{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FGBITTFC52BOQ5YMS7BVPPKK65","short_pith_number":"pith:FGBITTFC","schema_version":"1.0","canonical_sha256":"298289cca2ee82e8770c97c357bd4af7742a3959f0736bcf09e5377f9e2afa84","source":{"kind":"arxiv","id":"2509.00316","version":1},"attestation_state":"computed","paper":{"title":"Continuously Tempered Diffusion Samplers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bowen Jing, Ezra Erives, Peter Holderrieth, Tommi Jaakkola","submitted_at":"2025-08-30T02:24:52Z","abstract_excerpt":"Annealing-based neural samplers seek to amortize sampling from unnormalized distributions by training neural networks to transport a family of densities interpolating from source to target. A crucial design choice in the training phase of such samplers is the proposal distribution by which locations are generated at which to evaluate the loss. Previous work has obtained such a proposal distribution by combining a partially learned transport with annealed Langevin dynamics. However, isolated modes and other pathological properties of the annealing path imply that such proposals achieve insuffic"},"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":"2509.00316","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-08-30T02:24:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"030303b2257dea439fcc54cda118479a07a0c70bb6cd651a666fef999eb2de77","abstract_canon_sha256":"8ed4eac3b231303eed16767dc451f02505c175149cd86d50ea81ec55676f773a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:13.578796Z","signature_b64":"2y+sHG31hX/HG39d1YLrWOyqmblNypD+1L/jVKEhNxxsPCH2RE9tnBuSTIze0sWqKxfAVLCBaw7hjP2rJ/32CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"298289cca2ee82e8770c97c357bd4af7742a3959f0736bcf09e5377f9e2afa84","last_reissued_at":"2026-07-05T12:02:13.578232Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:13.578232Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Continuously Tempered Diffusion Samplers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Bowen Jing, Ezra Erives, Peter Holderrieth, Tommi Jaakkola","submitted_at":"2025-08-30T02:24:52Z","abstract_excerpt":"Annealing-based neural samplers seek to amortize sampling from unnormalized distributions by training neural networks to transport a family of densities interpolating from source to target. A crucial design choice in the training phase of such samplers is the proposal distribution by which locations are generated at which to evaluate the loss. Previous work has obtained such a proposal distribution by combining a partially learned transport with annealed Langevin dynamics. However, isolated modes and other pathological properties of the annealing path imply that such proposals achieve insuffic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00316","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/2509.00316/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":"2509.00316","created_at":"2026-07-05T12:02:13.578297+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.00316v1","created_at":"2026-07-05T12:02:13.578297+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00316","created_at":"2026-07-05T12:02:13.578297+00:00"},{"alias_kind":"pith_short_12","alias_value":"FGBITTFC52BO","created_at":"2026-07-05T12:02:13.578297+00:00"},{"alias_kind":"pith_short_16","alias_value":"FGBITTFC52BOQ5YM","created_at":"2026-07-05T12:02:13.578297+00:00"},{"alias_kind":"pith_short_8","alias_value":"FGBITTFC","created_at":"2026-07-05T12:02:13.578297+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/FGBITTFC52BOQ5YMS7BVPPKK65","json":"https://pith.science/pith/FGBITTFC52BOQ5YMS7BVPPKK65.json","graph_json":"https://pith.science/api/pith-number/FGBITTFC52BOQ5YMS7BVPPKK65/graph.json","events_json":"https://pith.science/api/pith-number/FGBITTFC52BOQ5YMS7BVPPKK65/events.json","paper":"https://pith.science/paper/FGBITTFC"},"agent_actions":{"view_html":"https://pith.science/pith/FGBITTFC52BOQ5YMS7BVPPKK65","download_json":"https://pith.science/pith/FGBITTFC52BOQ5YMS7BVPPKK65.json","view_paper":"https://pith.science/paper/FGBITTFC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.00316&json=true","fetch_graph":"https://pith.science/api/pith-number/FGBITTFC52BOQ5YMS7BVPPKK65/graph.json","fetch_events":"https://pith.science/api/pith-number/FGBITTFC52BOQ5YMS7BVPPKK65/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FGBITTFC52BOQ5YMS7BVPPKK65/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FGBITTFC52BOQ5YMS7BVPPKK65/action/storage_attestation","attest_author":"https://pith.science/pith/FGBITTFC52BOQ5YMS7BVPPKK65/action/author_attestation","sign_citation":"https://pith.science/pith/FGBITTFC52BOQ5YMS7BVPPKK65/action/citation_signature","submit_replication":"https://pith.science/pith/FGBITTFC52BOQ5YMS7BVPPKK65/action/replication_record"}},"created_at":"2026-07-05T12:02:13.578297+00:00","updated_at":"2026-07-05T12:02:13.578297+00:00"}