{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:R2NQGIKKKEJNLE2KCTCCIOWTY6","short_pith_number":"pith:R2NQGIKK","schema_version":"1.0","canonical_sha256":"8e9b03214a5112d5934a14c4243ad3c7827a072463b06c3629d45b9d66d1f191","source":{"kind":"arxiv","id":"2210.03308","version":1},"attestation_state":"computed","paper":{"title":"Generative Augmented Flow Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Dinghuai Zhang, Ling Pan, Longbo Huang, Yoshua Bengio","submitted_at":"2022-10-07T03:33:56Z","abstract_excerpt":"The Generative Flow Network is a probabilistic framework where an agent learns a stochastic policy for object generation, such that the probability of generating an object is proportional to a given reward function. Its effectiveness has been shown in discovering high-quality and diverse solutions, compared to reward-maximizing reinforcement learning-based methods. Nonetheless, GFlowNets only learn from rewards of the terminal states, which can limit its applicability. Indeed, intermediate rewards play a critical role in learning, for example from intrinsic motivation to provide intermediate f"},"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":"2210.03308","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-10-07T03:33:56Z","cross_cats_sorted":[],"title_canon_sha256":"438d5bd69f14bcd1898ff9e71c0c06bfb590ad3fe01c063e0cd9ccb1f217647e","abstract_canon_sha256":"cd2a870eb03194055944f24cb4b04f63139f7538e13207091a671d6ee182d2ab"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:18.585414Z","signature_b64":"T6VpzHvLoCbSFd0WCrnUEpdCE0C8WREM7SLJk/UCwvZlejwWTWBpth530qmh/RAyapJgp/pvrjN/NZI2ltgXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e9b03214a5112d5934a14c4243ad3c7827a072463b06c3629d45b9d66d1f191","last_reissued_at":"2026-07-05T05:04:18.584980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:18.584980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Generative Augmented Flow Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Dinghuai Zhang, Ling Pan, Longbo Huang, Yoshua Bengio","submitted_at":"2022-10-07T03:33:56Z","abstract_excerpt":"The Generative Flow Network is a probabilistic framework where an agent learns a stochastic policy for object generation, such that the probability of generating an object is proportional to a given reward function. Its effectiveness has been shown in discovering high-quality and diverse solutions, compared to reward-maximizing reinforcement learning-based methods. Nonetheless, GFlowNets only learn from rewards of the terminal states, which can limit its applicability. Indeed, intermediate rewards play a critical role in learning, for example from intrinsic motivation to provide intermediate f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.03308","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/2210.03308/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":"2210.03308","created_at":"2026-07-05T05:04:18.585034+00:00"},{"alias_kind":"arxiv_version","alias_value":"2210.03308v1","created_at":"2026-07-05T05:04:18.585034+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.03308","created_at":"2026-07-05T05:04:18.585034+00:00"},{"alias_kind":"pith_short_12","alias_value":"R2NQGIKKKEJN","created_at":"2026-07-05T05:04:18.585034+00:00"},{"alias_kind":"pith_short_16","alias_value":"R2NQGIKKKEJNLE2K","created_at":"2026-07-05T05:04:18.585034+00:00"},{"alias_kind":"pith_short_8","alias_value":"R2NQGIKK","created_at":"2026-07-05T05:04:18.585034+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.20110","citing_title":"Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training","ref_index":56,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/R2NQGIKKKEJNLE2KCTCCIOWTY6","json":"https://pith.science/pith/R2NQGIKKKEJNLE2KCTCCIOWTY6.json","graph_json":"https://pith.science/api/pith-number/R2NQGIKKKEJNLE2KCTCCIOWTY6/graph.json","events_json":"https://pith.science/api/pith-number/R2NQGIKKKEJNLE2KCTCCIOWTY6/events.json","paper":"https://pith.science/paper/R2NQGIKK"},"agent_actions":{"view_html":"https://pith.science/pith/R2NQGIKKKEJNLE2KCTCCIOWTY6","download_json":"https://pith.science/pith/R2NQGIKKKEJNLE2KCTCCIOWTY6.json","view_paper":"https://pith.science/paper/R2NQGIKK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2210.03308&json=true","fetch_graph":"https://pith.science/api/pith-number/R2NQGIKKKEJNLE2KCTCCIOWTY6/graph.json","fetch_events":"https://pith.science/api/pith-number/R2NQGIKKKEJNLE2KCTCCIOWTY6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R2NQGIKKKEJNLE2KCTCCIOWTY6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R2NQGIKKKEJNLE2KCTCCIOWTY6/action/storage_attestation","attest_author":"https://pith.science/pith/R2NQGIKKKEJNLE2KCTCCIOWTY6/action/author_attestation","sign_citation":"https://pith.science/pith/R2NQGIKKKEJNLE2KCTCCIOWTY6/action/citation_signature","submit_replication":"https://pith.science/pith/R2NQGIKKKEJNLE2KCTCCIOWTY6/action/replication_record"}},"created_at":"2026-07-05T05:04:18.585034+00:00","updated_at":"2026-07-05T05:04:18.585034+00:00"}