{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IRHOU7PLWNS7O3V74IIQRQCHIN","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"5ee4feb36ac3fc8b9cbcef629fdcc2760f7f40702e7533cea804802e45082256","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T11:33:13Z","title_canon_sha256":"8af13bfa8922235a9c9af133425c45469f40de48255bee84aaae5974a90df92e"},"schema_version":"1.0","source":{"id":"2410.01432","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.01432","created_at":"2026-07-05T10:48:19Z"},{"alias_kind":"arxiv_version","alias_value":"2410.01432v2","created_at":"2026-07-05T10:48:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.01432","created_at":"2026-07-05T10:48:19Z"},{"alias_kind":"pith_short_12","alias_value":"IRHOU7PLWNS7","created_at":"2026-07-05T10:48:19Z"},{"alias_kind":"pith_short_16","alias_value":"IRHOU7PLWNS7O3V7","created_at":"2026-07-05T10:48:19Z"},{"alias_kind":"pith_short_8","alias_value":"IRHOU7PL","created_at":"2026-07-05T10:48:19Z"}],"graph_snapshots":[{"event_id":"sha256:3ba102e28e0f9a95def10762153828bd32aea44822e75b9bb4d765af8b47624f","target":"graph","created_at":"2026-07-05T10:48:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.01432/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Amortized inference is the task of training a parametric model, such as a neural network, to approximate a distribution with a given unnormalized density where exact sampling is intractable. When sampling is implemented as a sequential decision-making process, reinforcement learning (RL) methods, such as generative flow networks, can be used to train the sampling policy. Off-policy RL training facilitates the discovery of diverse, high-reward candidates, but existing methods still face challenges in efficient exploration. We propose to use an adaptive training distribution (the \\teacher) to gu","authors_text":"Emmanuel Bengio, Jarrid Rector-Brooks, Jinkyoo Park, Leo Feng, Minsu Kim, Nikolay Malkin, Sanghyeok Choi, Sungsoo Ahn, Taeyoung Yun, Yoshua Bengio","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T11:33:13Z","title":"Adaptive teachers for amortized samplers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.01432","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0f5d33543611b38fc84d134e7b28df1a9c139f34383abc02bd6f6327ce500117","target":"record","created_at":"2026-07-05T10:48:19Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"5ee4feb36ac3fc8b9cbcef629fdcc2760f7f40702e7533cea804802e45082256","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-02T11:33:13Z","title_canon_sha256":"8af13bfa8922235a9c9af133425c45469f40de48255bee84aaae5974a90df92e"},"schema_version":"1.0","source":{"id":"2410.01432","kind":"arxiv","version":2}},"canonical_sha256":"444eea7debb365f76ebfe21108c047437bcf5c875c5347c16f051282671f3290","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"444eea7debb365f76ebfe21108c047437bcf5c875c5347c16f051282671f3290","first_computed_at":"2026-07-05T10:48:19.775472Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:48:19.775472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gYiE5LB6Bj87npZyW2kiV30fZPJa1CRvR885LWk5/KLIl5ILmNLuOiDcEEZfvhrCfJ6RHpW51w5rWqYGpEYIAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:48:19.776012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.01432","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f5d33543611b38fc84d134e7b28df1a9c139f34383abc02bd6f6327ce500117","sha256:3ba102e28e0f9a95def10762153828bd32aea44822e75b9bb4d765af8b47624f"],"state_sha256":"b51d6d22ad19d5352fd78a9871c94d77f105bf50afc68283702728ab1609db3a"}