{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LDE6LJ2DTDSSAHTWDW6PHQUMDH","short_pith_number":"pith:LDE6LJ2D","canonical_record":{"source":{"id":"2411.16044","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T02:15:30Z","cross_cats_sorted":[],"title_canon_sha256":"f8acd0863499cc809c9ec05cd788109495162b03793847346e8500e68ba30ae4","abstract_canon_sha256":"040948a3fce5e3d2bea76f3f724562e97322bb254f90786919a32f8ab720434e"},"schema_version":"1.0"},"canonical_sha256":"58c9e5a74398e5201e761dbcf3c28c19f6f03a00b8b36094620e44944f6c6e18","source":{"kind":"arxiv","id":"2411.16044","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16044","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16044v4","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16044","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"pith_short_12","alias_value":"LDE6LJ2DTDSS","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"pith_short_16","alias_value":"LDE6LJ2DTDSSAHTW","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"pith_short_8","alias_value":"LDE6LJ2D","created_at":"2026-07-05T12:02:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LDE6LJ2DTDSSAHTWDW6PHQUMDH","target":"record","payload":{"canonical_record":{"source":{"id":"2411.16044","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T02:15:30Z","cross_cats_sorted":[],"title_canon_sha256":"f8acd0863499cc809c9ec05cd788109495162b03793847346e8500e68ba30ae4","abstract_canon_sha256":"040948a3fce5e3d2bea76f3f724562e97322bb254f90786919a32f8ab720434e"},"schema_version":"1.0"},"canonical_sha256":"58c9e5a74398e5201e761dbcf3c28c19f6f03a00b8b36094620e44944f6c6e18","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:37.983291Z","signature_b64":"fjW9SkpYrql7LfRogbS+N8T8so3ecAR9Kb6WGjm/y3ckaD2nsADPlu4gr0KHSBYmQGqgqfkPMqdaQRxrnHalBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58c9e5a74398e5201e761dbcf3c28c19f6f03a00b8b36094620e44944f6c6e18","last_reissued_at":"2026-07-05T12:02:37.982813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:37.982813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.16044","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:02:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0ZClEW1q2pXG+BimvuthxJRuct0S504QVp+7SX/wyh8v9YVXmm5b8S91sStTzw7eRAe0mrOmAiNWCFvLyj8ZBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T03:03:03.121978Z"},"content_sha256":"0ea7efa04dc93bc1ca6ddda9b89acd63d1665a46bef544e545204aa162753fda","schema_version":"1.0","event_id":"sha256:0ea7efa04dc93bc1ca6ddda9b89acd63d1665a46bef544e545204aa162753fda"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LDE6LJ2DTDSSAHTWDW6PHQUMDH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haozhan Shen, Jianwei Yin, Kangjia Zhao, Mingwei Zhu, Ruochen Xu, Tiancheng Zhao, Zilun Zhang","submitted_at":"2024-11-25T02:15:30Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in vision-language understanding. Recently, with the integration of test-time scaling techniques, these models have also shown strong potential in visual reasoning. However, most existing reasoning approaches remain text-level in nature: MLLMs are prompted to explore various combinations of textual tokens via their underlying language model, while the visual input remains fixed throughout the reasoning process. This paradigm limits the model's ability to fully exploit rich visual information, particularly when d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16044","kind":"arxiv","version":4},"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/2411.16044/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":"2026-07-05T12:02:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RXlxbab2iYiI2mXE1CipqMR0tqd9DlBba9yMYKoDH/osw3HlRVMdBwAWrj+PO1nU1TvjnSPJDcr888QncoT/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-24T03:03:03.122412Z"},"content_sha256":"8e63921a3b8dc24168a7c00372746d5cf0a63f2e65afdfc97a01f9ef40e0136f","schema_version":"1.0","event_id":"sha256:8e63921a3b8dc24168a7c00372746d5cf0a63f2e65afdfc97a01f9ef40e0136f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/bundle.json","state_url":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/