{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KTVR5GSU2GOEJD3QHIACJ7DTTJ","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":"b9f89edda185e72e2e8a08686ffb1e94986bad1bf5d21c654be7a61a7acacdfc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T11:23:18Z","title_canon_sha256":"f75b514a19122b90b97007503b7923680affe763c3c40aee893438c1b1f8f7df"},"schema_version":"1.0","source":{"id":"2606.27974","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.27974","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"arxiv_version","alias_value":"2606.27974v1","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.27974","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"pith_short_12","alias_value":"KTVR5GSU2GOE","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"pith_short_16","alias_value":"KTVR5GSU2GOEJD3Q","created_at":"2026-06-29T01:14:54Z"},{"alias_kind":"pith_short_8","alias_value":"KTVR5GSU","created_at":"2026-06-29T01:14:54Z"}],"graph_snapshots":[{"event_id":"sha256:ec46bd5906d91f74b362fcc306bfcf533d50ad7d7b9dd61d17b9880d9eb53f43","target":"graph","created_at":"2026-06-29T01:14:54Z","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/2606.27974/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Knowledge-based Visual Question Answering (KB-VQA) requires models to combine image understanding with external knowledge. Most prior methods use a fixed retrieve-then-generate pipeline with a pre-selected retriever and a static top-k setting, which is not adaptive during reasoning. We propose ProMSA, a progressive multimodal search agent for KB-VQA. Given an image-question pair, the agent iteratively chooses image search, text search, or stop, under explicit tool-call budgets and with deduplication to avoid redundant retrieval. For training, we first use rejection-sampling SFT to learn valid ","authors_text":"Chuanrui Zhang, Hangrui Xu, Haonan Lu, Haoqian Wang, Jun Yang, Kai Shi, Yunyao Yu, Zhengxian Wu, Zhenyu Yang, Zhuohong Chen, Zirui Liao","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T11:23:18Z","title":"ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27974","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:a8228265d506d51c9c4d2e4be0ce4e6862ea4d8a55d5b7459ed630bcfcc20dfa","target":"record","created_at":"2026-06-29T01:14:54Z","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":"b9f89edda185e72e2e8a08686ffb1e94986bad1bf5d21c654be7a61a7acacdfc","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T11:23:18Z","title_canon_sha256":"f75b514a19122b90b97007503b7923680affe763c3c40aee893438c1b1f8f7df"},"schema_version":"1.0","source":{"id":"2606.27974","kind":"arxiv","version":1}},"canonical_sha256":"54eb1e9a54d19c448f703a0024fc739a4918d60fa0fa25baf42aaf2546aad5a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"54eb1e9a54d19c448f703a0024fc739a4918d60fa0fa25baf42aaf2546aad5a1","first_computed_at":"2026-06-29T01:14:54.331094Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:14:54.331094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nbHkWaXXgqiY+vB4uSujfLH01ty3oN+/NpzwzXbmczb6t6KXh8OezWu750sM+P+tXa5zP+qdCdDyT+44/1zrCQ==","signature_status":"signed_v1","signed_at":"2026-06-29T01:14:54.331485Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.27974","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a8228265d506d51c9c4d2e4be0ce4e6862ea4d8a55d5b7459ed630bcfcc20dfa","sha256:ec46bd5906d91f74b362fcc306bfcf533d50ad7d7b9dd61d17b9880d9eb53f43"],"state_sha256":"dabf7aac3edf3ca74f4fd3eaa3ba8f50917ce0a5c2737bb2be1580ef0ca7f485"}