{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:R4RO2FJKOO6ZLKVRRTW6ZBEUEJ","short_pith_number":"pith:R4RO2FJK","canonical_record":{"source":{"id":"2603.00171","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T15:41:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1db13394f1436b0ebce806accfcc05626ffaa95dcdb96d75aa3f0048c872f5d","abstract_canon_sha256":"4ea4f3991ff9d86a188b9f038c6bc43a29312f43605a55d09b7362a305825bad"},"schema_version":"1.0"},"canonical_sha256":"8f22ed152a73bd95aab18cedec84942245b48babd66f2462b898d76621484ae4","source":{"kind":"arxiv","id":"2603.00171","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00171","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00171v3","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00171","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"R4RO2FJKOO6Z","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"R4RO2FJKOO6ZLKVR","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"R4RO2FJK","created_at":"2026-06-02T01:03:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:R4RO2FJKOO6ZLKVRRTW6ZBEUEJ","target":"record","payload":{"canonical_record":{"source":{"id":"2603.00171","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T15:41:26Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c1db13394f1436b0ebce806accfcc05626ffaa95dcdb96d75aa3f0048c872f5d","abstract_canon_sha256":"4ea4f3991ff9d86a188b9f038c6bc43a29312f43605a55d09b7362a305825bad"},"schema_version":"1.0"},"canonical_sha256":"8f22ed152a73bd95aab18cedec84942245b48babd66f2462b898d76621484ae4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T01:03:44.281253Z","signature_b64":"cgDXWGLTo+7Crw3hzfdvG7x1z4ALh2lfvFxsDy5UPWozcX/+WuAaZGvkUdO8264ALUlbpEodzI1YQIZ/satlDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8f22ed152a73bd95aab18cedec84942245b48babd66f2462b898d76621484ae4","last_reissued_at":"2026-06-02T01:03:44.280777Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T01:03:44.280777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.00171","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-02T01:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eaXAcy6q1YjyASQFuViPFM118tuaBeNOLheXV1TwpsbR2cOvI4keVQOFken1np6gg39zTy/VE9+n3BnlUQvZCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:41:48.201724Z"},"content_sha256":"6d7a68b94d5c652bfa105ca21c5968d56dd280e6d81f05848e67cab0f2f2a69e","schema_version":"1.0","event_id":"sha256:6d7a68b94d5c652bfa105ca21c5968d56dd280e6d81f05848e67cab0f2f2a69e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:R4RO2FJKOO6ZLKVRRTW6ZBEUEJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengjun Xie, Hailong Huang, Haoxuan Che, Jie Zhang, Man Zhou, Xuanhua He, Xueheng Li, Yuxiang Shen, Zhenkun Gao","submitted_at":"2026-02-26T15:41:26Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) are shifting towards \"Thinking with Images\" by actively exploring image details. While effective, large-scale training is computationally expensive, which has spurred growing interest in lightweight, training-free solutions. However, existing training-free methods suffer from two flaws: perceptual redundancy from indiscriminate cropping, which increases computational cost and introduces noise; and a drift between semantic intent and spatial attention, which prevents accurate localization of user-focused regions. To address these challenges, we propose L"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00171","kind":"arxiv","version":3},"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/2603.00171/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":"2026-06-02T01:03:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"C2odM8b5uKQpu52Y1FfGvdWdNCbsq5WB6PrSKxS6sRw9MZFf+PfM9thNhUyfp+rCwWMuuxdCvD2+qVKsuehgBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-05T00:41:48.202369Z"},"content_sha256":"849285a0b7caca65d9a2cef5f2e9f598ccf13b29c60d8d88d14ed12668cff52f","schema_version":"1.0","event_id":"sha256:849285a0b7caca65d9a2cef5f2e9f598ccf13b29c60d8d88d14ed12668cff52f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/bundle.json","state_url":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/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