{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MB3WCQDYBJLVPULOPBCYNZPHGK","short_pith_number":"pith:MB3WCQDY","schema_version":"1.0","canonical_sha256":"60776140780a5757d16e784586e5e732bcc56e0e36a4c6559beeb0b9272822b7","source":{"kind":"arxiv","id":"2601.21025","version":3},"attestation_state":"computed","paper":{"title":"A Diffusive Classification Loss for Learning Energy-based Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Louis Grenioux, RuiKang OuYang","submitted_at":"2026-01-28T20:37:53Z","abstract_excerpt":"Score-based generative models have recently achieved remarkable success. While they are usually parameterized by the score, an alternative way is to use a series of time-dependent energy-based models (EBMs), where the score is obtained from the negative input-gradient of the energy. Crucially, EBMs can be leveraged not only for generation, but also for tasks such as compositional sampling or building Boltzmann Generators via Monte Carlo methods. However, training EBMs remains challenging. Direct maximum likelihood is computationally prohibitive due to the need for nested sampling, while score "},"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":"2601.21025","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2026-01-28T20:37:53Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"be98b00d15391e4b6ded5e7a5f8b2fb84a30b4b780cd75ae2c3c46c446e7e001","abstract_canon_sha256":"bae822f65d371c73f4c997b21375bb90f3eea2f2a26d069246a2d1a161b97d41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:17.376686Z","signature_b64":"gti6H73zIWUq+VtUa+W6ydwzxYOZVc2VzBaLM1P/8CJXZqFfRWTSzFX8Oj0YBEouiipGHJrnB3H5xgRO+qBrBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60776140780a5757d16e784586e5e732bcc56e0e36a4c6559beeb0b9272822b7","last_reissued_at":"2026-05-22T01:03:17.375862Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:17.375862Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Diffusive Classification Loss for Learning Energy-based Generative Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jos\\'e Miguel Hern\\'andez-Lobato, Louis Grenioux, RuiKang OuYang","submitted_at":"2026-01-28T20:37:53Z","abstract_excerpt":"Score-based generative models have recently achieved remarkable success. While they are usually parameterized by the score, an alternative way is to use a series of time-dependent energy-based models (EBMs), where the score is obtained from the negative input-gradient of the energy. Crucially, EBMs can be leveraged not only for generation, but also for tasks such as compositional sampling or building Boltzmann Generators via Monte Carlo methods. However, training EBMs remains challenging. Direct maximum likelihood is computationally prohibitive due to the need for nested sampling, while score "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.21025","kind":"arxiv","version":3},"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/2601.21025/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":"2601.21025","created_at":"2026-05-22T01:03:17.375998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.21025v3","created_at":"2026-05-22T01:03:17.375998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.21025","created_at":"2026-05-22T01:03:17.375998+00:00"},{"alias_kind":"pith_short_12","alias_value":"MB3WCQDYBJLV","created_at":"2026-05-22T01:03:17.375998+00:00"},{"alias_kind":"pith_short_16","alias_value":"MB3WCQDYBJLVPULO","created_at":"2026-05-22T01:03:17.375998+00:00"},{"alias_kind":"pith_short_8","alias_value":"MB3WCQDY","created_at":"2026-05-22T01:03:17.375998+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/MB3WCQDYBJLVPULOPBCYNZPHGK","json":"https://pith.science/pith/MB3WCQDYBJLVPULOPBCYNZPHGK.json","graph_json":"https://pith.science/api/pith-number/MB3WCQDYBJLVPULOPBCYNZPHGK/graph.json","events_json":"https://pith.science/api/pith-number/MB3WCQDYBJLVPULOPBCYNZPHGK/events.json","paper":"https://pith.science/paper/MB3WCQDY"},"agent_actions":{"view_html":"https://pith.science/pith/MB3WCQDYBJLVPULOPBCYNZPHGK","download_json":"https://pith.science/pith/MB3WCQDYBJLVPULOPBCYNZPHGK.json","view_paper":"https://pith.science/paper/MB3WCQDY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.21025&json=true","fetch_graph":"https://pith.science/api/pith-number/MB3WCQDYBJLVPULOPBCYNZPHGK/graph.json","fetch_events":"https://pith.science/api/pith-number/MB3WCQDYBJLVPULOPBCYNZPHGK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MB3WCQDYBJLVPULOPBCYNZPHGK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MB3WCQDYBJLVPULOPBCYNZPHGK/action/storage_attestation","attest_author":"https://pith.science/pith/MB3WCQDYBJLVPULOPBCYNZPHGK/action/author_attestation","sign_citation":"https://pith.science/pith/MB3WCQDYBJLVPULOPBCYNZPHGK/action/citation_signature","submit_replication":"https://pith.science/pith/MB3WCQDYBJLVPULOPBCYNZPHGK/action/replication_record"}},"created_at":"2026-05-22T01:03:17.375998+00:00","updated_at":"2026-05-22T01:03:17.375998+00:00"}