{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:77VKMRQSGK3YF6NO6BHC7VR3OP","short_pith_number":"pith:77VKMRQS","schema_version":"1.0","canonical_sha256":"ffeaa6461232b782f9aef04e2fd63b73ea64db07445fd4f0277ecbcce9c29b27","source":{"kind":"arxiv","id":"2607.00606","version":1},"attestation_state":"computed","paper":{"title":"Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingchen Huang, Yifu Chen, Yuanchao Du, Zhiling Wang","submitted_at":"2026-07-01T08:31:09Z","abstract_excerpt":"Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesizes code, or imagines new imagery, each at the cost of a tool protocol, brittle code, or an expensive training pipeline. A fourth route makes vision dynamic without generating anything, by retrieving labeled exemplar images and reasoning over them, yet it remains underexplored despite being train-free. We present ReVisIT, a train-free framework that realizes this retrieval-based route by treating each retrieved image-label pair as a unit of vis"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.00606","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-01T08:31:09Z","cross_cats_sorted":[],"title_canon_sha256":"225e981a3c4b7918141a180b3246eac8b0e6cf66ccef5311cdbd3036db008904","abstract_canon_sha256":"b014cc7dffaab3b3e736f3c2d2431bba564b4a87c818fd27400b6e7c316ce959"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T01:17:48.970999Z","signature_b64":"bl3jsAgPrAREUs17MwS6UKwhPsaz/7ArZfaboDvRUDp6UqwY/zPnEYUIcg/yxNhLs+t+rhFlCtAgwou7gSY6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ffeaa6461232b782f9aef04e2fd63b73ea64db07445fd4f0277ecbcce9c29b27","last_reissued_at":"2026-07-02T01:17:48.970581Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T01:17:48.970581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Retrieved Images as Visual Thought: Training-Free Multimodal In-Context Learning for the Open-vs-Closed Gap","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bingchen Huang, Yifu Chen, Yuanchao Du, Zhiling Wang","submitted_at":"2026-07-01T08:31:09Z","abstract_excerpt":"Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesizes code, or imagines new imagery, each at the cost of a tool protocol, brittle code, or an expensive training pipeline. A fourth route makes vision dynamic without generating anything, by retrieving labeled exemplar images and reasoning over them, yet it remains underexplored despite being train-free. We present ReVisIT, a train-free framework that realizes this retrieval-based route by treating each retrieved image-label pair as a unit of vis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00606","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/2607.00606/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.00606","created_at":"2026-07-02T01:17:48.970644+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.00606v1","created_at":"2026-07-02T01:17:48.970644+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00606","created_at":"2026-07-02T01:17:48.970644+00:00"},{"alias_kind":"pith_short_12","alias_value":"77VKMRQSGK3Y","created_at":"2026-07-02T01:17:48.970644+00:00"},{"alias_kind":"pith_short_16","alias_value":"77VKMRQSGK3YF6NO","created_at":"2026-07-02T01:17:48.970644+00:00"},{"alias_kind":"pith_short_8","alias_value":"77VKMRQS","created_at":"2026-07-02T01:17:48.970644+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/77VKMRQSGK3YF6NO6BHC7VR3OP","json":"https://pith.science/pith/77VKMRQSGK3YF6NO6BHC7VR3OP.json","graph_json":"https://pith.science/api/pith-number/77VKMRQSGK3YF6NO6BHC7VR3OP/graph.json","events_json":"https://pith.science/api/pith-number/77VKMRQSGK3YF6NO6BHC7VR3OP/events.json","paper":"https://pith.science/paper/77VKMRQS"},"agent_actions":{"view_html":"https://pith.science/pith/77VKMRQSGK3YF6NO6BHC7VR3OP","download_json":"https://pith.science/pith/77VKMRQSGK3YF6NO6BHC7VR3OP.json","view_paper":"https://pith.science/paper/77VKMRQS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.00606&json=true","fetch_graph":"https://pith.science/api/pith-number/77VKMRQSGK3YF6NO6BHC7VR3OP/graph.json","fetch_events":"https://pith.science/api/pith-number/77VKMRQSGK3YF6NO6BHC7VR3OP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/77VKMRQSGK3YF6NO6BHC7VR3OP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/77VKMRQSGK3YF6NO6BHC7VR3OP/action/storage_attestation","attest_author":"https://pith.science/pith/77VKMRQSGK3YF6NO6BHC7VR3OP/action/author_attestation","sign_citation":"https://pith.science/pith/77VKMRQSGK3YF6NO6BHC7VR3OP/action/citation_signature","submit_replication":"https://pith.science/pith/77VKMRQSGK3YF6NO6BHC7VR3OP/action/replication_record"}},"created_at":"2026-07-02T01:17:48.970644+00:00","updated_at":"2026-07-02T01:17:48.970644+00:00"}