{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:4VI7SO2QUFLBJ2MDAOBD24K2XM","short_pith_number":"pith:4VI7SO2Q","schema_version":"1.0","canonical_sha256":"e551f93b50a15614e98303823d715abb1934232d11878b97afa6eac0254a759c","source":{"kind":"arxiv","id":"1905.07088","version":2},"attestation_state":"computed","paper":{"title":"Sliced Score Matching: A Scalable Approach to Density and Score Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiaxin Shi, Sahaj Garg, Stefano Ermon, Yang Song","submitted_at":"2019-05-17T02:02:30Z","abstract_excerpt":"Score matching is a popular method for estimating unnormalized statistical models. However, it has been so far limited to simple, shallow models or low-dimensional data, due to the difficulty of computing the Hessian of log-density functions. We show this difficulty can be mitigated by projecting the scores onto random vectors before comparing them. This objective, called sliced score matching, only involves Hessian-vector products, which can be easily implemented using reverse-mode automatic differentiation. Therefore, sliced score matching is amenable to more complex models and higher dimens"},"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":"1905.07088","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-05-17T02:02:30Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"9a01ddcb8f4aecd0ba3c8a52bc3bb262e1db2cdee9768ba417b082e026eaee54","abstract_canon_sha256":"c25995d88d1d1eba68e78aa99e253faf355ad3513edb1bd4446a78298e193121"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:07.930978Z","signature_b64":"1yCIJ0qd3ytoD3NkAAUAvpmv4uHduYkCAiLFZF+8f0g9LK0O1psQtbDggy871lbVsJh97V1s4GFtespTitDICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e551f93b50a15614e98303823d715abb1934232d11878b97afa6eac0254a759c","last_reissued_at":"2026-05-17T23:42:07.930376Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:07.930376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Sliced Score Matching: A Scalable Approach to Density and Score Estimation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Jiaxin Shi, Sahaj Garg, Stefano Ermon, Yang Song","submitted_at":"2019-05-17T02:02:30Z","abstract_excerpt":"Score matching is a popular method for estimating unnormalized statistical models. However, it has been so far limited to simple, shallow models or low-dimensional data, due to the difficulty of computing the Hessian of log-density functions. We show this difficulty can be mitigated by projecting the scores onto random vectors before comparing them. This objective, called sliced score matching, only involves Hessian-vector products, which can be easily implemented using reverse-mode automatic differentiation. Therefore, sliced score matching is amenable to more complex models and higher dimens"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.07088","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":"1905.07088","created_at":"2026-05-17T23:42:07.930474+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.07088v2","created_at":"2026-05-17T23:42:07.930474+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.07088","created_at":"2026-05-17T23:42:07.930474+00:00"},{"alias_kind":"pith_short_12","alias_value":"4VI7SO2QUFLB","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_16","alias_value":"4VI7SO2QUFLBJ2MD","created_at":"2026-05-18T12:33:10.108867+00:00"},{"alias_kind":"pith_short_8","alias_value":"4VI7SO2Q","created_at":"2026-05-18T12:33:10.108867+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.15394","citing_title":"Representation Without Reward: A JEPA Audit for LLM Fine-Tuning","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2602.13847","citing_title":"Physics and causally constrained discrete-time neural models of turbulent dynamical systems","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26503","citing_title":"Delta Score Matters! Spatial Adaptive Multi Guidance in Diffusion Models","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06829","citing_title":"A Unified Measure-Theoretic View of Diffusion, Score-Based, and Flow Matching Generative Models","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21210","citing_title":"The Feedback Hamiltonian is the Score Function: A Diffusion-Model Framework for Quantum Trajectory Reversal","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4VI7SO2QUFLBJ2MDAOBD24K2XM","json":"https://pith.science/pith/4VI7SO2QUFLBJ2MDAOBD24K2XM.json","graph_json":"https://pith.science/api/pith-number/4VI7SO2QUFLBJ2MDAOBD24K2XM/graph.json","events_json":"https://pith.science/api/pith-number/4VI7SO2QUFLBJ2MDAOBD24K2XM/events.json","paper":"https://pith.science/paper/4VI7SO2Q"},"agent_actions":{"view_html":"https://pith.science/pith/4VI7SO2QUFLBJ2MDAOBD24K2XM","download_json":"https://pith.science/pith/4VI7SO2QUFLBJ2MDAOBD24K2XM.json","view_paper":"https://pith.science/paper/4VI7SO2Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.07088&json=true","fetch_graph":"https://pith.science/api/pith-number/4VI7SO2QUFLBJ2MDAOBD24K2XM/graph.json","fetch_events":"https://pith.science/api/pith-number/4VI7SO2QUFLBJ2MDAOBD24K2XM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4VI7SO2QUFLBJ2MDAOBD24K2XM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4VI7SO2QUFLBJ2MDAOBD24K2XM/action/storage_attestation","attest_author":"https://pith.science/pith/4VI7SO2QUFLBJ2MDAOBD24K2XM/action/author_attestation","sign_citation":"https://pith.science/pith/4VI7SO2QUFLBJ2MDAOBD24K2XM/action/citation_signature","submit_replication":"https://pith.science/pith/4VI7SO2QUFLBJ2MDAOBD24K2XM/action/replication_record"}},"created_at":"2026-05-17T23:42:07.930474+00:00","updated_at":"2026-05-17T23:42:07.930474+00:00"}