{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:WZ2PCDFJKHDG6X5IOCP5I3BNKI","short_pith_number":"pith:WZ2PCDFJ","canonical_record":{"source":{"id":"1607.04883","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2016-07-17T15:49:24Z","cross_cats_sorted":["q-fin.ST"],"title_canon_sha256":"85acf31f2bd8e49768aa36609e8c90d75c0dc030228a8428651f8e89d43fc92f","abstract_canon_sha256":"c957a16c81623fc27a9e5001323a615c7aa1978c7547b5368ca49a36431f37af"},"schema_version":"1.0"},"canonical_sha256":"b674f10ca951c66f5fa8709fd46c2d5218e8ffa7e0e486797b0f5f3bd0841613","source":{"kind":"arxiv","id":"1607.04883","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.04883","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"1607.04883v4","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.04883","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"WZ2PCDFJKHDG","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"WZ2PCDFJKHDG6X5I","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"WZ2PCDFJ","created_at":"2026-05-18T12:30:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:WZ2PCDFJKHDG6X5IOCP5I3BNKI","target":"record","payload":{"canonical_record":{"source":{"id":"1607.04883","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2016-07-17T15:49:24Z","cross_cats_sorted":["q-fin.ST"],"title_canon_sha256":"85acf31f2bd8e49768aa36609e8c90d75c0dc030228a8428651f8e89d43fc92f","abstract_canon_sha256":"c957a16c81623fc27a9e5001323a615c7aa1978c7547b5368ca49a36431f37af"},"schema_version":"1.0"},"canonical_sha256":"b674f10ca951c66f5fa8709fd46c2d5218e8ffa7e0e486797b0f5f3bd0841613","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:57:15.979823Z","signature_b64":"j7MmYqHju+rjioZytr1LnXn5HCpFwWAfOy+fCKyVimrNsICFlCR9Bv8sr5ayC8lVy1Yq+CUHlgnjqgmfPed/DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b674f10ca951c66f5fa8709fd46c2d5218e8ffa7e0e486797b0f5f3bd0841613","last_reissued_at":"2026-05-17T23:57:15.979434Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:57:15.979434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1607.04883","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dLZd0033mrp5402p0LM3SpfDGxH5aCOygl3yEviXr1dWvGqHnusATIhb2E6lGyqqshNzzmo6D/pX3yHNtsWNBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:26:04.852225Z"},"content_sha256":"e6c467bdec7e931249c80beb9370ecffc11d0c72afeb001d4b43c648baa332a4","schema_version":"1.0","event_id":"sha256:e6c467bdec7e931249c80beb9370ecffc11d0c72afeb001d4b43c648baa332a4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:WZ2PCDFJKHDG6X5IOCP5I3BNKI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Statistical Industry Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["q-fin.ST"],"primary_cat":"q-fin.PM","authors_text":"Willie Yu, Zura Kakushadze","submitted_at":"2016-07-17T15:49:24Z","abstract_excerpt":"We give complete algorithms and source code for constructing (multilevel) statistical industry classifications, including methods for fixing the number of clusters at each level (and the number of levels). Under the hood there are clustering algorithms (e.g., k-means). However, what should we cluster? Correlations? Returns? The answer turns out to be neither and our backtests suggest that these details make a sizable difference. We also give an algorithm and source code for building \"hybrid\" industry classifications by improving off-the-shelf \"fundamental\" industry classifications by applying "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.04883","kind":"arxiv","version":4},"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":"2026-05-17T23:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z+/PcOqLGgFFKUToQcs9lSYM+yYLk5FbK75tDrVykY87BmMPRLwNDzZNqcPctiIwObhvqCkzrZwC5ow/SGiECg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T23:26:04.852614Z"},"content_sha256":"544015a8de0af53d2587f48852ce376880c696cf42b65443eb5a286bb4ff9cb0","schema_version":"1.0","event_id":"sha256:544015a8de0af53d2587f48852ce376880c696cf42b65443eb5a286bb4ff9cb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WZ2PCDFJKHDG6X5IOCP5I3BNKI/bundle.json","state_url":"https://pith.science/pith/WZ2PCDFJKHDG6X5IOCP5I3BNKI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