{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5DRIVFIW7OTF6X34X6FVFJQRUH","short_pith_number":"pith:5DRIVFIW","canonical_record":{"source":{"id":"2510.00705","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T09:20:51Z","cross_cats_sorted":[],"title_canon_sha256":"f2b9be6ae67561b86ac2a9cd05da1b2c09a14c75074770c50c74b2ce0abf250e","abstract_canon_sha256":"2082b75952867c02bf4b6b1b22e0f39b2b28c39c9862b5deca4255ad8dd2a86d"},"schema_version":"1.0"},"canonical_sha256":"e8e28a9516fba65f5f7cbf8b52a611a1c09f9e88ccb3d55fa80b22fc10ce379a","source":{"kind":"arxiv","id":"2510.00705","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.00705","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2510.00705v3","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00705","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"5DRIVFIW7OTF","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"5DRIVFIW7OTF6X34","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"5DRIVFIW","created_at":"2026-06-29T01:15:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5DRIVFIW7OTF6X34X6FVFJQRUH","target":"record","payload":{"canonical_record":{"source":{"id":"2510.00705","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T09:20:51Z","cross_cats_sorted":[],"title_canon_sha256":"f2b9be6ae67561b86ac2a9cd05da1b2c09a14c75074770c50c74b2ce0abf250e","abstract_canon_sha256":"2082b75952867c02bf4b6b1b22e0f39b2b28c39c9862b5deca4255ad8dd2a86d"},"schema_version":"1.0"},"canonical_sha256":"e8e28a9516fba65f5f7cbf8b52a611a1c09f9e88ccb3d55fa80b22fc10ce379a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:03.275089Z","signature_b64":"1Sepe4ImRIgWWiZHwUVuHBnE+7PAECbBsPDKLf/9AazepuWtiZwkrrlxqxZIPBCr5lUefpLslTmTymzPCgYCDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8e28a9516fba65f5f7cbf8b52a611a1c09f9e88ccb3d55fa80b22fc10ce379a","last_reissued_at":"2026-06-29T01:15:03.274596Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:03.274596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.00705","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":"2026-06-29T01:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jJG2kQSBHwX9AxXZOPa4xlCM1aHJvqN6kJ9oXKTpQZ2EKlj3FjPuXCvFZYQ0wrVCYGJcD05TDnfKyKpj3EH/Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:33:09.337740Z"},"content_sha256":"8329533a443324fb5739b37e5f90c0cb2806f74c5a053be5e2ac8362a8218d3d","schema_version":"1.0","event_id":"sha256:8329533a443324fb5739b37e5f90c0cb2806f74c5a053be5e2ac8362a8218d3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5DRIVFIW7OTF6X34X6FVFJQRUH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Rui Xiao, Sanghwan Kim, Stephan Alaniz, Yongqin Xian, Zeynep Akata","submitted_at":"2025-10-01T09:20:51Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) often struggle with fine-grained perception, such as identifying small objects in high-resolution images or detecting key moments in long videos. Existing methods typically rely on complex, task-specific fine-tuning, which reduces generalizability and increases system complexity. In this work, we propose an effective, training-free framework that uses an MLLM's intrinsic uncertainty as proactive guidance. Our core insight is that a model's uncertainty decreases when provided with relevant visual information. We introduce a unified mechanism that scores "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00705","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/2510.00705/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":"2026-06-29T01:15:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wNZc32j5hzFEpt/IPbtY+f7Z9dPBrCzUaIv5UyxoQiDTcm2vXBQUAj3uTt8707uUcRV575szXBemVrCc+Cx/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T21:33:09.338106Z"},"content_sha256":"3c861067450cf1ebd2966d497d35f9f6297a95bd4a03c8c3a43a28fcbd24680b","schema_version":"1.0","event_id":"sha256:3c861067450cf1ebd2966d497d35f9f6297a95bd4a03c8c3a43a28fcbd24680b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5DRIVFIW7OTF6X34X6FVFJQRUH/bundle.json","state_url":"https://pith.science/pith/5DRIVFIW7OTF6X34X6FVFJQRUH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5DRIVFIW7OTF6X34X6FVFJQRUH/