{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QCTUHGEJLMCSFWZLRQKMYQ2WYG","short_pith_number":"pith:QCTUHGEJ","canonical_record":{"source":{"id":"2607.03184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T10:42:34Z","cross_cats_sorted":[],"title_canon_sha256":"7c393b918a58925f09e501e2952c79b635098b5ed751e40a8cabf49f75f0914d","abstract_canon_sha256":"88c77d4e0a1edfccb9072e9f6b0c2e09ba9458fe1e5302610fc9e6f5817448cd"},"schema_version":"1.0"},"canonical_sha256":"80a74398895b0522db2b8c14cc4356c1bb02c9ff916c8b469e89ec8c3d48a164","source":{"kind":"arxiv","id":"2607.03184","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03184","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03184v1","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03184","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"QCTUHGEJLMCS","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"QCTUHGEJLMCSFWZL","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"QCTUHGEJ","created_at":"2026-07-07T01:16:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QCTUHGEJLMCSFWZLRQKMYQ2WYG","target":"record","payload":{"canonical_record":{"source":{"id":"2607.03184","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T10:42:34Z","cross_cats_sorted":[],"title_canon_sha256":"7c393b918a58925f09e501e2952c79b635098b5ed751e40a8cabf49f75f0914d","abstract_canon_sha256":"88c77d4e0a1edfccb9072e9f6b0c2e09ba9458fe1e5302610fc9e6f5817448cd"},"schema_version":"1.0"},"canonical_sha256":"80a74398895b0522db2b8c14cc4356c1bb02c9ff916c8b469e89ec8c3d48a164","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T01:16:45.928930Z","signature_b64":"I+xS3/Xli8/WI7bV6/9lz23aoq12E3UlTQ5WlrSTxljAgsenbErGnhYanbkBFQhkNAy/LW1Rdluy2G0n69JkDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80a74398895b0522db2b8c14cc4356c1bb02c9ff916c8b469e89ec8c3d48a164","last_reissued_at":"2026-07-07T01:16:45.928540Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T01:16:45.928540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.03184","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":"2026-07-07T01:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UjVm6ErzfYVcbxlqHVZTVfTY77jLJ92398DubfkVyX9+xK8ym/oVOCk1Tv7LS0mpmeGa9xZcRHLkKAdt34e3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T15:44:56.314975Z"},"content_sha256":"b37fddcc51dec95e59191e4fb91b67e5ca83d3bc9b0595c3aa8d659be8669f6f","schema_version":"1.0","event_id":"sha256:b37fddcc51dec95e59191e4fb91b67e5ca83d3bc9b0595c3aa8d659be8669f6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QCTUHGEJLMCSFWZLRQKMYQ2WYG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Geng Li, Yuxin Peng","submitted_at":"2026-07-03T10:42:34Z","abstract_excerpt":"While Multimodal Large Language Models (MLLMs) demonstrate impressive general capabilities, they struggle with fine-grained perception in ultra-high-resolution (UHR) images, particularly for tiny objects in cluttered scenes. Existing methods face a dilemma: they either rely on inefficient prior-free scanning, or depend on static prior-driven heuristics that lack posterior correction to rectify initial model biases. To address this, we propose BVS (Bayesian Visual Search), a framework that formulates perception as a global optimization problem over a continuous spatial-scale manifold. Specifica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03184","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/2607.03184/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":"2026-07-07T01:16:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SHB7QS0h0YOAgKosCqOYHlScqzIH2CbVR9HAC9lnXl70WBmD+kFChAGFI9SkIqJyImVA656WsUV+lzJgJ7xGCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T15:44:56.315371Z"},"content_sha256":"c98cec9a2d94c9d0d66f1e0652d49d4a5c1a1859621a929c1ed8363f4e2606eb","schema_version":"1.0","event_id":"sha256:c98cec9a2d94c9d0d66f1e0652d49d4a5c1a1859621a929c1ed8363f4e2606eb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QCTUHGEJLMCSFWZLRQKMYQ2WYG/bundle.json","state_url":"https://pith.science/pith/QCTUHGEJLMCSFWZLRQKMYQ2WYG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QCTUHGEJLMCSFWZLRQKMYQ2WYG/