{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:KTVR5GSU2GOEJD3QHIACJ7DTTJ","short_pith_number":"pith:KTVR5GSU","canonical_record":{"source":{"id":"2606.27974","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T11:23:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f75b514a19122b90b97007503b7923680affe763c3c40aee893438c1b1f8f7df","abstract_canon_sha256":"b9f89edda185e72e2e8a08686ffb1e94986bad1bf5d21c654be7a61a7acacdfc"},"schema_version":"1.0"},"canonical_sha256":"54eb1e9a54d19c448f703a0024fc739a4918d60fa0fa25baf42aaf2546aad5a1","source":{"kind":"arxiv","id":"2606.27974","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:KTVR5GSU2GOEJD3QHIACJ7DTTJ","target":"record","payload":{"canonical_record":{"source":{"id":"2606.27974","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-26T11:23:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f75b514a19122b90b97007503b7923680affe763c3c40aee893438c1b1f8f7df","abstract_canon_sha256":"b9f89edda185e72e2e8a08686ffb1e94986bad1bf5d21c654be7a61a7acacdfc"},"schema_version":"1.0"},"canonical_sha256":"54eb1e9a54d19c448f703a0024fc739a4918d60fa0fa25baf42aaf2546aad5a1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:14:54.331485Z","signature_b64":"nbHkWaXXgqiY+vB4uSujfLH01ty3oN+/NpzwzXbmczb6t6KXh8OezWu750sM+P+tXa5zP+qdCdDyT+44/1zrCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"54eb1e9a54d19c448f703a0024fc739a4918d60fa0fa25baf42aaf2546aad5a1","last_reissued_at":"2026-06-29T01:14:54.331094Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:14:54.331094Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.27974","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":"2026-06-29T01:14:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ym9D5w/n11dYvIrAjFRtZwmPwn4Jwpmj1rajA5XuFakeksmcucu1DwIJy6C9b7A2lXwcH1j6L3PnqSdgRQnVAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:40:48.766718Z"},"content_sha256":"a8228265d506d51c9c4d2e4be0ce4e6862ea4d8a55d5b7459ed630bcfcc20dfa","schema_version":"1.0","event_id":"sha256:a8228265d506d51c9c4d2e4be0ce4e6862ea4d8a55d5b7459ed630bcfcc20dfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:KTVR5GSU2GOEJD3QHIACJ7DTTJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ProMSA:Progressive Multimodal Search Agents for Knowledge-Based Visual Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chuanrui Zhang, Hangrui Xu, Haonan Lu, Haoqian Wang, Jun Yang, Kai Shi, Yunyao Yu, Zhengxian Wu, Zhenyu Yang, Zhuohong Chen, Zirui Liao","submitted_at":"2026-06-26T11:23:18Z","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 "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.27974","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/2606.27974/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":"2026-06-29T01:14:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c7bGLQTYeCxylumcE+Z9c9XLOO9rqokKScnhHVwtrSA4y8jqo0yrxcRuBsQvvY3EBmyleJPGid1VDMEtJPhpCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T13:40:48.767083Z"},"content_sha256":"ec46bd5906d91f74b362fcc306bfcf533d50ad7d7b9dd61d17b9880d9eb53f43","schema_version":"1.0","event_id":"sha256:ec46bd5906d91f74b362fcc306bfcf533d50ad7d7b9dd61d17b9880d9eb53f43"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KTVR5GSU2GOEJD3QHIACJ7DTTJ/bundle.json","state_url":"https://pith.science/pith/KTVR5GSU2GOEJD3QHIACJ7DTTJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KTVR5GSU2GOEJD3QHIACJ7DTTJ/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":"2026-06-29T13:40:48Z","links":{"resolver":"https://pith.science/pith/KTVR5GSU2GOEJD3QHIACJ7DTTJ","bundle":"https://pith.science/pith/KTVR5GSU2GOEJD3QHIACJ7DTTJ/bundle.json","state":"https://pith.science/pith/KTVR5GSU2GOEJD3QHIACJ7DTTJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KTVR5GSU2GOEJD3QHIACJ7DTTJ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T+JgCxndUTu6xRD7iSLLE669JnjJoPiOciH6mYgYibyznzG2IbkmW9Pq4udt2mJqvoXhLjMhTUMr6mhN7SxyDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T13:40:48.769013Z","bundle_sha256":"3b5c461a26d7cc3e9014b760ddb9d99d0243cac46dcc0df2c9ce27b43bc7c29b"}}