{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:UHI5AKSIJJQKAIFXB5OD7OXP3P","short_pith_number":"pith:UHI5AKSI","canonical_record":{"source":{"id":"1712.05997","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-16T17:57:57Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG","stat.AP"],"title_canon_sha256":"7c0a072352ccc4026e89d79202aedea141e4ef65b9268ca6632e18e117b42777","abstract_canon_sha256":"cb46d908241e0735a2c9a8415bff8e93892569e1d154341c14a157fbf8ae15b2"},"schema_version":"1.0"},"canonical_sha256":"a1d1d02a484a60a020b70f5c3fbaefdbdb268a6f1f0e4c8b8bf6782891e4d4c1","source":{"kind":"arxiv","id":"1712.05997","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.05997","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"1712.05997v1","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.05997","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"UHI5AKSIJJQK","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UHI5AKSIJJQKAIFX","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UHI5AKSI","created_at":"2026-05-18T12:31:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:UHI5AKSIJJQKAIFXB5OD7OXP3P","target":"record","payload":{"canonical_record":{"source":{"id":"1712.05997","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-16T17:57:57Z","cross_cats_sorted":["cs.CL","cs.IR","cs.LG","stat.AP"],"title_canon_sha256":"7c0a072352ccc4026e89d79202aedea141e4ef65b9268ca6632e18e117b42777","abstract_canon_sha256":"cb46d908241e0735a2c9a8415bff8e93892569e1d154341c14a157fbf8ae15b2"},"schema_version":"1.0"},"canonical_sha256":"a1d1d02a484a60a020b70f5c3fbaefdbdb268a6f1f0e4c8b8bf6782891e4d4c1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:27:51.329136Z","signature_b64":"8CLSVI42DT+YxrFjuCBpq6vDESBNnuQAFrUsVd+/GoHY7XvuUGSOFJ7zerCppLGuK6+vOXyghkRosxuWlGYoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1d1d02a484a60a020b70f5c3fbaefdbdb268a6f1f0e4c8b8bf6782891e4d4c1","last_reissued_at":"2026-05-18T00:27:51.328614Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:27:51.328614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1712.05997","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":"2026-05-18T00:27:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1ThCa9aSaOgqWWXRftnnFK+3wKvk2YXWOgzPzMVQ1LlzaIzEfElni/Rh9xDbmIPjoS2tvvWDrBjQOXos5UGLDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:58:36.669182Z"},"content_sha256":"fde2714463e2bfa67bfa9a7bc1bdea6db8d5f27f81957b8062e7b84e9a3a067d","schema_version":"1.0","event_id":"sha256:fde2714463e2bfa67bfa9a7bc1bdea6db8d5f27f81957b8062e7b84e9a3a067d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:UHI5AKSIJJQKAIFXB5OD7OXP3P","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Taming Wild High Dimensional Text Data with a Fuzzy Lash","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.IR","cs.LG","stat.AP"],"primary_cat":"stat.ML","authors_text":"Amir Karami","submitted_at":"2017-12-16T17:57:57Z","abstract_excerpt":"The bag of words (BOW) represents a corpus in a matrix whose elements are the frequency of words. However, each row in the matrix is a very high-dimensional sparse vector. Dimension reduction (DR) is a popular method to address sparsity and high-dimensionality issues. Among different strategies to develop DR method, Unsupervised Feature Transformation (UFT) is a popular strategy to map all words on a new basis to represent BOW. The recent increase of text data and its challenges imply that DR area still needs new perspectives. Although a wide range of methods based on the UFT strategy has been"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.05997","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":"2026-05-18T00:27:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gpmWXv2v0QHu3gJzm3bArtpWOwOiLC9tlvKs/sdUGxDMjQTMoUL1SN9FhBUzfGwBOzsGIuioWaAIGAkWpzK/Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-01T12:58:36.669609Z"},"content_sha256":"40323bc628488dc6a87eb0a27d1040018afb3c5ad940e4e831860732ef0096cb","schema_version":"1.0","event_id":"sha256:40323bc628488dc6a87eb0a27d1040018afb3c5ad940e4e831860732ef0096cb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UHI5AKSIJJQKAIFXB5OD7OXP3P/bundle.json","state_url":"https://pith.science/pith/UHI5AKSIJJQKAIFXB5OD7OXP3P/