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":"2026-07-13T15:44:56Z","links":{"resolver":"https://pith.science/pith/QCTUHGEJLMCSFWZLRQKMYQ2WYG","bundle":"https://pith.science/pith/QCTUHGEJLMCSFWZLRQKMYQ2WYG/bundle.json","state":"https://pith.science/pith/QCTUHGEJLMCSFWZLRQKMYQ2WYG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QCTUHGEJLMCSFWZLRQKMYQ2WYG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QCTUHGEJLMCSFWZLRQKMYQ2WYG","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":"88c77d4e0a1edfccb9072e9f6b0c2e09ba9458fe1e5302610fc9e6f5817448cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T10:42:34Z","title_canon_sha256":"7c393b918a58925f09e501e2952c79b635098b5ed751e40a8cabf49f75f0914d"},"schema_version":"1.0","source":{"id":"2607.03184","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.03184","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"arxiv_version","alias_value":"2607.03184v1","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03184","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_12","alias_value":"QCTUHGEJLMCS","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_16","alias_value":"QCTUHGEJLMCSFWZL","created_at":"2026-07-07T01:16:45Z"},{"alias_kind":"pith_short_8","alias_value":"QCTUHGEJ","created_at":"2026-07-07T01:16:45Z"}],"graph_snapshots":[{"event_id":"sha256:c98cec9a2d94c9d0d66f1e0652d49d4a5c1a1859621a929c1ed8363f4e2606eb","target":"graph","created_at":"2026-07-07T01:16:45Z","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/2607.03184/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While Multimodal Large Language Models (MLLMs) demonstrate impressive general capabilities, they struggle with fine-grained perception in ultra-high-resolution (UHR) images, particularly for tiny objects in cluttered scenes. Existing methods face a dilemma: they either rely on inefficient prior-free scanning, or depend on static prior-driven heuristics that lack posterior correction to rectify initial model biases. To address this, we propose BVS (Bayesian Visual Search), a framework that formulates perception as a global optimization problem over a continuous spatial-scale manifold. Specifica","authors_text":"Geng Li, Yuxin Peng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T10:42:34Z","title":"BVS: Bayesian Visual Search with Multimodal Large Language Model for Fine-grained Perception"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03184","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:b37fddcc51dec95e59191e4fb91b67e5ca83d3bc9b0595c3aa8d659be8669f6f","target":"record","created_at":"2026-07-07T01:16:45Z","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":"88c77d4e0a1edfccb9072e9f6b0c2e09ba9458fe1e5302610fc9e6f5817448cd","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-03T10:42:34Z","title_canon_sha256":"7c393b918a58925f09e501e2952c79b635098b5ed751e40a8cabf49f75f0914d"},"schema_version":"1.0","source":{"id":"2607.03184","kind":"arxiv","version":1}},"canonical_sha256":"80a74398895b0522db2b8c14cc4356c1bb02c9ff916c8b469e89ec8c3d48a164","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80a74398895b0522db2b8c14cc4356c1bb02c9ff916c8b469e89ec8c3d48a164","first_computed_at":"2026-07-07T01:16:45.928540Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T01:16:45.928540Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I+xS3/Xli8/WI7bV6/9lz23aoq12E3UlTQ5WlrSTxljAgsenbErGnhYanbkBFQhkNAy/LW1Rdluy2G0n69JkDQ==","signature_status":"signed_v1","signed_at":"2026-07-07T01:16:45.928930Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.03184","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b37fddcc51dec95e59191e4fb91b67e5ca83d3bc9b0595c3aa8d659be8669f6f","sha256:c98cec9a2d94c9d0d66f1e0652d49d4a5c1a1859621a929c1ed8363f4e2606eb"],"state_sha256":"4c76ab2333e082ba2b763bf73ca5e28f464ce1e1cbb25863df37df6ee2379833"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eSn0JDXG2OX8VkZTWCBAXYDhtFG0Kk4QNHXQWvsO9Lsr56VZhnHbOtB+GvN0KUZ6ZZ1TjfjZ8bzqhbKB0/kfDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T15:44:56.317392Z","bundle_sha256":"c1ec17375d4dc46137aaaf5a430f75ccb74069ecf3da52dc2413504e3a4aa5a8"}}