{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:VTEBSE6P2QOHIYUMVO5WQK73SH","short_pith_number":"pith:VTEBSE6P","canonical_record":{"source":{"id":"2310.02679","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T09:39:05Z","cross_cats_sorted":["cs.AI","stat.CO","stat.ME","stat.ML"],"title_canon_sha256":"35ecc48de644dc9accc3e7744637059690892c3349c40569eecab62aa723ec45","abstract_canon_sha256":"e3526a6204b556e4e0623b94bf531b69b965c4adade16f4e55e1f74afc0a9ca4"},"schema_version":"1.0"},"canonical_sha256":"acc81913cfd41c74628cabbb682bfb91cbfbc8a3c2d9addcca4e5601b0335a29","source":{"kind":"arxiv","id":"2310.02679","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02679","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02679v3","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02679","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"VTEBSE6P2QOH","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"VTEBSE6P2QOHIYUM","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"VTEBSE6P","created_at":"2026-07-05T07:54:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:VTEBSE6P2QOHIYUMVO5WQK73SH","target":"record","payload":{"canonical_record":{"source":{"id":"2310.02679","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T09:39:05Z","cross_cats_sorted":["cs.AI","stat.CO","stat.ME","stat.ML"],"title_canon_sha256":"35ecc48de644dc9accc3e7744637059690892c3349c40569eecab62aa723ec45","abstract_canon_sha256":"e3526a6204b556e4e0623b94bf531b69b965c4adade16f4e55e1f74afc0a9ca4"},"schema_version":"1.0"},"canonical_sha256":"acc81913cfd41c74628cabbb682bfb91cbfbc8a3c2d9addcca4e5601b0335a29","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:54:04.427112Z","signature_b64":"ZsbPmVwUlwWGNPwnsUrSg4D/K5+RDiLzKbdVH0WqYKGAoUmewTGRpQb9umA9WkkauzoPC/UBS9XhsSPqjz0+DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acc81913cfd41c74628cabbb682bfb91cbfbc8a3c2d9addcca4e5601b0335a29","last_reissued_at":"2026-07-05T07:54:04.426592Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:54:04.426592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.02679","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:54:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V2SPmSE8Hf+T00vWfjRZTMdW4GjGi+0xnJ9etQHLeRAOnkHXQs7eL6jqxGP15DUJ+eZCXwLRqDXKBF/CMAsyBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T04:21:33.963569Z"},"content_sha256":"62d7ebb40561db9f9c85604dedd38b519ad7fc3486c8b3893613ce7339c46643","schema_version":"1.0","event_id":"sha256:62d7ebb40561db9f9c85604dedd38b519ad7fc3486c8b3893613ce7339c46643"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:VTEBSE6P2QOHIYUMVO5WQK73SH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.CO","stat.ME","stat.ML"],"primary_cat":"cs.LG","authors_text":"Aaron Courville, Cheng-Hao Liu, Dinghuai Zhang, Ricky T. Q. Chen, Yoshua Bengio","submitted_at":"2023-10-04T09:39:05Z","abstract_excerpt":"We tackle the problem of sampling from intractable high-dimensional density functions, a fundamental task that often appears in machine learning and statistics. We extend recent sampling-based approaches that leverage controlled stochastic processes to model approximate samples from these target densities. The main drawback of these approaches is that the training objective requires full trajectories to compute, resulting in sluggish credit assignment issues due to use of entire trajectories and a learning signal present only at the terminal time. In this work, we present Diffusion Generative "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02679","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/2310.02679/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:54:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mDBH9Ufa3gLN3rTh3CNQgr0ygpItpqx3/v1I9NxAhAE/bkR6l03omB3+J0uca7mejQBoVrE+W0kgaQRAr/+ZDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T04:21:33.963976Z"},"content_sha256":"fff318709735ab58dace9ee6beb5dffc1be5e1ce1e8701a7ba4f99b93730e9a2","schema_version":"1.0","event_id":"sha256:fff318709735ab58dace9ee6beb5dffc1be5e1ce1e8701a7ba4f99b93730e9a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VTEBSE6P2QOHIYUMVO5WQK73SH/bundle.json","state_url":"https://pith.science/pith/VTEBSE6P2QOHIYUMVO5WQK73SH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VTEBSE6P2QOHIYUMVO5