{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:A5ISV53QFCLBQIWC3DC4HP6TK4","short_pith_number":"pith:A5ISV53Q","schema_version":"1.0","canonical_sha256":"07512af77028961822c2d8c5c3bfd35708f327da815d7b31a17dd928b5f5dc34","source":{"kind":"arxiv","id":"2605.26850","version":1},"attestation_state":"computed","paper":{"title":"Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arto Klami, Hanlin Yu, Michael U. Gutmann, Omar Chehab, Partha Kaushik, RuiKang OuYang","submitted_at":"2026-05-26T11:07:02Z","abstract_excerpt":"Learning an energy-based model from data samples is a central problem in machine learning. Many recent and popular methods, such as denoising score matching for training energy-based diffusion models, use stochastic interpolants to corrupt data samples at different noise levels indexed by a time variable. This defines a joint density over both the data space and time, and most methods learn its energy through either spatial or temporal differences. We identify distinct failure modes for both of these approaches. To solve them, we propose Spatiotemporal Noise-Contrastive Estimation (stNCE), a f"},"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":"2605.26850","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T11:07:02Z","cross_cats_sorted":[],"title_canon_sha256":"ef03f524160eb4e18052974d547545dacf0b03fb193333d83f9e0aa821344700","abstract_canon_sha256":"ae45793bf124b02527aa1c92fc215020983105f8ea08f7f8a1e509a0e92dfaa3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:06:15.610355Z","signature_b64":"YV93YzzOsm8bo/hobajGop9WggnFTbcue9v2AYBZIYBB+y0m5ntz28osg0RyfbxxboRSTgrYX8pW20L1vgNNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07512af77028961822c2d8c5c3bfd35708f327da815d7b31a17dd928b5f5dc34","last_reissued_at":"2026-05-27T01:06:15.609656Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:06:15.609656Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Energy-Based Models from Stochastic Interpolants using Spatiotemporal Differences","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Arto Klami, Hanlin Yu, Michael U. Gutmann, Omar Chehab, Partha Kaushik, RuiKang OuYang","submitted_at":"2026-05-26T11:07:02Z","abstract_excerpt":"Learning an energy-based model from data samples is a central problem in machine learning. Many recent and popular methods, such as denoising score matching for training energy-based diffusion models, use stochastic interpolants to corrupt data samples at different noise levels indexed by a time variable. This defines a joint density over both the data space and time, and most methods learn its energy through either spatial or temporal differences. We identify distinct failure modes for both of these approaches. To solve them, we propose Spatiotemporal Noise-Contrastive Estimation (stNCE), a f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26850","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.26850/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2605.26850","created_at":"2026-05-27T01:06:15.609783+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.26850v1","created_at":"2026-05-27T01:06:15.609783+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26850","created_at":"2026-05-27T01:06:15.609783+00:00"},{"alias_kind":"pith_short_12","alias_value":"A5ISV53QFCLB","created_at":"2026-05-27T01:06:15.609783+00:00"},{"alias_kind":"pith_short_16","alias_value":"A5ISV53QFCLBQIWC","created_at":"2026-05-27T01:06:15.609783+00:00"},{"alias_kind":"pith_short_8","alias_value":"A5ISV53Q","created_at":"2026-05-27T01:06:15.609783+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A5ISV53QFCLBQIWC3DC4HP6TK4","json":"https://pith.science/pith/A5ISV53QFCLBQIWC3DC4HP6TK4.json","graph_json":"https://pith.science/api/pith-number/A5ISV53QFCLBQIWC3DC4HP6TK4/graph.json","events_json":"https://pith.science/api/pith-number/A5ISV53QFCLBQIWC3DC4HP6TK4/events.json","paper":"https://pith.science/paper/A5ISV53Q"},"agent_actions":{"view_html":"https://pith.science/pith/A5ISV53QFCLBQIWC3DC4HP6TK4","download_json":"https://pith.science/pith/A5ISV53QFCLBQIWC3DC4HP6TK4.json","view_paper":"https://pith.science/paper/A5ISV53Q","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.26850&json=true","fetch_graph":"https://pith.science/api/pith-number/A5ISV53QFCLBQIWC3DC4HP6TK4/graph.json","fetch_events":"https://pith.science/api/pith-number/A5ISV53QFCLBQIWC3DC4HP6TK4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A5ISV53QFCLBQIWC3DC4HP6TK4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A5ISV53QFCLBQIWC3DC4HP6TK4/action/storage_attestation","attest_author":"https://pith.science/pith/A5ISV53QFCLBQIWC3DC4HP6TK4/action/author_attestation","sign_citation":"https://pith.science/pith/A5ISV53QFCLBQIWC3DC4HP6TK4/action/citation_signature","submit_replication":"https://pith.science/pith/A5ISV53QFCLBQIWC3DC4HP6TK4/action/replication_record"}},"created_at":"2026-05-27T01:06:15.609783+00:00","updated_at":"2026-05-27T01:06:15.609783+00:00"}