{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:WAHGNXJCYN67TCKJTR3NILXXVB","short_pith_number":"pith:WAHGNXJC","schema_version":"1.0","canonical_sha256":"b00e66dd22c37df989499c76d42ef7a8531f2ea071039fc7a3806fedf365c804","source":{"kind":"arxiv","id":"1712.04195","version":1},"attestation_state":"computed","paper":{"title":"Concept Formation and Dynamics of Repeated Inference in Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Masato Okada, Ryo Karakida, Yoshihiro Nagano","submitted_at":"2017-12-12T09:55:11Z","abstract_excerpt":"Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quality of inferred results. However, previous studies only qualitatively evaluated image outputs in data space, and the mechanism behind the inference has not been investigated. The purpose of the current study is to numerically analyze changes in activity patterns of neurons in the latent space of a deep generative model called a \"variational auto-encoder\" (VAE). What kinds of inf"},"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":"1712.04195","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-12T09:55:11Z","cross_cats_sorted":["cs.LG","cs.NE","q-bio.NC"],"title_canon_sha256":"ebffa32f0d9f5aa2b6dbcaf2f3f61790598c6ce527e17d04a88f99173bbd7985","abstract_canon_sha256":"59a49c917bed9ed06ba5cbc06e9b938e868699691c4932ebd6b76ce60ab1ee19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:08.816689Z","signature_b64":"goPd42mxXMTHKk7OqajTp9AxuPLZehMb78WmAYcd6I1FwB+WdPwSFIvp+MEAVHcaklE7UkYWr09t+kqHf1U4AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b00e66dd22c37df989499c76d42ef7a8531f2ea071039fc7a3806fedf365c804","last_reissued_at":"2026-05-18T00:28:08.816097Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:08.816097Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Concept Formation and Dynamics of Repeated Inference in Deep Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NE","q-bio.NC"],"primary_cat":"stat.ML","authors_text":"Masato Okada, Ryo Karakida, Yoshihiro Nagano","submitted_at":"2017-12-12T09:55:11Z","abstract_excerpt":"Deep generative models are reported to be useful in broad applications including image generation. Repeated inference between data space and latent space in these models can denoise cluttered images and improve the quality of inferred results. However, previous studies only qualitatively evaluated image outputs in data space, and the mechanism behind the inference has not been investigated. The purpose of the current study is to numerically analyze changes in activity patterns of neurons in the latent space of a deep generative model called a \"variational auto-encoder\" (VAE). What kinds of inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.04195","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":"1712.04195","created_at":"2026-05-18T00:28:08.816177+00:00"},{"alias_kind":"arxiv_version","alias_value":"1712.04195v1","created_at":"2026-05-18T00:28:08.816177+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.04195","created_at":"2026-05-18T00:28:08.816177+00:00"},{"alias_kind":"pith_short_12","alias_value":"WAHGNXJCYN67","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_16","alias_value":"WAHGNXJCYN67TCKJ","created_at":"2026-05-18T12:31:53.515858+00:00"},{"alias_kind":"pith_short_8","alias_value":"WAHGNXJC","created_at":"2026-05-18T12:31:53.515858+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/WAHGNXJCYN67TCKJTR3NILXXVB","json":"https://pith.science/pith/WAHGNXJCYN67TCKJTR3NILXXVB.json","graph_json":"https://pith.science/api/pith-number/WAHGNXJCYN67TCKJTR3NILXXVB/graph.json","events_json":"https://pith.science/api/pith-number/WAHGNXJCYN67TCKJTR3NILXXVB/events.json","paper":"https://pith.science/paper/WAHGNXJC"},"agent_actions":{"view_html":"https://pith.science/pith/WAHGNXJCYN67TCKJTR3NILXXVB","download_json":"https://pith.science/pith/WAHGNXJCYN67TCKJTR3NILXXVB.json","view_paper":"https://pith.science/paper/WAHGNXJC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1712.04195&json=true","fetch_graph":"https://pith.science/api/pith-number/WAHGNXJCYN67TCKJTR3NILXXVB/graph.json","fetch_events":"https://pith.science/api/pith-number/WAHGNXJCYN67TCKJTR3NILXXVB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WAHGNXJCYN67TCKJTR3NILXXVB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WAHGNXJCYN67TCKJTR3NILXXVB/action/storage_attestation","attest_author":"https://pith.science/pith/WAHGNXJCYN67TCKJTR3NILXXVB/action/author_attestation","sign_citation":"https://pith.science/pith/WAHGNXJCYN67TCKJTR3NILXXVB/action/citation_signature","submit_replication":"https://pith.science/pith/WAHGNXJCYN67TCKJTR3NILXXVB/action/replication_record"}},"created_at":"2026-05-18T00:28:08.816177+00:00","updated_at":"2026-05-18T00:28:08.816177+00:00"}