{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:EAE5HWSHXQYI35OAJDT4BC7R5L","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"38be84a57066f2fdeb1596d2445ae5f1f214e2320839c34ea0d5bf557e56ec3a","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-23T18:00:40Z","title_canon_sha256":"2e62a7d3f384a63dcc14db171fcffcb21de38e717b63597dcf682857f6dc99a1"},"schema_version":"1.0","source":{"id":"1908.08961","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1908.08961","created_at":"2026-07-05T00:33:35Z"},{"alias_kind":"arxiv_version","alias_value":"1908.08961v2","created_at":"2026-07-05T00:33:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1908.08961","created_at":"2026-07-05T00:33:35Z"},{"alias_kind":"pith_short_12","alias_value":"EAE5HWSHXQYI","created_at":"2026-07-05T00:33:35Z"},{"alias_kind":"pith_short_16","alias_value":"EAE5HWSHXQYI35OA","created_at":"2026-07-05T00:33:35Z"},{"alias_kind":"pith_short_8","alias_value":"EAE5HWSH","created_at":"2026-07-05T00:33:35Z"}],"graph_snapshots":[{"event_id":"sha256:fd98bc845d90bae99b8a31dac9f1084a90f8a85ad75fdf59958f42485fb787d2","target":"graph","created_at":"2026-07-05T00:33:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/1908.08961/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The goal of lossy data compression is to reduce the storage cost of a data set $X$ while retaining as much information as possible about something ($Y$) that you care about. For example, what aspects of an image $X$ contain the most information about whether it depicts a cat? Mathematically, this corresponds to finding a mapping $X\\to Z\\equiv f(X)$ that maximizes the mutual information $I(Z,Y)$ while the entropy $H(Z)$ is kept below some fixed threshold. We present a method for mapping out the Pareto frontier for classification tasks, reflecting the tradeoff between retained entropy and class ","authors_text":"Max Tegmark (MIT), Tailin Wu (MIT)","cross_cats":["cs.CV","cs.IT","math.IT","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-23T18:00:40Z","title":"Pareto-optimal data compression for binary classification tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1908.08961","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1789f8ef7641e0628200bf9c7937a98187a80ab8b5266761b0586e4a0b3b2a22","target":"record","created_at":"2026-07-05T00:33:35Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"38be84a57066f2fdeb1596d2445ae5f1f214e2320839c34ea0d5bf557e56ec3a","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-08-23T18:00:40Z","title_canon_sha256":"2e62a7d3f384a63dcc14db171fcffcb21de38e717b63597dcf682857f6dc99a1"},"schema_version":"1.0","source":{"id":"1908.08961","kind":"arxiv","version":2}},"canonical_sha256":"2009d3da47bc308df5c048e7c08bf1eaedfafabba3a2695d70da35928fcf6ec4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2009d3da47bc308df5c048e7c08bf1eaedfafabba3a2695d70da35928fcf6ec4","first_computed_at":"2026-07-05T00:33:35.342447Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:33:35.342447Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xEzlIpRUrzDV+bOdcAgQkP1L0ZK8kuIqHudXpu2+/Wwv7k7Der9e9ytxz5gIo18gArWZ1C6U1jeON7FOTTp6Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:33:35.342837Z","signed_message":"canonical_sha256_bytes"},"source_id":"1908.08961","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1789f8ef7641e0628200bf9c7937a98187a80ab8b5266761b0586e4a0b3b2a22","sha256:fd98bc845d90bae99b8a31dac9f1084a90f8a85ad75fdf59958f42485fb787d2"],"state_sha256":"ed805b4d542da854bcf6106dbd0a02a0929e94c58c05f39b259c3b306871f761"}