{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:RQ6UPSVBCLUVQYOJXL5EB2AECY","short_pith_number":"pith:RQ6UPSVB","schema_version":"1.0","canonical_sha256":"8c3d47caa112e95861c9bafa40e80416298e2eadfecbe8f9f086dba39e0e35be","source":{"kind":"arxiv","id":"2310.02823","version":3},"attestation_state":"computed","paper":{"title":"Learning to Scale Logits for Temperature-Conditional GFlowNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dinghuai Zhang, Emmanuel Bengio, Jinkyoo Park, Joohwan Ko, Ling Pan, Minsu Kim, Taeyoung Yun, Woochang Kim, Yoshua Bengio","submitted_at":"2023-10-04T13:45:56Z","abstract_excerpt":"GFlowNets are probabilistic models that sequentially generate compositional structures through a stochastic policy. Among GFlowNets, temperature-conditional GFlowNets can introduce temperature-based controllability for exploration and exploitation. We propose \\textit{Logit-scaling GFlowNets} (Logit-GFN), a novel architectural design that greatly accelerates the training of temperature-conditional GFlowNets. It is based on the idea that previously proposed approaches introduced numerical challenges in the deep network training, since different temperatures may give rise to very different gradie"},"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":"2310.02823","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T13:45:56Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"a7f923e41d8637635c9b60368e5abc15f5701f17205aca6c6cef2955b8d2b07e","abstract_canon_sha256":"b8c14f207f346ed6b717414d7d549600355861c72753a582ca22d600eaf214a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:14.140243Z","signature_b64":"8PigypibyA6durDl5VO++rqMQC2YtUEYyFP3B/u56zAFyNaABdKa0bWquHeAAtzhoy+wFB7YuwQHA6cOCeu8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c3d47caa112e95861c9bafa40e80416298e2eadfecbe8f9f086dba39e0e35be","last_reissued_at":"2026-07-05T08:26:14.139808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:14.139808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Scale Logits for Temperature-Conditional GFlowNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Dinghuai Zhang, Emmanuel Bengio, Jinkyoo Park, Joohwan Ko, Ling Pan, Minsu Kim, Taeyoung Yun, Woochang Kim, Yoshua Bengio","submitted_at":"2023-10-04T13:45:56Z","abstract_excerpt":"GFlowNets are probabilistic models that sequentially generate compositional structures through a stochastic policy. Among GFlowNets, temperature-conditional GFlowNets can introduce temperature-based controllability for exploration and exploitation. We propose \\textit{Logit-scaling GFlowNets} (Logit-GFN), a novel architectural design that greatly accelerates the training of temperature-conditional GFlowNets. It is based on the idea that previously proposed approaches introduced numerical challenges in the deep network training, since different temperatures may give rise to very different gradie"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02823","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/2310.02823/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":"2310.02823","created_at":"2026-07-05T08:26:14.139864+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.02823v3","created_at":"2026-07-05T08:26:14.139864+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02823","created_at":"2026-07-05T08:26:14.139864+00:00"},{"alias_kind":"pith_short_12","alias_value":"RQ6UPSVBCLUV","created_at":"2026-07-05T08:26:14.139864+00:00"},{"alias_kind":"pith_short_16","alias_value":"RQ6UPSVBCLUVQYOJ","created_at":"2026-07-05T08:26:14.139864+00:00"},{"alias_kind":"pith_short_8","alias_value":"RQ6UPSVB","created_at":"2026-07-05T08:26:14.139864+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05314","citing_title":"Machine learning for sample-based quantum diagonalization: generative configuration recovery and the classical-simulability frontier","ref_index":70,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RQ6UPSVBCLUVQYOJXL5EB2AECY","json":"https://pith.science/pith/RQ6UPSVBCLUVQYOJXL5EB2AECY.json","graph_json":"https://pith.science/api/pith-number/RQ6UPSVBCLUVQYOJXL5EB2AECY/graph.json","events_json":"https://pith.science/api/pith-number/RQ6UPSVBCLUVQYOJXL5EB2AECY/events.json","paper":"https://pith.science/paper/RQ6UPSVB"},"agent_actions":{"view_html":"https://pith.science/pith/RQ6UPSVBCLUVQYOJXL5EB2AECY","download_json":"https://pith.science/pith/RQ6UPSVBCLUVQYOJXL5EB2AECY.json","view_paper":"https://pith.science/paper/RQ6UPSVB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.02823&json=true","fetch_graph":"https://pith.science/api/pith-number/RQ6UPSVBCLUVQYOJXL5EB2AECY/graph.json","fetch_events":"https://pith.science/api/pith-number/RQ6UPSVBCLUVQYOJXL5EB2AECY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RQ6UPSVBCLUVQYOJXL5EB2AECY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RQ6UPSVBCLUVQYOJXL5EB2AECY/action/storage_attestation","attest_author":"https://pith.science/pith/RQ6UPSVBCLUVQYOJXL5EB2AECY/action/author_attestation","sign_citation":"https://pith.science/pith/RQ6UPSVBCLUVQYOJXL5EB2AECY/action/citation_signature","submit_replication":"https://pith.science/pith/RQ6UPSVBCLUVQYOJXL5EB2AECY/action/replication_record"}},"created_at":"2026-07-05T08:26:14.139864+00:00","updated_at":"2026-07-05T08:26:14.139864+00:00"}