{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GWNGNI4J27GTSXDCLD4KIA6F2N","short_pith_number":"pith:GWNGNI4J","canonical_record":{"source":{"id":"2410.02596","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T15:37:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9f80b5ad31c824b25a3c9bdd49534a62d7325c8e1648094cce8ad956b3b4e64","abstract_canon_sha256":"6d2320a3c06a4f63dd64d09fe7d6954bd04a04770bc24c243a5565a1b2231696"},"schema_version":"1.0"},"canonical_sha256":"359a66a389d7cd395c6258f8a403c5d36dc0d52f0783a2535d66aefdc46fbcea","source":{"kind":"arxiv","id":"2410.02596","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02596","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02596v1","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02596","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"pith_short_12","alias_value":"GWNGNI4J27GT","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"pith_short_16","alias_value":"GWNGNI4J27GTSXDC","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"pith_short_8","alias_value":"GWNGNI4J","created_at":"2026-07-05T09:15:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GWNGNI4J27GTSXDCLD4KIA6F2N","target":"record","payload":{"canonical_record":{"source":{"id":"2410.02596","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T15:37:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c9f80b5ad31c824b25a3c9bdd49534a62d7325c8e1648094cce8ad956b3b4e64","abstract_canon_sha256":"6d2320a3c06a4f63dd64d09fe7d6954bd04a04770bc24c243a5565a1b2231696"},"schema_version":"1.0"},"canonical_sha256":"359a66a389d7cd395c6258f8a403c5d36dc0d52f0783a2535d66aefdc46fbcea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:23.329608Z","signature_b64":"72ONwIAwvJunpSi5nMUfzgnae/xuu207sy7YWfr8/2VfjOpgtec9BHPiSZ5noMSOz6s0WlLU4onkUHyeglBqBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"359a66a389d7cd395c6258f8a403c5d36dc0d52f0783a2535d66aefdc46fbcea","last_reissued_at":"2026-07-05T09:15:23.329149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:23.329149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.02596","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:15:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rQRyUf/NDPRKY51L0Wlgrj0HCs22bmFpfqr4Prx6IggBdbvcGJhLBh7MTBDkPTzuMp9BKsINRzkyuL/1E2d0Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:32:30.793676Z"},"content_sha256":"08daf2799a25fa9c38757f934e0ea43a9c1b6a18fc00a5a15d8dbac5c639a7ed","schema_version":"1.0","event_id":"sha256:08daf2799a25fa9c38757f934e0ea43a9c1b6a18fc00a5a15d8dbac5c639a7ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GWNGNI4J27GTSXDCLD4KIA6F2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Longbo Huang, Rui Hu, Yifan Zhang, Zhuoran Li","submitted_at":"2024-10-03T15:37:22Z","abstract_excerpt":"Generative Flow Networks (GFlowNets) are a novel class of generative models designed to sample from unnormalized distributions and have found applications in various important tasks, attracting great research interest in their training algorithms. In general, GFlowNets are trained by fitting the forward flow to the backward flow on sampled training objects. Prior work focused on the choice of training objects, parameterizations, sampling and resampling strategies, and backward policies, aiming to enhance credit assignment, exploration, or exploitation of the training process. However, the choi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02596","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/2410.02596/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":"2026-07-05T09:15:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZDBUYRzC2VwSHlx3EWRcfdT/eYrU0jiGqLoKMAxxwXyawoVNGP+nGIjTLi11pXEaENAmYMqgWUWbtdfCayQNAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:32:30.794169Z"},"content_sha256":"2f7552134bda77479f7097d2509159a6838efafb965802ecf7ebb94ca3d4a551","schema_version":"1.0","event_id":"sha256:2f7552134bda77479f7097d2509159a6838efafb965802ecf7ebb94ca3d4a551"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GWNGNI4J27GTSXDCLD4KIA6F2N/bundle.json","state_url":"https://pith.science/pith/GWNGNI4J27GTSXDCLD4KIA6F2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GWNGNI4J27GTSXDCLD