{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BIAZX77IPZAFHZQ4HQZK2TXZJL","short_pith_number":"pith:BIAZX77I","schema_version":"1.0","canonical_sha256":"0a019bffe87e4053e61c3c32ad4ef94af2a0aa15ad7e6fe21ad873a2da97d91d","source":{"kind":"arxiv","id":"2507.02619","version":1},"attestation_state":"computed","paper":{"title":"L-VAE: Variational Auto-Encoder with Learnable Beta for Disentangled Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Fatos T. Yarman-Vural, Hazal Mogultay Ozcan, Sinan Kalkan","submitted_at":"2025-07-03T13:45:42Z","abstract_excerpt":"In this paper, we propose a novel model called Learnable VAE (L-VAE), which learns a disentangled representation together with the hyperparameters of the cost function. L-VAE can be considered as an extension of \\b{eta}-VAE, wherein the hyperparameter, \\b{eta}, is empirically adjusted. L-VAE mitigates the limitations of \\b{eta}-VAE by learning the relative weights of the terms in the loss function to control the dynamic trade-off between disentanglement and reconstruction losses. In the proposed model, the weight of the loss terms and the parameters of the model architecture are learned concur"},"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":"2507.02619","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-03T13:45:42Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"65f752b04c5a09ebb39e60cec9d9163237e30245ee3db044e8c47f9c1e6e4c30","abstract_canon_sha256":"c23e1cea2e8f38582948edf4d34dfaf8ba32e9644e86a69eff355c7afcf89f8d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:31.776452Z","signature_b64":"88HM3pXmnLu3dT2/8P51yXIaewI7Ml4hIkqWw9N4BeShtxIRK5ICy5NUjB55Yptiu5Htd8MKE2N1ng1+xHfzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a019bffe87e4053e61c3c32ad4ef94af2a0aa15ad7e6fe21ad873a2da97d91d","last_reissued_at":"2026-07-05T11:31:31.775974Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:31.775974Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"L-VAE: Variational Auto-Encoder with Learnable Beta for Disentangled Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Fatos T. Yarman-Vural, Hazal Mogultay Ozcan, Sinan Kalkan","submitted_at":"2025-07-03T13:45:42Z","abstract_excerpt":"In this paper, we propose a novel model called Learnable VAE (L-VAE), which learns a disentangled representation together with the hyperparameters of the cost function. L-VAE can be considered as an extension of \\b{eta}-VAE, wherein the hyperparameter, \\b{eta}, is empirically adjusted. L-VAE mitigates the limitations of \\b{eta}-VAE by learning the relative weights of the terms in the loss function to control the dynamic trade-off between disentanglement and reconstruction losses. In the proposed model, the weight of the loss terms and the parameters of the model architecture are learned concur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02619","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/2507.02619/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":"2507.02619","created_at":"2026-07-05T11:31:31.776030+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02619v1","created_at":"2026-07-05T11:31:31.776030+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02619","created_at":"2026-07-05T11:31:31.776030+00:00"},{"alias_kind":"pith_short_12","alias_value":"BIAZX77IPZAF","created_at":"2026-07-05T11:31:31.776030+00:00"},{"alias_kind":"pith_short_16","alias_value":"BIAZX77IPZAFHZQ4","created_at":"2026-07-05T11:31:31.776030+00:00"},{"alias_kind":"pith_short_8","alias_value":"BIAZX77I","created_at":"2026-07-05T11:31:31.776030+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/BIAZX77IPZAFHZQ4HQZK2TXZJL","json":"https://pith.science/pith/BIAZX77IPZAFHZQ4HQZK2TXZJL.json","graph_json":"https://pith.science/api/pith-number/BIAZX77IPZAFHZQ4HQZK2TXZJL/graph.json","events_json":"https://pith.science/api/pith-number/BIAZX77IPZAFHZQ4HQZK2TXZJL/events.json","paper":"https://pith.science/paper/BIAZX77I"},"agent_actions":{"view_html":"https://pith.science/pith/BIAZX77IPZAFHZQ4HQZK2TXZJL","download_json":"https://pith.science/pith/BIAZX77IPZAFHZQ4HQZK2TXZJL.json","view_paper":"https://pith.science/paper/BIAZX77I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02619&json=true","fetch_graph":"https://pith.science/api/pith-number/BIAZX77IPZAFHZQ4HQZK2TXZJL/graph.json","fetch_events":"https://pith.science/api/pith-number/BIAZX77IPZAFHZQ4HQZK2TXZJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BIAZX77IPZAFHZQ4HQZK2TXZJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BIAZX77IPZAFHZQ4HQZK2TXZJL/action/storage_attestation","attest_author":"https://pith.science/pith/BIAZX77IPZAFHZQ4HQZK2TXZJL/action/author_attestation","sign_citation":"https://pith.science/pith/BIAZX77IPZAFHZQ4HQZK2TXZJL/action/citation_signature","submit_replication":"https://pith.science/pith/BIAZX77IPZAFHZQ4HQZK2TXZJL/action/replication_record"}},"created_at":"2026-07-05T11:31:31.776030+00:00","updated_at":"2026-07-05T11:31:31.776030+00:00"}