{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZAEC74AYHBNIPEQ2AG2MHFVG2W","short_pith_number":"pith:ZAEC74AY","schema_version":"1.0","canonical_sha256":"c8082ff018385a87921a01b4c396a6d598d311e8e3506941adc186d63403bc08","source":{"kind":"arxiv","id":"1912.04564","version":2},"attestation_state":"computed","paper":{"title":"MaskAAE: Latent space optimization for Adversarial Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aravind Jayendran, Arnab Kumar Mondal, Himanshu Asnani, Parag Singla, Prathosh AP, Sankalan Pal Chowdhury","submitted_at":"2019-12-10T08:18:13Z","abstract_excerpt":"The field of neural generative models is dominated by the highly successful Generative Adversarial Networks (GANs) despite their challenges, such as training instability and mode collapse. Auto-Encoders (AE) with regularized latent space provide an alternative framework for generative models, albeit their performance levels have not reached that of GANs. In this work, we hypothesise that the dimensionality of the AE model's latent space has a critical effect on the quality of generated data. Under the assumption that nature generates data by sampling from a \"true\" generative latent space follo"},"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":"1912.04564","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-10T08:18:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"8280406ae5d7430ae3dbc9b78f10c04bb29f6b7780cb6ef638413d05c7a864a6","abstract_canon_sha256":"120d03650953c7743242da4ad3425451fc64f1b6aab61c94323cf79ab635cd21"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:03:21.915163Z","signature_b64":"rw5aIp33YX4+WBCjXCuPrXZPEtMHPtPyxjWMNcFT9SGg7AA296rDzoAhKO22Cb9MB7cKzaVQ8FgR9OSv1WyIBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c8082ff018385a87921a01b4c396a6d598d311e8e3506941adc186d63403bc08","last_reissued_at":"2026-07-05T01:03:21.914690Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:03:21.914690Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MaskAAE: Latent space optimization for Adversarial Auto-Encoders","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aravind Jayendran, Arnab Kumar Mondal, Himanshu Asnani, Parag Singla, Prathosh AP, Sankalan Pal Chowdhury","submitted_at":"2019-12-10T08:18:13Z","abstract_excerpt":"The field of neural generative models is dominated by the highly successful Generative Adversarial Networks (GANs) despite their challenges, such as training instability and mode collapse. Auto-Encoders (AE) with regularized latent space provide an alternative framework for generative models, albeit their performance levels have not reached that of GANs. In this work, we hypothesise that the dimensionality of the AE model's latent space has a critical effect on the quality of generated data. Under the assumption that nature generates data by sampling from a \"true\" generative latent space follo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.04564","kind":"arxiv","version":2},"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/1912.04564/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"1912.04564","created_at":"2026-07-05T01:03:21.914751+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.04564v2","created_at":"2026-07-05T01:03:21.914751+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.04564","created_at":"2026-07-05T01:03:21.914751+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZAEC74AYHBNI","created_at":"2026-07-05T01:03:21.914751+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZAEC74AYHBNIPEQ2","created_at":"2026-07-05T01:03:21.914751+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZAEC74AY","created_at":"2026-07-05T01:03:21.914751+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.06158","citing_title":"Adaptive Tokenisation Via Temporal Redundancy Masking And Latent Inpainting","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZAEC74AYHBNIPEQ2AG2MHFVG2W","json":"https://pith.science/pith/ZAEC74AYHBNIPEQ2AG2MHFVG2W.json","graph_json":"https://pith.science/api/pith-number/ZAEC74AYHBNIPEQ2AG2MHFVG2W/graph.json","events_json":"https://pith.science/api/pith-number/ZAEC74AYHBNIPEQ2AG2MHFVG2W/events.json","paper":"https://pith.science/paper/ZAEC74AY"},"agent_actions":{"view_html":"https://pith.science/pith/ZAEC74AYHBNIPEQ2AG2MHFVG2W","download_json":"https://pith.science/pith/ZAEC74AYHBNIPEQ2AG2MHFVG2W.json","view_paper":"https://pith.science/paper/ZAEC74AY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.04564&json=true","fetch_graph":"https://pith.science/api/pith-number/ZAEC74AYHBNIPEQ2AG2MHFVG2W/graph.json","fetch_events":"https://pith.science/api/pith-number/ZAEC74AYHBNIPEQ2AG2MHFVG2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZAEC74AYHBNIPEQ2AG2MHFVG2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZAEC74AYHBNIPEQ2AG2MHFVG2W/action/storage_attestation","attest_author":"https://pith.science/pith/ZAEC74AYHBNIPEQ2AG2MHFVG2W/action/author_attestation","sign_citation":"https://pith.science/pith/ZAEC74AYHBNIPEQ2AG2MHFVG2W/action/citation_signature","submit_replication":"https://pith.science/pith/ZAEC74AYHBNIPEQ2AG2MHFVG2W/action/replication_record"}},"created_at":"2026-07-05T01:03:21.914751+00:00","updated_at":"2026-07-05T01:03:21.914751+00:00"}