WZ2PCDFJKHDG6X5IOCP5I3BNKI/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":"2026-05-22T23:26:04Z","links":{"resolver":"https://pith.science/pith/WZ2PCDFJKHDG6X5IOCP5I3BNKI","bundle":"https://pith.science/pith/WZ2PCDFJKHDG6X5IOCP5I3BNKI/bundle.json","state":"https://pith.science/pith/WZ2PCDFJKHDG6X5IOCP5I3BNKI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WZ2PCDFJKHDG6X5IOCP5I3BNKI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:WZ2PCDFJKHDG6X5IOCP5I3BNKI","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":"c957a16c81623fc27a9e5001323a615c7aa1978c7547b5368ca49a36431f37af","cross_cats_sorted":["q-fin.ST"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2016-07-17T15:49:24Z","title_canon_sha256":"85acf31f2bd8e49768aa36609e8c90d75c0dc030228a8428651f8e89d43fc92f"},"schema_version":"1.0","source":{"id":"1607.04883","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1607.04883","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"1607.04883v4","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1607.04883","created_at":"2026-05-17T23:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"WZ2PCDFJKHDG","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"WZ2PCDFJKHDG6X5I","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"WZ2PCDFJ","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:544015a8de0af53d2587f48852ce376880c696cf42b65443eb5a286bb4ff9cb0","target":"graph","created_at":"2026-05-17T23:57:15Z","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":"We give complete algorithms and source code for constructing (multilevel) statistical industry classifications, including methods for fixing the number of clusters at each level (and the number of levels). Under the hood there are clustering algorithms (e.g., k-means). However, what should we cluster? Correlations? Returns? The answer turns out to be neither and our backtests suggest that these details make a sizable difference. We also give an algorithm and source code for building \"hybrid\" industry classifications by improving off-the-shelf \"fundamental\" industry classifications by applying ","authors_text":"Willie Yu, Zura Kakushadze","cross_cats":["q-fin.ST"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2016-07-17T15:49:24Z","title":"Statistical Industry Classification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1607.04883","kind":"arxiv","version":4},"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:e6c467bdec7e931249c80beb9370ecffc11d0c72afeb001d4b43c648baa332a4","target":"record","created_at":"2026-05-17T23:57:15Z","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":"c957a16c81623fc27a9e5001323a615c7aa1978c7547b5368ca49a36431f37af","cross_cats_sorted":["q-fin.ST"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.PM","submitted_at":"2016-07-17T15:49:24Z","title_canon_sha256":"85acf31f2bd8e49768aa36609e8c90d75c0dc030228a8428651f8e89d43fc92f"},"schema_version":"1.0","source":{"id":"1607.04883","kind":"arxiv","version":4}},"canonical_sha256":"b674f10ca951c66f5fa8709fd46c2d5218e8ffa7e0e486797b0f5f3bd0841613","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b674f10ca951c66f5fa8709fd46c2d5218e8ffa7e0e486797b0f5f3bd0841613","first_computed_at":"2026-05-17T23:57:15.979434Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:57:15.979434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j7MmYqHju+rjioZytr1LnXn5HCpFwWAfOy+fCKyVimrNsICFlCR9Bv8sr5ayC8lVy1Yq+CUHlgnjqgmfPed/DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:57:15.979823Z","signed_message":"canonical_sha256_bytes"},"source_id":"1607.04883","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e6c467bdec7e931249c80beb9370ecffc11d0c72afeb001d4b43c648baa332a4","sha256:544015a8de0af53d2587f48852ce376880c696cf42b65443eb5a286bb4ff9cb0"],"state_sha256":"e0c5179538906eed116b403d8ee1c2b5331d0f0ae9196ecfe3540ca39e630504"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gyZMcHXSANxfLrnMQH/YF1YxfLpSrMAohQY6Tb/R7UgkxCi1d2y23WXDscK5emEl4K82/gKyXmcg7McbY+M+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T23:26:04.855452Z","bundle_sha256":"0d2dc4d4ee904f259db7ed8489deba086dbcab9ac424c51a0f9d8343599ae21e"}}