{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:SV2VYTKFXDOOHVFMOINL3YYFQI","short_pith_number":"pith:SV2VYTKF","schema_version":"1.0","canonical_sha256":"95755c4d45b8dce3d4ac721abde3058208db0db18e5017ad96cce2769affeb0e","source":{"kind":"arxiv","id":"2305.17010","version":3},"attestation_state":"computed","paper":{"title":"Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Dinghuai Zhang, Hanjun Dai, Ling Pan, Nikolay Malkin, Yoshua Bengio","submitted_at":"2023-05-26T15:13:09Z","abstract_excerpt":"Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning methods. The highly structured constraints in these problems can hinder either optimization or sampling directly in the solution space. On the other hand, GFlowNets have recently emerged as a powerful machinery to efficiently sample from composite unnormalized densities sequentially and have the potential to amortize such solution-searching processes in CO, as well as generate diverse solution candidates. In this paper, we design Markov "},"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":"2305.17010","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-05-26T15:13:09Z","cross_cats_sorted":["cs.AI","cs.DM","stat.ML"],"title_canon_sha256":"4a94abac72fbaa8a406c3b8a9031a8ca287c145ee978ccd7b20067b3307e05f1","abstract_canon_sha256":"0a8fb6bc4ed1fbde73d292acf6f3802fcd68f8f07ba7cef7572569fe084e4fd9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:14:12.751327Z","signature_b64":"7eYacdrTwsQVqGx2be0TBeZT5CXEjJ1WQd5UDG7o99Yt4JhUqxEZPi/iiVbr+KEVJOdnF3sdlD2wOcWeSVaoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95755c4d45b8dce3d4ac721abde3058208db0db18e5017ad96cce2769affeb0e","last_reissued_at":"2026-07-05T07:14:12.750815Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:14:12.750815Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Let the Flows Tell: Solving Graph Combinatorial Optimization Problems with GFlowNets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DM","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Dinghuai Zhang, Hanjun Dai, Ling Pan, Nikolay Malkin, Yoshua Bengio","submitted_at":"2023-05-26T15:13:09Z","abstract_excerpt":"Combinatorial optimization (CO) problems are often NP-hard and thus out of reach for exact algorithms, making them a tempting domain to apply machine learning methods. The highly structured constraints in these problems can hinder either optimization or sampling directly in the solution space. On the other hand, GFlowNets have recently emerged as a powerful machinery to efficiently sample from composite unnormalized densities sequentially and have the potential to amortize such solution-searching processes in CO, as well as generate diverse solution candidates. In this paper, we design Markov "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.17010","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/2305.17010/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":"2305.17010","created_at":"2026-07-05T07:14:12.750882+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.17010v3","created_at":"2026-07-05T07:14:12.750882+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.17010","created_at":"2026-07-05T07:14:12.750882+00:00"},{"alias_kind":"pith_short_12","alias_value":"SV2VYTKFXDOO","created_at":"2026-07-05T07:14:12.750882+00:00"},{"alias_kind":"pith_short_16","alias_value":"SV2VYTKFXDOOHVFM","created_at":"2026-07-05T07:14:12.750882+00:00"},{"alias_kind":"pith_short_8","alias_value":"SV2VYTKF","created_at":"2026-07-05T07:14:12.750882+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.28886","citing_title":"Differentiable Approximations for Distance Queries","ref_index":58,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SV2VYTKFXDOOHVFMOINL3YYFQI","json":"https://pith.science/pith/SV2VYTKFXDOOHVFMOINL3YYFQI.json","graph_json":"https://pith.science/api/pith-number/SV2VYTKFXDOOHVFMOINL3YYFQI/graph.json","events_json":"https://pith.science/api/pith-number/SV2VYTKFXDOOHVFMOINL3YYFQI/events.json","paper":"https://pith.science/paper/SV2VYTKF"},"agent_actions":{"view_html":"https://pith.science/pith/SV2VYTKFXDOOHVFMOINL3YYFQI","download_json":"https://pith.science/pith/SV2VYTKFXDOOHVFMOINL3YYFQI.json","view_paper":"https://pith.science/paper/SV2VYTKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.17010&json=true","fetch_graph":"https://pith.science/api/pith-number/SV2VYTKFXDOOHVFMOINL3YYFQI/graph.json","fetch_events":"https://pith.science/api/pith-number/SV2VYTKFXDOOHVFMOINL3YYFQI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SV2VYTKFXDOOHVFMOINL3YYFQI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SV2VYTKFXDOOHVFMOINL3YYFQI/action/storage_attestation","attest_author":"https://pith.science/pith/SV2VYTKFXDOOHVFMOINL3YYFQI/action/author_attestation","sign_citation":"https://pith.science/pith/SV2VYTKFXDOOHVFMOINL3YYFQI/action/citation_signature","submit_replication":"https://pith.science/pith/SV2VYTKFXDOOHVFMOINL3YYFQI/action/replication_record"}},"created_at":"2026-07-05T07:14:12.750882+00:00","updated_at":"2026-07-05T07:14:12.750882+00:00"}