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UHI5AKSIJJQKAIFXB5OD7OXP3P/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":"2026-06-01T12:58:36Z","links":{"resolver":"https://pith.science/pith/UHI5AKSIJJQKAIFXB5OD7OXP3P","bundle":"https://pith.science/pith/UHI5AKSIJJQKAIFXB5OD7OXP3P/bundle.json","state":"https://pith.science/pith/UHI5AKSIJJQKAIFXB5OD7OXP3P/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UHI5AKSIJJQKAIFXB5OD7OXP3P/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:UHI5AKSIJJQKAIFXB5OD7OXP3P","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":"cb46d908241e0735a2c9a8415bff8e93892569e1d154341c14a157fbf8ae15b2","cross_cats_sorted":["cs.CL","cs.IR","cs.LG","stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-16T17:57:57Z","title_canon_sha256":"7c0a072352ccc4026e89d79202aedea141e4ef65b9268ca6632e18e117b42777"},"schema_version":"1.0","source":{"id":"1712.05997","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1712.05997","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"arxiv_version","alias_value":"1712.05997v1","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1712.05997","created_at":"2026-05-18T00:27:51Z"},{"alias_kind":"pith_short_12","alias_value":"UHI5AKSIJJQK","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_16","alias_value":"UHI5AKSIJJQKAIFX","created_at":"2026-05-18T12:31:46Z"},{"alias_kind":"pith_short_8","alias_value":"UHI5AKSI","created_at":"2026-05-18T12:31:46Z"}],"graph_snapshots":[{"event_id":"sha256:40323bc628488dc6a87eb0a27d1040018afb3c5ad940e4e831860732ef0096cb","target":"graph","created_at":"2026-05-18T00:27:51Z","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":"The bag of words (BOW) represents a corpus in a matrix whose elements are the frequency of words. However, each row in the matrix is a very high-dimensional sparse vector. Dimension reduction (DR) is a popular method to address sparsity and high-dimensionality issues. Among different strategies to develop DR method, Unsupervised Feature Transformation (UFT) is a popular strategy to map all words on a new basis to represent BOW. The recent increase of text data and its challenges imply that DR area still needs new perspectives. Although a wide range of methods based on the UFT strategy has been","authors_text":"Amir Karami","cross_cats":["cs.CL","cs.IR","cs.LG","stat.AP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-16T17:57:57Z","title":"Taming Wild High Dimensional Text Data with a Fuzzy Lash"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1712.05997","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:fde2714463e2bfa67bfa9a7bc1bdea6db8d5f27f81957b8062e7b84e9a3a067d","target":"record","created_at":"2026-05-18T00:27:51Z","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":"cb46d908241e0735a2c9a8415bff8e93892569e1d154341c14a157fbf8ae15b2","cross_cats_sorted":["cs.CL","cs.IR","cs.LG","stat.AP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-12-16T17:57:57Z","title_canon_sha256":"7c0a072352ccc4026e89d79202aedea141e4ef65b9268ca6632e18e117b42777"},"schema_version":"1.0","source":{"id":"1712.05997","kind":"arxiv","version":1}},"canonical_sha256":"a1d1d02a484a60a020b70f5c3fbaefdbdb268a6f1f0e4c8b8bf6782891e4d4c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1d1d02a484a60a020b70f5c3fbaefdbdb268a6f1f0e4c8b8bf6782891e4d4c1","first_computed_at":"2026-05-18T00:27:51.328614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:27:51.328614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8CLSVI42DT+YxrFjuCBpq6vDESBNnuQAFrUsVd+/GoHY7XvuUGSOFJ7zerCppLGuK6+vOXyghkRosxuWlGYoAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:27:51.329136Z","signed_message":"canonical_sha256_bytes"},"source_id":"1712.05997","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fde2714463e2bfa67bfa9a7bc1bdea6db8d5f27f81957b8062e7b84e9a3a067d","sha256:40323bc628488dc6a87eb0a27d1040018afb3c5ad940e4e831860732ef0096cb"],"state_sha256":"c8f1c383585168900ecea2ebc2a8147d2fac8bd8df67b1200c4ed8d7bc1cf32c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Npp68uYJ88hjM8Ow4VitbCmGPbA3uSxzkIIj6TyWAXbyTGZuu9Z0yRV1f/TCqRMRCTsDTwFvnJ/7ca95T8QfCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-01T12:58:36.671747Z","bundle_sha256":"225f54c8545addfc328f40b7535638e5dbee1e8a475210308fc996771706072e"}}