{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HECEU52GORIBV2CHZJLUAK64UQ","short_pith_number":"pith:HECEU52G","schema_version":"1.0","canonical_sha256":"39044a774674501ae847ca57402bdca4358ce6d2cf9471d550b0383b5ac26654","source":{"kind":"arxiv","id":"2511.05924","version":3},"attestation_state":"computed","paper":{"title":"DiScoFormer: Plug-In Density and Score Estimation with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Peter Sushko, Ranjay Krishna, Vasily Ilin","submitted_at":"2025-11-08T08:38:37Z","abstract_excerpt":"Estimating probability density and its score from samples remains a core problem in generative modeling, Bayesian inference, and kinetic theory. Existing methods are bifurcated: classical kernel density estimators (KDE) generalize across distributions but suffer from the curse of dimensionality, while modern neural score models achieve high precision but require retraining for every target distribution. We introduce DiScoFormer (Density and Score Transformer), a ``train-once, infer-anywhere\" equivariant Transformer that maps i.i.d. samples to both density values and score vectors, generalizing"},"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":"2511.05924","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-11-08T08:38:37Z","cross_cats_sorted":[],"title_canon_sha256":"2a00c08b55c43e36af5cfa5609821c112dc1f4d2fc44b9a8b51ed51c5a132398","abstract_canon_sha256":"f81efa60c67a8980cfe416a0d2fac875bae9e3f89360175794f483005c9a1c49"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:57.967245Z","signature_b64":"OXyCLRaehAMF5hG/CDIT90vTYLALkHeQ/1xCJ2pMNxWWsdeVVO2QtS+sG9uGjD6SrHzIAdfpq1zAjvduXgh3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"39044a774674501ae847ca57402bdca4358ce6d2cf9471d550b0383b5ac26654","last_reissued_at":"2026-05-29T01:04:57.966400Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:57.966400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiScoFormer: Plug-In Density and Score Estimation with Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Peter Sushko, Ranjay Krishna, Vasily Ilin","submitted_at":"2025-11-08T08:38:37Z","abstract_excerpt":"Estimating probability density and its score from samples remains a core problem in generative modeling, Bayesian inference, and kinetic theory. Existing methods are bifurcated: classical kernel density estimators (KDE) generalize across distributions but suffer from the curse of dimensionality, while modern neural score models achieve high precision but require retraining for every target distribution. We introduce DiScoFormer (Density and Score Transformer), a ``train-once, infer-anywhere\" equivariant Transformer that maps i.i.d. samples to both density values and score vectors, generalizing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.05924","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/2511.05924/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":"2511.05924","created_at":"2026-05-29T01:04:57.966506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.05924v3","created_at":"2026-05-29T01:04:57.966506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.05924","created_at":"2026-05-29T01:04:57.966506+00:00"},{"alias_kind":"pith_short_12","alias_value":"HECEU52GORIB","created_at":"2026-05-29T01:04:57.966506+00:00"},{"alias_kind":"pith_short_16","alias_value":"HECEU52GORIBV2CH","created_at":"2026-05-29T01:04:57.966506+00:00"},{"alias_kind":"pith_short_8","alias_value":"HECEU52G","created_at":"2026-05-29T01:04:57.966506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.13386","citing_title":"Support-Conditioned Flow Matching Is Kernel Smoothing","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HECEU52GORIBV2CHZJLUAK64UQ","json":"https://pith.science/pith/HECEU52GORIBV2CHZJLUAK64UQ.json","graph_json":"https://pith.science/api/pith-number/HECEU52GORIBV2CHZJLUAK64UQ/graph.json","events_json":"https://pith.science/api/pith-number/HECEU52GORIBV2CHZJLUAK64UQ/events.json","paper":"https://pith.science/paper/HECEU52G"},"agent_actions":{"view_html":"https://pith.science/pith/HECEU52GORIBV2CHZJLUAK64UQ","download_json":"https://pith.science/pith/HECEU52GORIBV2CHZJLUAK64UQ.json","view_paper":"https://pith.science/paper/HECEU52G","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.05924&json=true","fetch_graph":"https://pith.science/api/pith-number/HECEU52GORIBV2CHZJLUAK64UQ/graph.json","fetch_events":"https://pith.science/api/pith-number/HECEU52GORIBV2CHZJLUAK64UQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HECEU52GORIBV2CHZJLUAK64UQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HECEU52GORIBV2CHZJLUAK64UQ/action/storage_attestation","attest_author":"https://pith.science/pith/HECEU52GORIBV2CHZJLUAK64UQ/action/author_attestation","sign_citation":"https://pith.science/pith/HECEU52GORIBV2CHZJLUAK64UQ/action/citation_signature","submit_replication":"https://pith.science/pith/HECEU52GORIBV2CHZJLUAK64UQ/action/replication_record"}},"created_at":"2026-05-29T01:04:57.966506+00:00","updated_at":"2026-05-29T01:04:57.966506+00:00"}