{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:AJBSJOWROZGVEVPQLTZ6J7XQ5F","short_pith_number":"pith:AJBSJOWR","schema_version":"1.0","canonical_sha256":"024324bad1764d5255f05cf3e4fef0e978209f12653e0084042a4a5c391f4141","source":{"kind":"arxiv","id":"2401.17789","version":3},"attestation_state":"computed","paper":{"title":"Robustly overfitting latents for flexible neural image compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Arwin Gansekoele, Sandjai Bhulai, Yura Perugachi-Diaz","submitted_at":"2024-01-31T12:32:17Z","abstract_excerpt":"Neural image compression has made a great deal of progress. State-of-the-art models are based on variational autoencoders and are outperforming classical models. Neural compression models learn to encode an image into a quantized latent representation that can be efficiently sent to the decoder, which decodes the quantized latent into a reconstructed image. While these models have proven successful in practice, they lead to sub-optimal results due to imperfect optimization and limitations in the encoder and decoder capacity. Recent work shows how to use stochastic Gumbel annealing (SGA) to ref"},"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":"2401.17789","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-31T12:32:17Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"bae9f3498a58b1c6899b8b800223b26ab25ac3e5ece3dc7669bf17f4cf794d9b","abstract_canon_sha256":"9e5837c2f0e472f8e44831137c0ceacd8e4020343ebab5bc9caadb945d04d592"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:30:58.858004Z","signature_b64":"wmkXnqTEhT5q/0xTcGG7l7R4eyCO4OGodYhLk8Vq9g1U0gPDyPfNQHbyCog0DAvk8EHQIKLV93WhBfhJp50xBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"024324bad1764d5255f05cf3e4fef0e978209f12653e0084042a4a5c391f4141","last_reissued_at":"2026-07-05T09:30:58.857509Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:30:58.857509Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Robustly overfitting latents for flexible neural image compression","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.CV","authors_text":"Arwin Gansekoele, Sandjai Bhulai, Yura Perugachi-Diaz","submitted_at":"2024-01-31T12:32:17Z","abstract_excerpt":"Neural image compression has made a great deal of progress. State-of-the-art models are based on variational autoencoders and are outperforming classical models. Neural compression models learn to encode an image into a quantized latent representation that can be efficiently sent to the decoder, which decodes the quantized latent into a reconstructed image. While these models have proven successful in practice, they lead to sub-optimal results due to imperfect optimization and limitations in the encoder and decoder capacity. Recent work shows how to use stochastic Gumbel annealing (SGA) to ref"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17789","kind":"arxiv","version":3},"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/2401.17789/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":"2401.17789","created_at":"2026-07-05T09:30:58.857569+00:00"},{"alias_kind":"arxiv_version","alias_value":"2401.17789v3","created_at":"2026-07-05T09:30:58.857569+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17789","created_at":"2026-07-05T09:30:58.857569+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJBSJOWROZGV","created_at":"2026-07-05T09:30:58.857569+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJBSJOWROZGVEVPQ","created_at":"2026-07-05T09:30:58.857569+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJBSJOWR","created_at":"2026-07-05T09:30:58.857569+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/AJBSJOWROZGVEVPQLTZ6J7XQ5F","json":"https://pith.science/pith/AJBSJOWROZGVEVPQLTZ6J7XQ5F.json","graph_json":"https://pith.science/api/pith-number/AJBSJOWROZGVEVPQLTZ6J7XQ5F/graph.json","events_json":"https://pith.science/api/pith-number/AJBSJOWROZGVEVPQLTZ6J7XQ5F/events.json","paper":"https://pith.science/paper/AJBSJOWR"},"agent_actions":{"view_html":"https://pith.science/pith/AJBSJOWROZGVEVPQLTZ6J7XQ5F","download_json":"https://pith.science/pith/AJBSJOWROZGVEVPQLTZ6J7XQ5F.json","view_paper":"https://pith.science/paper/AJBSJOWR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2401.17789&json=true","fetch_graph":"https://pith.science/api/pith-number/AJBSJOWROZGVEVPQLTZ6J7XQ5F/graph.json","fetch_events":"https://pith.science/api/pith-number/AJBSJOWROZGVEVPQLTZ6J7XQ5F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJBSJOWROZGVEVPQLTZ6J7XQ5F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJBSJOWROZGVEVPQLTZ6J7XQ5F/action/storage_attestation","attest_author":"https://pith.science/pith/AJBSJOWROZGVEVPQLTZ6J7XQ5F/action/author_attestation","sign_citation":"https://pith.science/pith/AJBSJOWROZGVEVPQLTZ6J7XQ5F/action/citation_signature","submit_replication":"https://pith.science/pith/AJBSJOWROZGVEVPQLTZ6J7XQ5F/action/replication_record"}},"created_at":"2026-07-05T09:30:58.857569+00:00","updated_at":"2026-07-05T09:30:58.857569+00:00"}