{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:R4PQZNCJ7SCA2FUW3OPNLXDVZV","short_pith_number":"pith:R4PQZNCJ","schema_version":"1.0","canonical_sha256":"8f1f0cb449fc840d1696db9ed5dc75cd7821eae7af5a1352969bd82d40e7a1db","source":{"kind":"arxiv","id":"1705.10762","version":8},"attestation_state":"computed","paper":{"title":"Generative Models of Visually Grounded Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ian Fischer, Jonathan Huang, Kevin Murphy, Ramakrishna Vedantam","submitted_at":"2017-05-30T17:32:26Z","abstract_excerpt":"It is easy for people to imagine what a man with pink hair looks like, even if they have never seen such a person before. We call the ability to create images of novel semantic concepts visually grounded imagination. In this paper, we show how we can modify variational auto-encoders to perform this task. Our method uses a novel training objective, and a novel product-of-experts inference network, which can handle partially specified (abstract) concepts in a principled and efficient way. We also propose a set of easy-to-compute evaluation metrics that capture our intuitive notions of what it me"},"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":"1705.10762","kind":"arxiv","version":8},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-05-30T17:32:26Z","cross_cats_sorted":["cs.CV","stat.ML"],"title_canon_sha256":"e98d2fe743990b64d7792d703ec4ff5b0e42711b41d157adad24c53d0f48c184","abstract_canon_sha256":"bc5d5d5b6bbce220b1ae3248a4dc65f07e96715ca2d8cde1efed07e7b60a37dd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:15.411514Z","signature_b64":"WZo+LqLI4XOlS3HWCLha8tNApZGEtj+PT92j6NAnexDrCTJlnFlQfIX+wb0+axOdfAZXGwlscoCXnEHMo5+QCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f1f0cb449fc840d1696db9ed5dc75cd7821eae7af5a1352969bd82d40e7a1db","last_reissued_at":"2026-05-18T00:01:15.411082Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:15.411082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Models of Visually Grounded Imagination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Ian Fischer, Jonathan Huang, Kevin Murphy, Ramakrishna Vedantam","submitted_at":"2017-05-30T17:32:26Z","abstract_excerpt":"It is easy for people to imagine what a man with pink hair looks like, even if they have never seen such a person before. We call the ability to create images of novel semantic concepts visually grounded imagination. In this paper, we show how we can modify variational auto-encoders to perform this task. Our method uses a novel training objective, and a novel product-of-experts inference network, which can handle partially specified (abstract) concepts in a principled and efficient way. We also propose a set of easy-to-compute evaluation metrics that capture our intuitive notions of what it me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.10762","kind":"arxiv","version":8},"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":"1705.10762","created_at":"2026-05-18T00:01:15.411140+00:00"},{"alias_kind":"arxiv_version","alias_value":"1705.10762v8","created_at":"2026-05-18T00:01:15.411140+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.10762","created_at":"2026-05-18T00:01:15.411140+00:00"},{"alias_kind":"pith_short_12","alias_value":"R4PQZNCJ7SCA","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"R4PQZNCJ7SCA2FUW","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"R4PQZNCJ","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.12165","citing_title":"Multi-Component VAE with Gaussian Markov Random Field","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R4PQZNCJ7SCA2FUW3OPNLXDVZV","json":"https://pith.science/pith/R4PQZNCJ7SCA2FUW3OPNLXDVZV.json","graph_json":"https://pith.science/api/pith-number/R4PQZNCJ7SCA2FUW3OPNLXDVZV/graph.json","events_json":"https://pith.science/api/pith-number/R4PQZNCJ7SCA2FUW3OPNLXDVZV/events.json","paper":"https://pith.science/paper/R4PQZNCJ"},"agent_actions":{"view_html":"https://pith.science/pith/R4PQZNCJ7SCA2FUW3OPNLXDVZV","download_json":"https://pith.science/pith/R4PQZNCJ7SCA2FUW3OPNLXDVZV.json","view_paper":"https://pith.science/paper/R4PQZNCJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1705.10762&json=true","fetch_graph":"https://pith.science/api/pith-number/R4PQZNCJ7SCA2FUW3OPNLXDVZV/graph.json","fetch_events":"https://pith.science/api/pith-number/R4PQZNCJ7SCA2FUW3OPNLXDVZV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R4PQZNCJ7SCA2FUW3OPNLXDVZV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R4PQZNCJ7SCA2FUW3OPNLXDVZV/action/storage_attestation","attest_author":"https://pith.science/pith/R4PQZNCJ7SCA2FUW3OPNLXDVZV/action/author_attestation","sign_citation":"https://pith.science/pith/R4PQZNCJ7SCA2FUW3OPNLXDVZV/action/citation_signature","submit_replication":"https://pith.science/pith/R4PQZNCJ7SCA2FUW3OPNLXDVZV/action/replication_record"}},"created_at":"2026-05-18T00:01:15.411140+00:00","updated_at":"2026-05-18T00:01:15.411140+00:00"}