{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CYHI64ITHHWNTOJKZJIJGWLWXU","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":"663be99f3525a115182866bec72777b5e38161e7db1073b51bc4b2a7af9cab44","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-18T17:23:36Z","title_canon_sha256":"f8e709b00ec8ca793c8affb4bec9b0ebb9cc468c1f5055d7f582621d076b199e"},"schema_version":"1.0","source":{"id":"2506.15649","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.15649","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"arxiv_version","alias_value":"2506.15649v1","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.15649","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"pith_short_12","alias_value":"CYHI64ITHHWN","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"pith_short_16","alias_value":"CYHI64ITHHWNTOJK","created_at":"2026-07-05T11:23:47Z"},{"alias_kind":"pith_short_8","alias_value":"CYHI64IT","created_at":"2026-07-05T11:23:47Z"}],"graph_snapshots":[{"event_id":"sha256:8a5195e4a360d27f8690517a0ec0ca6f23615163d857549dc82a8674a50e9818","target":"graph","created_at":"2026-07-05T11:23:47Z","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/2506.15649/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite significant advances in inference-time search for vision-language models (VLMs), existing approaches remain both computationally expensive and prone to unpenalized, low-confidence generations which often lead to persistent hallucinations. We introduce \\textbf{Value-guided Inference with Margin-based Reward (ViMaR)}, a two-stage inference framework that improves both efficiency and output fidelity by combining a temporal-difference value model with a margin-aware reward adjustment. In the first stage, we perform a single pass to identify the highest-value caption among diverse candidate","authors_text":"Adinath Madhavrao Dukre, Ankan Deria, Feilong Tang, Imran Razzak, Muhammad Awais, Muhammad Haris Khan, Sara Atito, Sudipta Roy","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-18T17:23:36Z","title":"Dual-Stage Value-Guided Inference with Margin-Based Reward Adjustment for Fast and Faithful VLM Captioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.15649","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":"sha256:0ca01780500da23f956ce7a14fb2f837bc5aff994afcc3b91c879d35a5486b01","target":"record","created_at":"2026-07-05T11:23:47Z","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":"663be99f3525a115182866bec72777b5e38161e7db1073b51bc4b2a7af9cab44","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-18T17:23:36Z","title_canon_sha256":"f8e709b00ec8ca793c8affb4bec9b0ebb9cc468c1f5055d7f582621d076b199e"},"schema_version":"1.0","source":{"id":"2506.15649","kind":"arxiv","version":1}},"canonical_sha256":"160e8f711339ecd9b92aca50935976bd0ebcfa9925cc0fd95abf32a0af68282a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"160e8f711339ecd9b92aca50935976bd0ebcfa9925cc0fd95abf32a0af68282a","first_computed_at":"2026-07-05T11:23:47.770929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:23:47.770929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ef1fidor4kAl9Pbo7hn4N2ujYQvtdZyGspJBj1kCFuKoEa6GuAkVRnHauDDoARGuBT3yfWLpiznfHM2AhSFlDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:23:47.771684Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.15649","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ca01780500da23f956ce7a14fb2f837bc5aff994afcc3b91c879d35a5486b01","sha256:8a5195e4a360d27f8690517a0ec0ca6f23615163d857549dc82a8674a50e9818"],"state_sha256":"4c3e53df26452caa28824743e807b6f18b9b94cd75375430cb3cb4ed7bb8af12"}