{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:LGU7I57FAOZ53TSDNDERBA5RZH","short_pith_number":"pith:LGU7I57F","schema_version":"1.0","canonical_sha256":"59a9f477e503b3ddce4368c91083b1c9fa75dc65d00e26509bd1a1c4b67e3eed","source":{"kind":"arxiv","id":"2201.01741","version":2},"attestation_state":"computed","paper":{"title":"Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician's Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Robert Bamler","submitted_at":"2022-01-05T18:04:42Z","abstract_excerpt":"Entropy coding is the backbone data compression. Novel machine-learning based compression methods often use a new entropy coder called Asymmetric Numeral Systems (ANS) [Duda et al., 2015], which provides very close to optimal bitrates and simplifies [Townsend et al., 2019] advanced compression techniques such as bits-back coding. However, researchers with a background in machine learning often struggle to understand how ANS works, which prevents them from exploiting its full versatility. This paper is meant as an educational resource to make ANS more approachable by presenting it from a new pe"},"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":"2201.01741","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2022-01-05T18:04:42Z","cross_cats_sorted":["cs.IT","cs.LG","math.IT"],"title_canon_sha256":"daae1a6ef0a61c948d55e5fa7e5487fd455b73dbbc6dd71132513c5fe8a8fb97","abstract_canon_sha256":"e0724c65aa7cacf72f0a531851e790d1e298f4e05691fa116247b68df8ad429c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:47:03.841710Z","signature_b64":"5AJ/pWQjF9RvuRIGeoqg2miG2mH28riZgqPTU1qjHUAufCy/2M/n5NvKa7AqH8x4j6qiNTi60dZOPULM7qSrBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59a9f477e503b3ddce4368c91083b1c9fa75dc65d00e26509bd1a1c4b67e3eed","last_reissued_at":"2026-07-05T03:47:03.841252Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:47:03.841252Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Entropy Coding With Asymmetric Numeral Systems (ANS): a Statistician's Perspective","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","cs.LG","math.IT"],"primary_cat":"stat.ML","authors_text":"Robert Bamler","submitted_at":"2022-01-05T18:04:42Z","abstract_excerpt":"Entropy coding is the backbone data compression. Novel machine-learning based compression methods often use a new entropy coder called Asymmetric Numeral Systems (ANS) [Duda et al., 2015], which provides very close to optimal bitrates and simplifies [Townsend et al., 2019] advanced compression techniques such as bits-back coding. However, researchers with a background in machine learning often struggle to understand how ANS works, which prevents them from exploiting its full versatility. This paper is meant as an educational resource to make ANS more approachable by presenting it from a new pe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.01741","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/2201.01741/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":"2201.01741","created_at":"2026-07-05T03:47:03.841322+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.01741v2","created_at":"2026-07-05T03:47:03.841322+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.01741","created_at":"2026-07-05T03:47:03.841322+00:00"},{"alias_kind":"pith_short_12","alias_value":"LGU7I57FAOZ5","created_at":"2026-07-05T03:47:03.841322+00:00"},{"alias_kind":"pith_short_16","alias_value":"LGU7I57FAOZ53TSD","created_at":"2026-07-05T03:47:03.841322+00:00"},{"alias_kind":"pith_short_8","alias_value":"LGU7I57F","created_at":"2026-07-05T03:47:03.841322+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24531","citing_title":"Unified Position-Invariant Random Access Through Two Compression Layers via Absolute-Offset Coordinates: A Bit-Perfect Device-Resident Proof","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21655","citing_title":"PaaF: Raising the perceived quality of INR-Based Image Compression","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06055","citing_title":"Singular Relative Entropy Coding with Bits-Back Rejection Sampling","ref_index":15,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LGU7I57FAOZ53TSDNDERBA5RZH","json":"https://pith.science/pith/LGU7I57FAOZ53TSDNDERBA5RZH.json","graph_json":"https://pith.science/api/pith-number/LGU7I57FAOZ53TSDNDERBA5RZH/graph.json","events_json":"https://pith.science/api/pith-number/LGU7I57FAOZ53TSDNDERBA5RZH/events.json","paper":"https://pith.science/paper/LGU7I57F"},"agent_actions":{"view_html":"https://pith.science/pith/LGU7I57FAOZ53TSDNDERBA5RZH","download_json":"https://pith.science/pith/LGU7I57FAOZ53TSDNDERBA5RZH.json","view_paper":"https://pith.science/paper/LGU7I57F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.01741&json=true","fetch_graph":"https://pith.science/api/pith-number/LGU7I57FAOZ53TSDNDERBA5RZH/graph.json","fetch_events":"https://pith.science/api/pith-number/LGU7I57FAOZ53TSDNDERBA5RZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LGU7I57FAOZ53TSDNDERBA5RZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LGU7I57FAOZ53TSDNDERBA5RZH/action/storage_attestation","attest_author":"https://pith.science/pith/LGU7I57FAOZ53TSDNDERBA5RZH/action/author_attestation","sign_citation":"https://pith.science/pith/LGU7I57FAOZ53TSDNDERBA5RZH/action/citation_signature","submit_replication":"https://pith.science/pith/LGU7I57FAOZ53TSDNDERBA5RZH/action/replication_record"}},"created_at":"2026-07-05T03:47:03.841322+00:00","updated_at":"2026-07-05T03:47:03.841322+00:00"}