{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:LQUKLY7ACEC2S4RGKQEPMKWYIK","short_pith_number":"pith:LQUKLY7A","schema_version":"1.0","canonical_sha256":"5c28a5e3e01105a972265408f62ad8428531be068ce936a97aa1cac33cda19e0","source":{"kind":"arxiv","id":"2101.08687","version":2},"attestation_state":"computed","paper":{"title":"Overfitting for Fun and Profit: Instance-Adaptive Data Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Iris A.M. Huijben, Taco S. Cohen, Ties van Rozendaal","submitted_at":"2021-01-21T15:58:58Z","abstract_excerpt":"Neural data compression has been shown to outperform classical methods in terms of $RD$ performance, with results still improving rapidly. At a high level, neural compression is based on an autoencoder that tries to reconstruct the input instance from a (quantized) latent representation, coupled with a prior that is used to losslessly compress these latents. Due to limitations on model capacity and imperfect optimization and generalization, such models will suboptimally compress test data in general. However, one of the great strengths of learned compression is that if the test-time data distr"},"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":"2101.08687","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-01-21T15:58:58Z","cross_cats_sorted":[],"title_canon_sha256":"384ed7709ec3d4ad30d36fda1e56506fd38063b62844e4f5e46471e9420e5ba9","abstract_canon_sha256":"2941388dc0b1871a3206a9124d3ca3c92039efc048ed05ca89d0408a7cd54855"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:44:53.907418Z","signature_b64":"tEURkoNJRHYHZI63RPL7yt9GrlSeAhqNe8TgVB07WLzHc0AUvVYRPsolf5mXtKH7DD92Ab7RaWxiy/wPiaWaCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c28a5e3e01105a972265408f62ad8428531be068ce936a97aa1cac33cda19e0","last_reissued_at":"2026-07-05T02:44:53.906918Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:44:53.906918Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overfitting for Fun and Profit: Instance-Adaptive Data Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Iris A.M. Huijben, Taco S. Cohen, Ties van Rozendaal","submitted_at":"2021-01-21T15:58:58Z","abstract_excerpt":"Neural data compression has been shown to outperform classical methods in terms of $RD$ performance, with results still improving rapidly. At a high level, neural compression is based on an autoencoder that tries to reconstruct the input instance from a (quantized) latent representation, coupled with a prior that is used to losslessly compress these latents. Due to limitations on model capacity and imperfect optimization and generalization, such models will suboptimally compress test data in general. However, one of the great strengths of learned compression is that if the test-time data distr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08687","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/2101.08687/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":"2101.08687","created_at":"2026-07-05T02:44:53.906972+00:00"},{"alias_kind":"arxiv_version","alias_value":"2101.08687v2","created_at":"2026-07-05T02:44:53.906972+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08687","created_at":"2026-07-05T02:44:53.906972+00:00"},{"alias_kind":"pith_short_12","alias_value":"LQUKLY7ACEC2","created_at":"2026-07-05T02:44:53.906972+00:00"},{"alias_kind":"pith_short_16","alias_value":"LQUKLY7ACEC2S4RG","created_at":"2026-07-05T02:44:53.906972+00:00"},{"alias_kind":"pith_short_8","alias_value":"LQUKLY7A","created_at":"2026-07-05T02:44:53.906972+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.01231","citing_title":"Exploiting Latent Properties to Optimize Neural Codecs","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LQUKLY7ACEC2S4RGKQEPMKWYIK","json":"https://pith.science/pith/LQUKLY7ACEC2S4RGKQEPMKWYIK.json","graph_json":"https://pith.science/api/pith-number/LQUKLY7ACEC2S4RGKQEPMKWYIK/graph.json","events_json":"https://pith.science/api/pith-number/LQUKLY7ACEC2S4RGKQEPMKWYIK/events.json","paper":"https://pith.science/paper/LQUKLY7A"},"agent_actions":{"view_html":"https://pith.science/pith/LQUKLY7ACEC2S4RGKQEPMKWYIK","download_json":"https://pith.science/pith/LQUKLY7ACEC2S4RGKQEPMKWYIK.json","view_paper":"https://pith.science/paper/LQUKLY7A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2101.08687&json=true","fetch_graph":"https://pith.science/api/pith-number/LQUKLY7ACEC2S4RGKQEPMKWYIK/graph.json","fetch_events":"https://pith.science/api/pith-number/LQUKLY7ACEC2S4RGKQEPMKWYIK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LQUKLY7ACEC2S4RGKQEPMKWYIK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LQUKLY7ACEC2S4RGKQEPMKWYIK/action/storage_attestation","attest_author":"https://pith.science/pith/LQUKLY7ACEC2S4RGKQEPMKWYIK/action/author_attestation","sign_citation":"https://pith.science/pith/LQUKLY7ACEC2S4RGKQEPMKWYIK/action/citation_signature","submit_replication":"https://pith.science/pith/LQUKLY7ACEC2S4RGKQEPMKWYIK/action/replication_record"}},"created_at":"2026-07-05T02:44:53.906972+00:00","updated_at":"2026-07-05T02:44:53.906972+00:00"}