{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:YVZIM4OZE3EXVG363NIT36PYKZ","short_pith_number":"pith:YVZIM4OZ","canonical_record":{"source":{"id":"1702.08565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2017-02-27T22:29:11Z","cross_cats_sorted":["cs.IT","math.IT","nlin.CD","stat.ML"],"title_canon_sha256":"21159723d957b35a791567337e623de9cc828d4bca4421ce70127b5da7fd8a7f","abstract_canon_sha256":"18ae487d1a3a39affbb038f22b609b99d88309d98347e1e8c0ced910cf13f79b"},"schema_version":"1.0"},"canonical_sha256":"c5728671d926c97a9b7edb513df9f8564b964e953d4bd4b626ef2e047a678e6a","source":{"kind":"arxiv","id":"1702.08565","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08565","created_at":"2026-05-18T00:43:26Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08565v1","created_at":"2026-05-18T00:43:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08565","created_at":"2026-05-18T00:43:26Z"},{"alias_kind":"pith_short_12","alias_value":"YVZIM4OZE3EX","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YVZIM4OZE3EXVG36","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YVZIM4OZ","created_at":"2026-05-18T12:31:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:YVZIM4OZE3EXVG363NIT36PYKZ","target":"record","payload":{"canonical_record":{"source":{"id":"1702.08565","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2017-02-27T22:29:11Z","cross_cats_sorted":["cs.IT","math.IT","nlin.CD","stat.ML"],"title_canon_sha256":"21159723d957b35a791567337e623de9cc828d4bca4421ce70127b5da7fd8a7f","abstract_canon_sha256":"18ae487d1a3a39affbb038f22b609b99d88309d98347e1e8c0ced910cf13f79b"},"schema_version":"1.0"},"canonical_sha256":"c5728671d926c97a9b7edb513df9f8564b964e953d4bd4b626ef2e047a678e6a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:43:26.529775Z","signature_b64":"EukvRJrSeaoY+hvK+EQLT1gsc//Fzz3tvYQZzLQ6tJSSwqinGI7vsq43vEKaOXaQj9NOYBXa5eaEuOpPBSZqCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5728671d926c97a9b7edb513df9f8564b964e953d4bd4b626ef2e047a678e6a","last_reissued_at":"2026-05-18T00:43:26.529105Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:43:26.529105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1702.08565","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YpWk4ezwuhHfBTXOZci5qPOay72v5s1eGeIyQK8OvTsB4PvUiFaTWfYqi4lXhm1wgMkbHBLcAhvjaUW4lnfrAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:49:50.443423Z"},"content_sha256":"1fba0ffad906f403774a92f1463fddb74d11262992a95b6afd4e4e1aa121b6b1","schema_version":"1.0","event_id":"sha256:1fba0ffad906f403774a92f1463fddb74d11262992a95b6afd4e4e1aa121b6b1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:YVZIM4OZE3EXVG363NIT36PYKZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Nearly Maximally Predictive Features and Their Dimensions","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IT","math.IT","nlin.CD","stat.ML"],"primary_cat":"cond-mat.stat-mech","authors_text":"James P. Crutchfield, Sarah E. Marzen","submitted_at":"2017-02-27T22:29:11Z","abstract_excerpt":"Scientific explanation often requires inferring maximally predictive features from a given data set. Unfortunately, the collection of minimal maximally predictive features for most stochastic processes is uncountably infinite. In such cases, one compromises and instead seeks nearly maximally predictive features. Here, we derive upper-bounds on the rates at which the number and the coding cost of nearly maximally predictive features scales with desired predictive power. The rates are determined by the fractal dimensions of a process' mixed-state distribution. These results, in turn, show how wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08565","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":""},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T00:43:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rno9J09hPxv8bxmk2IoZkhEG6mtRapiFGrdI4pDqt+DhftpQWbwVuZE/EMmHPZ2I90FCIS7YxZBiZKo3xd4wBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-08T02:49:50.444121Z"},"content_sha256":"e7c8059813f36aa8d4669fe5f87606c2da72f46ad1755169f80f4b340f807a10","schema_version":"1.0","event_id":"sha256:e7c8059813f36aa8d4669fe5f87606c2da72f46ad1755169f80f4b340f807a10"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YVZIM4OZE3EXVG363NIT36PYKZ/bundle.json","state_url":"https://pith.science/pith/YVZIM4OZE3EXVG363NIT36PYKZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