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":"2026-06-29T21:33:09Z","links":{"resolver":"https://pith.science/pith/5DRIVFIW7OTF6X34X6FVFJQRUH","bundle":"https://pith.science/pith/5DRIVFIW7OTF6X34X6FVFJQRUH/bundle.json","state":"https://pith.science/pith/5DRIVFIW7OTF6X34X6FVFJQRUH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5DRIVFIW7OTF6X34X6FVFJQRUH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5DRIVFIW7OTF6X34X6FVFJQRUH","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":"2082b75952867c02bf4b6b1b22e0f39b2b28c39c9862b5deca4255ad8dd2a86d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T09:20:51Z","title_canon_sha256":"f2b9be6ae67561b86ac2a9cd05da1b2c09a14c75074770c50c74b2ce0abf250e"},"schema_version":"1.0","source":{"id":"2510.00705","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.00705","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"arxiv_version","alias_value":"2510.00705v3","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.00705","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"pith_short_12","alias_value":"5DRIVFIW7OTF","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"pith_short_16","alias_value":"5DRIVFIW7OTF6X34","created_at":"2026-06-29T01:15:03Z"},{"alias_kind":"pith_short_8","alias_value":"5DRIVFIW","created_at":"2026-06-29T01:15:03Z"}],"graph_snapshots":[{"event_id":"sha256:3c861067450cf1ebd2966d497d35f9f6297a95bd4a03c8c3a43a28fcbd24680b","target":"graph","created_at":"2026-06-29T01:15:03Z","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/2510.00705/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal Large Language Models (MLLMs) often struggle with fine-grained perception, such as identifying small objects in high-resolution images or detecting key moments in long videos. Existing methods typically rely on complex, task-specific fine-tuning, which reduces generalizability and increases system complexity. In this work, we propose an effective, training-free framework that uses an MLLM's intrinsic uncertainty as proactive guidance. Our core insight is that a model's uncertainty decreases when provided with relevant visual information. We introduce a unified mechanism that scores ","authors_text":"Rui Xiao, Sanghwan Kim, Stephan Alaniz, Yongqin Xian, Zeynep Akata","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T09:20:51Z","title":"Training-free Uncertainty Guidance for Complex Visual Tasks with MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.00705","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":"sha256:8329533a443324fb5739b37e5f90c0cb2806f74c5a053be5e2ac8362a8218d3d","target":"record","created_at":"2026-06-29T01:15:03Z","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":"2082b75952867c02bf4b6b1b22e0f39b2b28c39c9862b5deca4255ad8dd2a86d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-10-01T09:20:51Z","title_canon_sha256":"f2b9be6ae67561b86ac2a9cd05da1b2c09a14c75074770c50c74b2ce0abf250e"},"schema_version":"1.0","source":{"id":"2510.00705","kind":"arxiv","version":3}},"canonical_sha256":"e8e28a9516fba65f5f7cbf8b52a611a1c09f9e88ccb3d55fa80b22fc10ce379a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e8e28a9516fba65f5f7cbf8b52a611a1c09f9e88ccb3d55fa80b22fc10ce379a","first_computed_at":"2026-06-29T01:15:03.274596Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-29T01:15:03.274596Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Sepe4ImRIgWWiZHwUVuHBnE+7PAECbBsPDKLf/9AazepuWtiZwkrrlxqxZIPBCr5lUefpLslTmTymzPCgYCDw==","signature_status":"signed_v1","signed_at":"2026-06-29T01:15:03.275089Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.00705","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8329533a443324fb5739b37e5f90c0cb2806f74c5a053be5e2ac8362a8218d3d","sha256:3c861067450cf1ebd2966d497d35f9f6297a95bd4a03c8c3a43a28fcbd24680b"],"state_sha256":"5092322ad0f3a88a9ed9f8cdf672f65ab279c9da68c0dea8ca235a7b31db7f1c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TOqIPDjkTLsqtHsf+BuuWdi/4rmseul5outtRdqop9uwCEwfwAhn2h2bhBJBJ5xR69DOWbN67GqYzf6op3faAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T21:33:09.340033Z","bundle_sha256":"59606396ee15b1c230bbe1e8b0f5bff4c50d43a5dcca6bca8c85e2c22f8d1c88"}}