4KIA6F2N/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":"2026-08-08T12:32:30Z","links":{"resolver":"https://pith.science/pith/GWNGNI4J27GTSXDCLD4KIA6F2N","bundle":"https://pith.science/pith/GWNGNI4J27GTSXDCLD4KIA6F2N/bundle.json","state":"https://pith.science/pith/GWNGNI4J27GTSXDCLD4KIA6F2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GWNGNI4J27GTSXDCLD4KIA6F2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GWNGNI4J27GTSXDCLD4KIA6F2N","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":"6d2320a3c06a4f63dd64d09fe7d6954bd04a04770bc24c243a5565a1b2231696","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T15:37:22Z","title_canon_sha256":"c9f80b5ad31c824b25a3c9bdd49534a62d7325c8e1648094cce8ad956b3b4e64"},"schema_version":"1.0","source":{"id":"2410.02596","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.02596","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"arxiv_version","alias_value":"2410.02596v1","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02596","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"pith_short_12","alias_value":"GWNGNI4J27GT","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"pith_short_16","alias_value":"GWNGNI4J27GTSXDC","created_at":"2026-07-05T09:15:23Z"},{"alias_kind":"pith_short_8","alias_value":"GWNGNI4J","created_at":"2026-07-05T09:15:23Z"}],"graph_snapshots":[{"event_id":"sha256:2f7552134bda77479f7097d2509159a6838efafb965802ecf7ebb94ca3d4a551","target":"graph","created_at":"2026-07-05T09:15:23Z","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/2410.02596/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative Flow Networks (GFlowNets) are a novel class of generative models designed to sample from unnormalized distributions and have found applications in various important tasks, attracting great research interest in their training algorithms. In general, GFlowNets are trained by fitting the forward flow to the backward flow on sampled training objects. Prior work focused on the choice of training objects, parameterizations, sampling and resampling strategies, and backward policies, aiming to enhance credit assignment, exploration, or exploitation of the training process. However, the choi","authors_text":"Longbo Huang, Rui Hu, Yifan Zhang, Zhuoran Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T15:37:22Z","title":"Beyond Squared Error: Exploring Loss Design for Enhanced Training of Generative Flow Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02596","kind":"arxiv","version":1},"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":"sha256:08daf2799a25fa9c38757f934e0ea43a9c1b6a18fc00a5a15d8dbac5c639a7ed","target":"record","created_at":"2026-07-05T09:15:23Z","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":"6d2320a3c06a4f63dd64d09fe7d6954bd04a04770bc24c243a5565a1b2231696","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-10-03T15:37:22Z","title_canon_sha256":"c9f80b5ad31c824b25a3c9bdd49534a62d7325c8e1648094cce8ad956b3b4e64"},"schema_version":"1.0","source":{"id":"2410.02596","kind":"arxiv","version":1}},"canonical_sha256":"359a66a389d7cd395c6258f8a403c5d36dc0d52f0783a2535d66aefdc46fbcea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"359a66a389d7cd395c6258f8a403c5d36dc0d52f0783a2535d66aefdc46fbcea","first_computed_at":"2026-07-05T09:15:23.329149Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:15:23.329149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"72ONwIAwvJunpSi5nMUfzgnae/xuu207sy7YWfr8/2VfjOpgtec9BHPiSZ5noMSOz6s0WlLU4onkUHyeglBqBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:15:23.329608Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.02596","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08daf2799a25fa9c38757f934e0ea43a9c1b6a18fc00a5a15d8dbac5c639a7ed","sha256:2f7552134bda77479f7097d2509159a6838efafb965802ecf7ebb94ca3d4a551"],"state_sha256":"ed313145c36e1e7be8008462645dbebfa1e62667018e4839a0c1e0da447b323a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iyJn7i6UuOiwJJc7AZ/OYKm8DP79iQKjPTfKIqvG/EzwQzeZKMDqmvjXLN8YuqC5nL0JLn6Uvl+QBBDha6g/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:32:30.797402Z","bundle_sha256":"f038550c719d4a19aa89286120f917ca36599b43f4ed992fcd14b810bd2cde5a"}}