{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:6NTPV3RC4KEVWSCG5AHUD2ZNVQ","short_pith_number":"pith:6NTPV3RC","schema_version":"1.0","canonical_sha256":"f366faee22e2895b4846e80f41eb2dac1799b015da0520261647f0781fd995cb","source":{"kind":"arxiv","id":"1710.10629","version":2},"attestation_state":"computed","paper":{"title":"Dimensionality reduction methods for molecular simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"stat.ML","authors_text":"Gianni de Fabritiis, Igor Ariz-Extreme, Matthew J. Harvey, Stefan Doerr","submitted_at":"2017-10-29T15:33:42Z","abstract_excerpt":"Molecular simulations produce very high-dimensional data-sets with millions of data points. As analysis methods are often unable to cope with so many dimensions, it is common to use dimensionality reduction and clustering methods to reach a reduced representation of the data. Yet these methods often fail to capture the most important features necessary for the construction of a Markov model. Here we demonstrate the results of various dimensionality reduction methods on two simulation data-sets, one of protein folding and another of protein-ligand binding. The methods tested include a k-means c"},"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":"1710.10629","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2017-10-29T15:33:42Z","cross_cats_sorted":["cs.LG","q-bio.BM"],"title_canon_sha256":"b5a8ad2623679bb63cd5cfb5636c673dc119952035fc98e6a4f8e2af74603467","abstract_canon_sha256":"68e6923542de71fd80684b0a2e051f9ce6de9842bd2e99b2e98c8b27353a08c0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:31:30.599119Z","signature_b64":"PWQVhdkGEiCF2sGhuiOzeIlrD3d5cC70E4JWFs39KOv2KKmH+7SLeGH8Ok8GmQsCoCY3a1CR/5O2bWlyjY+bAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f366faee22e2895b4846e80f41eb2dac1799b015da0520261647f0781fd995cb","last_reissued_at":"2026-05-18T00:31:30.598377Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:31:30.598377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dimensionality reduction methods for molecular simulations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","q-bio.BM"],"primary_cat":"stat.ML","authors_text":"Gianni de Fabritiis, Igor Ariz-Extreme, Matthew J. Harvey, Stefan Doerr","submitted_at":"2017-10-29T15:33:42Z","abstract_excerpt":"Molecular simulations produce very high-dimensional data-sets with millions of data points. As analysis methods are often unable to cope with so many dimensions, it is common to use dimensionality reduction and clustering methods to reach a reduced representation of the data. Yet these methods often fail to capture the most important features necessary for the construction of a Markov model. Here we demonstrate the results of various dimensionality reduction methods on two simulation data-sets, one of protein folding and another of protein-ligand binding. The methods tested include a k-means c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.10629","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":""},"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":"1710.10629","created_at":"2026-05-18T00:31:30.598502+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.10629v2","created_at":"2026-05-18T00:31:30.598502+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.10629","created_at":"2026-05-18T00:31:30.598502+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NTPV3RC4KEV","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NTPV3RC4KEVWSCG","created_at":"2026-05-18T12:31:03.183658+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NTPV3RC","created_at":"2026-05-18T12:31:03.183658+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16330","citing_title":"A Data-Driven Parametric Reduced-Order Chemical Kinetics Model Derived from Atomistic Simulations","ref_index":46,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NTPV3RC4KEVWSCG5AHUD2ZNVQ","json":"https://pith.science/pith/6NTPV3RC4KEVWSCG5AHUD2ZNVQ.json","graph_json":"https://pith.science/api/pith-number/6NTPV3RC4KEVWSCG5AHUD2ZNVQ/graph.json","events_json":"https://pith.science/api/pith-number/6NTPV3RC4KEVWSCG5AHUD2ZNVQ/events.json","paper":"https://pith.science/paper/6NTPV3RC"},"agent_actions":{"view_html":"https://pith.science/pith/6NTPV3RC4KEVWSCG5AHUD2ZNVQ","download_json":"https://pith.science/pith/6NTPV3RC4KEVWSCG5AHUD2ZNVQ.json","view_paper":"https://pith.science/paper/6NTPV3RC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.10629&json=true","fetch_graph":"https://pith.science/api/pith-number/6NTPV3RC4KEVWSCG5AHUD2ZNVQ/graph.json","fetch_events":"https://pith.science/api/pith-number/6NTPV3RC4KEVWSCG5AHUD2ZNVQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NTPV3RC4KEVWSCG5AHUD2ZNVQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NTPV3RC4KEVWSCG5AHUD2ZNVQ/action/storage_attestation","attest_author":"https://pith.science/pith/6NTPV3RC4KEVWSCG5AHUD2ZNVQ/action/author_attestation","sign_citation":"https://pith.science/pith/6NTPV3RC4KEVWSCG5AHUD2ZNVQ/action/citation_signature","submit_replication":"https://pith.science/pith/6NTPV3RC4KEVWSCG5AHUD2ZNVQ/action/replication_record"}},"created_at":"2026-05-18T00:31:30.598502+00:00","updated_at":"2026-05-18T00:31:30.598502+00:00"}