YVZIM4OZE3EXVG363NIT36PYKZ/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-08T02:49:50Z","links":{"resolver":"https://pith.science/pith/YVZIM4OZE3EXVG363NIT36PYKZ","bundle":"https://pith.science/pith/YVZIM4OZE3EXVG363NIT36PYKZ/bundle.json","state":"https://pith.science/pith/YVZIM4OZE3EXVG363NIT36PYKZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YVZIM4OZE3EXVG363NIT36PYKZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:YVZIM4OZE3EXVG363NIT36PYKZ","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":"18ae487d1a3a39affbb038f22b609b99d88309d98347e1e8c0ced910cf13f79b","cross_cats_sorted":["cs.IT","math.IT","nlin.CD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2017-02-27T22:29:11Z","title_canon_sha256":"21159723d957b35a791567337e623de9cc828d4bca4421ce70127b5da7fd8a7f"},"schema_version":"1.0","source":{"id":"1702.08565","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1702.08565","created_at":"2026-05-18T00:43:26Z"},{"alias_kind":"arxiv_version","alias_value":"1702.08565v1","created_at":"2026-05-18T00:43:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1702.08565","created_at":"2026-05-18T00:43:26Z"},{"alias_kind":"pith_short_12","alias_value":"YVZIM4OZE3EX","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_16","alias_value":"YVZIM4OZE3EXVG36","created_at":"2026-05-18T12:31:56Z"},{"alias_kind":"pith_short_8","alias_value":"YVZIM4OZ","created_at":"2026-05-18T12:31:56Z"}],"graph_snapshots":[{"event_id":"sha256:e7c8059813f36aa8d4669fe5f87606c2da72f46ad1755169f80f4b340f807a10","target":"graph","created_at":"2026-05-18T00:43:26Z","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"},"paper":{"abstract_excerpt":"Scientific explanation often requires inferring maximally predictive features from a given data set. Unfortunately, the collection of minimal maximally predictive features for most stochastic processes is uncountably infinite. In such cases, one compromises and instead seeks nearly maximally predictive features. Here, we derive upper-bounds on the rates at which the number and the coding cost of nearly maximally predictive features scales with desired predictive power. The rates are determined by the fractal dimensions of a process' mixed-state distribution. These results, in turn, show how wi","authors_text":"James P. Crutchfield, Sarah E. Marzen","cross_cats":["cs.IT","math.IT","nlin.CD","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2017-02-27T22:29:11Z","title":"Nearly Maximally Predictive Features and Their Dimensions"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1702.08565","kind":"arxiv","version":1},"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":"sha256:1fba0ffad906f403774a92f1463fddb74d11262992a95b6afd4e4e1aa121b6b1","target":"record","created_at":"2026-05-18T00:43:26Z","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":"18ae487d1a3a39affbb038f22b609b99d88309d98347e1e8c0ced910cf13f79b","cross_cats_sorted":["cs.IT","math.IT","nlin.CD","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2017-02-27T22:29:11Z","title_canon_sha256":"21159723d957b35a791567337e623de9cc828d4bca4421ce70127b5da7fd8a7f"},"schema_version":"1.0","source":{"id":"1702.08565","kind":"arxiv","version":1}},"canonical_sha256":"c5728671d926c97a9b7edb513df9f8564b964e953d4bd4b626ef2e047a678e6a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5728671d926c97a9b7edb513df9f8564b964e953d4bd4b626ef2e047a678e6a","first_computed_at":"2026-05-18T00:43:26.529105Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:43:26.529105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EukvRJrSeaoY+hvK+EQLT1gsc//Fzz3tvYQZzLQ6tJSSwqinGI7vsq43vEKaOXaQj9NOYBXa5eaEuOpPBSZqCw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:43:26.529775Z","signed_message":"canonical_sha256_bytes"},"source_id":"1702.08565","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1fba0ffad906f403774a92f1463fddb74d11262992a95b6afd4e4e1aa121b6b1","sha256:e7c8059813f36aa8d4669fe5f87606c2da72f46ad1755169f80f4b340f807a10"],"state_sha256":"8a7edf923c613325e5dfe17b9262c099bb80e12b155ede12e51819458e101a8c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"btaGLYALBKS17ri9+ZW5uIsUmtuIjlszqH7wej/6JxKdDZxCCABANDkOv8isz4jz5rNlh0c6QBKjQHpIDWU2DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-08T02:49:50.448225Z","bundle_sha256":"7aa9cd5eb4e83cbc10e0bd9054de8408f651252c2b9f44ff71023fb0d4f61edc"}}