:21.093400+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.03361","created_at":"2026-05-17T23:54:21.093400+00:00"},{"alias_kind":"pith_short_12","alias_value":"UYZPBMSDPFO5","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_16","alias_value":"UYZPBMSDPFO5WASA","created_at":"2026-05-18T12:33:30.264802+00:00"},{"alias_kind":"pith_short_8","alias_value":"UYZPBMSD","created_at":"2026-05-18T12:33:30.264802+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/UYZPBMSDPFO5WASAZCU6NVL3QO","json":"https://pith.science/pith/UYZPBMSDPFO5WASAZCU6NVL3QO.json","graph_json":"https://pith.science/api/pith-number/UYZPBMSDPFO5WASAZCU6NVL3QO/graph.json","events_json":"https://pith.science/api/pith-number/UYZPBMSDPFO5WASAZCU6NVL3QO/events.json","paper":"https://pith.science/paper/UYZPBMSD"},"agent_actions":{"view_html":"https://pith.science/pith/UYZPBMSDPFO5WASAZCU6NVL3QO","download_json":"https://pith.science/pith/UYZPBMSDPFO5WASAZCU6NVL3QO.json","view_paper":"https://pith.science/paper/UYZPBMSD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1902.03361&json=true","fetch_graph":"https://pith.science/api/pith-number/UYZPBMSDPFO5WASAZCU6NVL3QO/graph.json","fetch_events":"https://pith.science/api/pith-number/UYZPBMSDPFO5WASAZCU6NVL3QO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UYZPBMSDPFO5WASAZCU6NVL3QO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UYZPBMSDPFO5WASAZCU6NVL3QO/action/storage_attestation","attest_author":"https://pith.science/pith/UYZPBMSDPFO5WASAZCU6NVL3QO/action/author_attestation","sign_citation":"https://pith.science/pith/UYZPBMSDPFO5WASAZCU6NVL3QO/action/citation_signature","submit_replication":"https://pith.science/pith/UYZPBMSDPFO5WASAZCU6NVL3QO/action/replication_record"}},"created_at":"2026-05-17T23:54:21.093400+00:00","updated_at":"2026-05-17T23:54:21.093400+00:00"}