{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:47BTEXTSA7Q4YSGBFWD4SH2Y33","short_pith_number":"pith:47BTEXTS","schema_version":"1.0","canonical_sha256":"e7c3325e7207e1cc48c12d87c91f58deff8b3a97ef38c573d6a7a8c262b611f9","source":{"kind":"arxiv","id":"2310.03301","version":1},"attestation_state":"computed","paper":{"title":"Learning Energy Decompositions for Partial Inference of GFlowNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyosoon Jang, Minsu Kim, Sungsoo Ahn","submitted_at":"2023-10-05T04:02:36Z","abstract_excerpt":"This paper studies generative flow networks (GFlowNets) to sample objects from the Boltzmann energy distribution via a sequence of actions. In particular, we focus on improving GFlowNet with partial inference: training flow functions with the evaluation of the intermediate states or transitions. To this end, the recently developed forward-looking GFlowNet reparameterizes the flow functions based on evaluating the energy of intermediate states. However, such an evaluation of intermediate energies may (i) be too expensive or impossible to evaluate and (ii) even provide misleading training signal"},"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":"2310.03301","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-05T04:02:36Z","cross_cats_sorted":[],"title_canon_sha256":"1c99960de1825e2c255144c22dfa65703fe51b83b8e216791a2c4f44e5152271","abstract_canon_sha256":"2cf4ce0e30aa902c25b6642ca4044faea10adcbfbb2e9ceab6e4e7775f4fbc02"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:57:31.362517Z","signature_b64":"TQGokxP6ndQ7NRztIVIiuhF+ekNwjvkG6nfg4gDYu09PyEY4y1MFjSZxeTTzCr/E/GiMmS/kwWDfVVT/LroYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7c3325e7207e1cc48c12d87c91f58deff8b3a97ef38c573d6a7a8c262b611f9","last_reissued_at":"2026-07-05T06:57:31.361926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:57:31.361926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Energy Decompositions for Partial Inference of GFlowNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hyosoon Jang, Minsu Kim, Sungsoo Ahn","submitted_at":"2023-10-05T04:02:36Z","abstract_excerpt":"This paper studies generative flow networks (GFlowNets) to sample objects from the Boltzmann energy distribution via a sequence of actions. In particular, we focus on improving GFlowNet with partial inference: training flow functions with the evaluation of the intermediate states or transitions. To this end, the recently developed forward-looking GFlowNet reparameterizes the flow functions based on evaluating the energy of intermediate states. However, such an evaluation of intermediate energies may (i) be too expensive or impossible to evaluate and (ii) even provide misleading training signal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.03301","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/2310.03301/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":"2310.03301","created_at":"2026-07-05T06:57:31.361997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.03301v1","created_at":"2026-07-05T06:57:31.361997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.03301","created_at":"2026-07-05T06:57:31.361997+00:00"},{"alias_kind":"pith_short_12","alias_value":"47BTEXTSA7Q4","created_at":"2026-07-05T06:57:31.361997+00:00"},{"alias_kind":"pith_short_16","alias_value":"47BTEXTSA7Q4YSGB","created_at":"2026-07-05T06:57:31.361997+00:00"},{"alias_kind":"pith_short_8","alias_value":"47BTEXTS","created_at":"2026-07-05T06:57:31.361997+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":30,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/47BTEXTSA7Q4YSGBFWD4SH2Y33","json":"https://pith.science/pith/47BTEXTSA7Q4YSGBFWD4SH2Y33.json","graph_json":"https://pith.science/api/pith-number/47BTEXTSA7Q4YSGBFWD4SH2Y33/graph.json","events_json":"https://pith.science/api/pith-number/47BTEXTSA7Q4YSGBFWD4SH2Y33/events.json","paper":"https://pith.science/paper/47BTEXTS"},"agent_actions":{"view_html":"https://pith.science/pith/47BTEXTSA7Q4YSGBFWD4SH2Y33","download_json":"https://pith.science/pith/47BTEXTSA7Q4YSGBFWD4SH2Y33.json","view_paper":"https://pith.science/paper/47BTEXTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.03301&json=true","fetch_graph":"https://pith.science/api/pith-number/47BTEXTSA7Q4YSGBFWD4SH2Y33/graph.json","fetch_events":"https://pith.science/api/pith-number/47BTEXTSA7Q4YSGBFWD4SH2Y33/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/47BTEXTSA7Q4YSGBFWD4SH2Y33/action/timestamp_anchor","attest_storage":"https://pith.science/pith/47BTEXTSA7Q4YSGBFWD4SH2Y33/action/storage_attestation","attest_author":"https://pith.science/pith/47BTEXTSA7Q4YSGBFWD4SH2Y33/action/author_attestation","sign_citation":"https://pith.science/pith/47BTEXTSA7Q4YSGBFWD4SH2Y33/action/citation_signature","submit_replication":"https://pith.science/pith/47BTEXTSA7Q4YSGBFWD4SH2Y33/action/replication_record"}},"created_at":"2026-07-05T06:57:31.361997+00:00","updated_at":"2026-07-05T06:57:31.361997+00:00"}