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":"2026-07-24T03:03:03Z","links":{"resolver":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH","bundle":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/bundle.json","state":"https://pith.science/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LDE6LJ2DTDSSAHTWDW6PHQUMDH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LDE6LJ2DTDSSAHTWDW6PHQUMDH","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":"040948a3fce5e3d2bea76f3f724562e97322bb254f90786919a32f8ab720434e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T02:15:30Z","title_canon_sha256":"f8acd0863499cc809c9ec05cd788109495162b03793847346e8500e68ba30ae4"},"schema_version":"1.0","source":{"id":"2411.16044","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.16044","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"arxiv_version","alias_value":"2411.16044v4","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.16044","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"pith_short_12","alias_value":"LDE6LJ2DTDSS","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"pith_short_16","alias_value":"LDE6LJ2DTDSSAHTW","created_at":"2026-07-05T12:02:37Z"},{"alias_kind":"pith_short_8","alias_value":"LDE6LJ2D","created_at":"2026-07-05T12:02:37Z"}],"graph_snapshots":[{"event_id":"sha256:8e63921a3b8dc24168a7c00372746d5cf0a63f2e65afdfc97a01f9ef40e0136f","target":"graph","created_at":"2026-07-05T12:02:37Z","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/2411.16044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in vision-language understanding. Recently, with the integration of test-time scaling techniques, these models have also shown strong potential in visual reasoning. However, most existing reasoning approaches remain text-level in nature: MLLMs are prompted to explore various combinations of textual tokens via their underlying language model, while the visual input remains fixed throughout the reasoning process. This paradigm limits the model's ability to fully exploit rich visual information, particularly when d","authors_text":"Haozhan Shen, Jianwei Yin, Kangjia Zhao, Mingwei Zhu, Ruochen Xu, Tiancheng Zhao, Zilun Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T02:15:30Z","title":"ZoomEye: Enhancing Multimodal LLMs with Human-Like Zooming Capabilities through Tree-Based Image Exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.16044","kind":"arxiv","version":4},"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":"sha256:0ea7efa04dc93bc1ca6ddda9b89acd63d1665a46bef544e545204aa162753fda","target":"record","created_at":"2026-07-05T12:02:37Z","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":"040948a3fce5e3d2bea76f3f724562e97322bb254f90786919a32f8ab720434e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-25T02:15:30Z","title_canon_sha256":"f8acd0863499cc809c9ec05cd788109495162b03793847346e8500e68ba30ae4"},"schema_version":"1.0","source":{"id":"2411.16044","kind":"arxiv","version":4}},"canonical_sha256":"58c9e5a74398e5201e761dbcf3c28c19f6f03a00b8b36094620e44944f6c6e18","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"58c9e5a74398e5201e761dbcf3c28c19f6f03a00b8b36094620e44944f6c6e18","first_computed_at":"2026-07-05T12:02:37.982813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:37.982813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fjW9SkpYrql7LfRogbS+N8T8so3ecAR9Kb6WGjm/y3ckaD2nsADPlu4gr0KHSBYmQGqgqfkPMqdaQRxrnHalBw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:37.983291Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.16044","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0ea7efa04dc93bc1ca6ddda9b89acd63d1665a46bef544e545204aa162753fda","sha256:8e63921a3b8dc24168a7c00372746d5cf0a63f2e65afdfc97a01f9ef40e0136f"],"state_sha256":"a182fd9f87cd1ea7ad6865965b8cc0d2d51cff382adc363c4d728fc14f29965f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZIuy1LqQHHEbxq9zVOxnXEl/t3Dvh4hw0hzhfTm3lo1WKSMyF6qiv3CYxwQILncxUWvuVjDNb5sP/O6mCWaQDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-24T03:03:03.126536Z","bundle_sha256":"d1a0151f0d08f70fd2f414db1abffdb01b5f5a1daeb906818db456564a6ad6b8"}}