{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CRLQZXOY55NK45P7UY3HL7K2MQ","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":"ec28f303e51ce7ec91941df0dfb4ea7ce3f470e3e32351c1fcfd566df1de4bca","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-09T08:38:10Z","title_canon_sha256":"edbc5e4fc0a603a3f2b58f66a1f4113d7a02edcf492255d7fbdce998ac024680"},"schema_version":"1.0","source":{"id":"2503.06514","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.06514","created_at":"2026-07-05T10:38:44Z"},{"alias_kind":"arxiv_version","alias_value":"2503.06514v2","created_at":"2026-07-05T10:38:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.06514","created_at":"2026-07-05T10:38:44Z"},{"alias_kind":"pith_short_12","alias_value":"CRLQZXOY55NK","created_at":"2026-07-05T10:38:44Z"},{"alias_kind":"pith_short_16","alias_value":"CRLQZXOY55NK45P7","created_at":"2026-07-05T10:38:44Z"},{"alias_kind":"pith_short_8","alias_value":"CRLQZXOY","created_at":"2026-07-05T10:38:44Z"}],"graph_snapshots":[{"event_id":"sha256:49dee3591afbddc20e92b48a50ca1ecd9ca4234388051f45a9c9fef8b54fdcc3","target":"graph","created_at":"2026-07-05T10:38:44Z","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/2503.06514/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-Language Models (VLMs) have recently shown promising advancements in sequential decision-making tasks through task-specific fine-tuning. However, common fine-tuning methods, such as Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) techniques like Proximal Policy Optimization (PPO), present notable limitations: SFT assumes Independent and Identically Distributed (IID) data, while PPO focuses on maximizing cumulative rewards. These limitations often restrict solution diversity and hinder generalization in multi-step reasoning tasks. To address these challenges, we introduce a ","authors_text":"Enna Sachdeva, Haoqiang Kang, Kwonjoon Lee, Piyush Gupta, Sangjae Bae","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-09T08:38:10Z","title":"GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.06514","kind":"arxiv","version":2},"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":"sha256:6d1c2e9fdc5ab79d081ad93f49557fd636539ea3e455c5312eaa1885e4b15a6c","target":"record","created_at":"2026-07-05T10:38:44Z","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":"ec28f303e51ce7ec91941df0dfb4ea7ce3f470e3e32351c1fcfd566df1de4bca","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-09T08:38:10Z","title_canon_sha256":"edbc5e4fc0a603a3f2b58f66a1f4113d7a02edcf492255d7fbdce998ac024680"},"schema_version":"1.0","source":{"id":"2503.06514","kind":"arxiv","version":2}},"canonical_sha256":"14570cddd8ef5aae75ffa63675fd5a640f32af29c32fbfce12e15608d1288c47","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14570cddd8ef5aae75ffa63675fd5a640f32af29c32fbfce12e15608d1288c47","first_computed_at":"2026-07-05T10:38:44.006861Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:38:44.006861Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wdJh1OJMBaVCta3fApH4C7jiSPbt/SKQO51yL4WfVHdgbPkW8xX0tEDEbm6WTtgMAYfAEZXYFt/eTuzieGakAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:38:44.007332Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.06514","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d1c2e9fdc5ab79d081ad93f49557fd636539ea3e455c5312eaa1885e4b15a6c","sha256:49dee3591afbddc20e92b48a50ca1ecd9ca4234388051f45a9c9fef8b54fdcc3"],"state_sha256":"1ed2a5d8f3a8b0ec70ecdd5f80f7e153332885fa44adcfe38b5383aab09769f8"}