{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:L7GWIRLZVXATYT3HVGJXANKF4H","short_pith_number":"pith:L7GWIRLZ","schema_version":"1.0","canonical_sha256":"5fcd644579adc13c4f67a993703545e1ff66daf0af7961b15b73dfdb02122693","source":{"kind":"arxiv","id":"2605.16164","version":1},"attestation_state":"computed","paper":{"title":"Entropic Auto-Encoding via Implicit Free-Energy Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Greg van Anders, Hazhir Aliahmadi, Irina Babayan","submitted_at":"2026-05-15T16:43:45Z","abstract_excerpt":"Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a failure mode in which latent variables are effectively ignored. This failure arises because explicit prior imposition drives optimization toward loss landscape regions corresponding to uninformative latent representations. Here, we introduce Entropic Autoencoders (EAEs), a framework in which reconstruction loss is the only explicit objective, and entropy generates the latent variables' prior implicitly through a free energy-minimizing ensemble of encoders. This ensemble biases learning toward h"},"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":"2605.16164","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T16:43:45Z","cross_cats_sorted":[],"title_canon_sha256":"89360ce0422e9522b8a36f01837b657a2a4cdecde305a29380a7a2f268ec69a2","abstract_canon_sha256":"aaac04b4456dc120ed8bcbe9e7e6dec61d19d56f13699b85d86733499d39d4b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:55.711006Z","signature_b64":"VLx2RRpoHn+lahKtZUdcC2NUWnheNQrzhR167hMyTV5q6L1K5GKG0w1IVvoUkHNjE73HuIWqENMtuFEWRPLPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5fcd644579adc13c4f67a993703545e1ff66daf0af7961b15b73dfdb02122693","last_reissued_at":"2026-05-20T00:01:55.710052Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:55.710052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entropic Auto-Encoding via Implicit Free-Energy Minimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Greg van Anders, Hazhir Aliahmadi, Irina Babayan","submitted_at":"2026-05-15T16:43:45Z","abstract_excerpt":"Despite their ubiquity, variational autoencoders (VAEs) inherently suffer from posterior collapse, a failure mode in which latent variables are effectively ignored. This failure arises because explicit prior imposition drives optimization toward loss landscape regions corresponding to uninformative latent representations. Here, we introduce Entropic Autoencoders (EAEs), a framework in which reconstruction loss is the only explicit objective, and entropy generates the latent variables' prior implicitly through a free energy-minimizing ensemble of encoders. This ensemble biases learning toward h"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16164","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16164/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T18:21:56.476643Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:31.034994Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T17:31:47.206029Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T16:41:55.434340Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"63a86ddd7b679d64d36c269862ee7dbbc4087a92ef46ad2801177c02801993c1"},"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":"2605.16164","created_at":"2026-05-20T00:01:55.710261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16164v1","created_at":"2026-05-20T00:01:55.710261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16164","created_at":"2026-05-20T00:01:55.710261+00:00"},{"alias_kind":"pith_short_12","alias_value":"L7GWIRLZVXAT","created_at":"2026-05-20T00:01:55.710261+00:00"},{"alias_kind":"pith_short_16","alias_value":"L7GWIRLZVXATYT3H","created_at":"2026-05-20T00:01:55.710261+00:00"},{"alias_kind":"pith_short_8","alias_value":"L7GWIRLZ","created_at":"2026-05-20T00:01:55.710261+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/L7GWIRLZVXATYT3HVGJXANKF4H","json":"https://pith.science/pith/L7GWIRLZVXATYT3HVGJXANKF4H.json","graph_json":"https://pith.science/api/pith-number/L7GWIRLZVXATYT3HVGJXANKF4H/graph.json","events_json":"https://pith.science/api/pith-number/L7GWIRLZVXATYT3HVGJXANKF4H/events.json","paper":"https://pith.science/paper/L7GWIRLZ"},"agent_actions":{"view_html":"https://pith.science/pith/L7GWIRLZVXATYT3HVGJXANKF4H","download_json":"https://pith.science/pith/L7GWIRLZVXATYT3HVGJXANKF4H.json","view_paper":"https://pith.science/paper/L7GWIRLZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16164&json=true","fetch_graph":"https://pith.science/api/pith-number/L7GWIRLZVXATYT3HVGJXANKF4H/graph.json","fetch_events":"https://pith.science/api/pith-number/L7GWIRLZVXATYT3HVGJXANKF4H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L7GWIRLZVXATYT3HVGJXANKF4H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L7GWIRLZVXATYT3HVGJXANKF4H/action/storage_attestation","attest_author":"https://pith.science/pith/L7GWIRLZVXATYT3HVGJXANKF4H/action/author_attestation","sign_citation":"https://pith.science/pith/L7GWIRLZVXATYT3HVGJXANKF4H/action/citation_signature","submit_replication":"https://pith.science/pith/L7GWIRLZVXATYT3HVGJXANKF4H/action/replication_record"}},"created_at":"2026-05-20T00:01:55.710261+00:00","updated_at":"2026-05-20T00:01:55.710261+00:00"}