WQK73SH/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T04:21:33Z","links":{"resolver":"https://pith.science/pith/VTEBSE6P2QOHIYUMVO5WQK73SH","bundle":"https://pith.science/pith/VTEBSE6P2QOHIYUMVO5WQK73SH/bundle.json","state":"https://pith.science/pith/VTEBSE6P2QOHIYUMVO5WQK73SH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VTEBSE6P2QOHIYUMVO5WQK73SH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:VTEBSE6P2QOHIYUMVO5WQK73SH","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":"e3526a6204b556e4e0623b94bf531b69b965c4adade16f4e55e1f74afc0a9ca4","cross_cats_sorted":["cs.AI","stat.CO","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T09:39:05Z","title_canon_sha256":"35ecc48de644dc9accc3e7744637059690892c3349c40569eecab62aa723ec45"},"schema_version":"1.0","source":{"id":"2310.02679","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.02679","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2310.02679v3","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.02679","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"VTEBSE6P2QOH","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"VTEBSE6P2QOHIYUM","created_at":"2026-07-05T07:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"VTEBSE6P","created_at":"2026-07-05T07:54:04Z"}],"graph_snapshots":[{"event_id":"sha256:fff318709735ab58dace9ee6beb5dffc1be5e1ce1e8701a7ba4f99b93730e9a2","target":"graph","created_at":"2026-07-05T07:54:04Z","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/2310.02679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We tackle the problem of sampling from intractable high-dimensional density functions, a fundamental task that often appears in machine learning and statistics. We extend recent sampling-based approaches that leverage controlled stochastic processes to model approximate samples from these target densities. The main drawback of these approaches is that the training objective requires full trajectories to compute, resulting in sluggish credit assignment issues due to use of entire trajectories and a learning signal present only at the terminal time. In this work, we present Diffusion Generative ","authors_text":"Aaron Courville, Cheng-Hao Liu, Dinghuai Zhang, Ricky T. Q. Chen, Yoshua Bengio","cross_cats":["cs.AI","stat.CO","stat.ME","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T09:39:05Z","title":"Diffusion Generative Flow Samplers: Improving learning signals through partial trajectory optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.02679","kind":"arxiv","version":3},"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":"sha256:62d7ebb40561db9f9c85604dedd38b519ad7fc3486c8b3893613ce7339c46643","target":"record","created_at":"2026-07-05T07:54:04Z","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":"e3526a6204b556e4e0623b94bf531b69b965c4adade16f4e55e1f74afc0a9ca4","cross_cats_sorted":["cs.AI","stat.CO","stat.ME","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-04T09:39:05Z","title_canon_sha256":"35ecc48de644dc9accc3e7744637059690892c3349c40569eecab62aa723ec45"},"schema_version":"1.0","source":{"id":"2310.02679","kind":"arxiv","version":3}},"canonical_sha256":"acc81913cfd41c74628cabbb682bfb91cbfbc8a3c2d9addcca4e5601b0335a29","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"acc81913cfd41c74628cabbb682bfb91cbfbc8a3c2d9addcca4e5601b0335a29","first_computed_at":"2026-07-05T07:54:04.426592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:54:04.426592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZsbPmVwUlwWGNPwnsUrSg4D/K5+RDiLzKbdVH0WqYKGAoUmewTGRpQb9umA9WkkauzoPC/UBS9XhsSPqjz0+DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:54:04.427112Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.02679","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62d7ebb40561db9f9c85604dedd38b519ad7fc3486c8b3893613ce7339c46643","sha256:fff318709735ab58dace9ee6beb5dffc1be5e1ce1e8701a7ba4f99b93730e9a2"],"state_sha256":"ae4a88dba7a566bfd99ae2b84433066ed5fb9b45ff1a75382f3a85a63f4359b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ngZcgMyyJKCTYNysm1RYTdTheqF6BCTMnC7+F7nF3zKNib/xARC/CCJOGKEv1DAD0Y944NR94J99ITy54K6PDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T04:21:33.966339Z","bundle_sha256":"48bcd9fd9fc5fd2f87c4b6d663ef4a293217423b77ebcf88c3aa169ab38897ef"}}