":"2026-06-05T00:41:48Z","links":{"resolver":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ","bundle":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/bundle.json","state":"https://pith.science/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R4RO2FJKOO6ZLKVRRTW6ZBEUEJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:R4RO2FJKOO6ZLKVRRTW6ZBEUEJ","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":"4ea4f3991ff9d86a188b9f038c6bc43a29312f43605a55d09b7362a305825bad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T15:41:26Z","title_canon_sha256":"c1db13394f1436b0ebce806accfcc05626ffaa95dcdb96d75aa3f0048c872f5d"},"schema_version":"1.0","source":{"id":"2603.00171","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.00171","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"arxiv_version","alias_value":"2603.00171v3","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.00171","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_12","alias_value":"R4RO2FJKOO6Z","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_16","alias_value":"R4RO2FJKOO6ZLKVR","created_at":"2026-06-02T01:03:44Z"},{"alias_kind":"pith_short_8","alias_value":"R4RO2FJK","created_at":"2026-06-02T01:03:44Z"}],"graph_snapshots":[{"event_id":"sha256:849285a0b7caca65d9a2cef5f2e9f598ccf13b29c60d8d88d14ed12668cff52f","target":"graph","created_at":"2026-06-02T01:03:44Z","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/2603.00171/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) are shifting towards \"Thinking with Images\" by actively exploring image details. While effective, large-scale training is computationally expensive, which has spurred growing interest in lightweight, training-free solutions. However, existing training-free methods suffer from two flaws: perceptual redundancy from indiscriminate cropping, which increases computational cost and introduces noise; and a drift between semantic intent and spatial attention, which prevents accurate localization of user-focused regions. To address these challenges, we propose L","authors_text":"Chengjun Xie, Hailong Huang, Haoxuan Che, Jie Zhang, Man Zhou, Xuanhua He, Xueheng Li, Yuxiang Shen, Zhenkun Gao","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T15:41:26Z","title":"LookWise: Knowing When and Where to Look for Fine-Grained Visual Reasoning in Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.00171","kind":"arxiv","version":3},"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":"sha256:6d7a68b94d5c652bfa105ca21c5968d56dd280e6d81f05848e67cab0f2f2a69e","target":"record","created_at":"2026-06-02T01:03:44Z","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":"4ea4f3991ff9d86a188b9f038c6bc43a29312f43605a55d09b7362a305825bad","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-02-26T15:41:26Z","title_canon_sha256":"c1db13394f1436b0ebce806accfcc05626ffaa95dcdb96d75aa3f0048c872f5d"},"schema_version":"1.0","source":{"id":"2603.00171","kind":"arxiv","version":3}},"canonical_sha256":"8f22ed152a73bd95aab18cedec84942245b48babd66f2462b898d76621484ae4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8f22ed152a73bd95aab18cedec84942245b48babd66f2462b898d76621484ae4","first_computed_at":"2026-06-02T01:03:44.280777Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T01:03:44.280777Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cgDXWGLTo+7Crw3hzfdvG7x1z4ALh2lfvFxsDy5UPWozcX/+WuAaZGvkUdO8264ALUlbpEodzI1YQIZ/satlDA==","signature_status":"signed_v1","signed_at":"2026-06-02T01:03:44.281253Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.00171","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d7a68b94d5c652bfa105ca21c5968d56dd280e6d81f05848e67cab0f2f2a69e","sha256:849285a0b7caca65d9a2cef5f2e9f598ccf13b29c60d8d88d14ed12668cff52f"],"state_sha256":"281d206bd23db5283613e2e3cbe6091be65ee7cfe259e4f7b3e22b00c9a66ae8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c0mA3gEpIMcJMPl+7WinkAwmsxJSy6JBhPWTBZ6ONROyQjcp7iVDet0o7YkFsxSMuO4S6DWQI7yDfTrRnWWwBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-05T00:41:48.205350Z","bundle_sha256":"6e088636f2cfc59f639be4fa7cc8880ed6c4052be99bc793355811bed009f8c2"}}