{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:U5O6AB65OLRMIHKL5SK3YBPQPO","short_pith_number":"pith:U5O6AB65","canonical_record":{"source":{"id":"2608.03450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-04T10:46:10Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"b48fed4f5de278969ceb8fe1c71dc4ed24f1fb0dfb4adb50e2795bd0cb3f61ff","abstract_canon_sha256":"9164e9081e8b25cbbb06695919d7521e1c6a3e33d8024d616ef27cf7f15313b0"},"schema_version":"1.0"},"canonical_sha256":"a75de007dd72e2c41d4bec95bc05f07b8a1e316679f1f9d592ef223d23410774","source":{"kind":"arxiv","id":"2608.03450","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03450","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03450v1","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03450","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"U5O6AB65OLRM","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"U5O6AB65OLRMIHKL","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"U5O6AB65","created_at":"2026-08-05T01:35:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:U5O6AB65OLRMIHKL5SK3YBPQPO","target":"record","payload":{"canonical_record":{"source":{"id":"2608.03450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-04T10:46:10Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"b48fed4f5de278969ceb8fe1c71dc4ed24f1fb0dfb4adb50e2795bd0cb3f61ff","abstract_canon_sha256":"9164e9081e8b25cbbb06695919d7521e1c6a3e33d8024d616ef27cf7f15313b0"},"schema_version":"1.0"},"canonical_sha256":"a75de007dd72e2c41d4bec95bc05f07b8a1e316679f1f9d592ef223d23410774","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:35:52.361687Z","signature_b64":"/lQsAS266d5G5B3KYo8wKH5AXDc/RhEWE/EYBuClnh6n7R6R7vkUhdilQFeU6UTNcv4w1+wC9ibtdCO82cN7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a75de007dd72e2c41d4bec95bc05f07b8a1e316679f1f9d592ef223d23410774","last_reissued_at":"2026-08-05T01:35:52.360311Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:35:52.360311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.03450","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":"2026-08-05T01:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QV7XbpAQCoZ04dCBw2VA3u+0nRFhyaATkgU7mY12k6Ers/NrGSm6KlgTpARZDTHo57t6yrtQroBEIKo9rRClAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:26:46.526576Z"},"content_sha256":"001d87bf8e9355632a35d5e0a5266e9dae11bd9dee11324579405fd9519a45ab","schema_version":"1.0","event_id":"sha256:001d87bf8e9355632a35d5e0a5266e9dae11bd9dee11324579405fd9519a45ab"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:U5O6AB65OLRMIHKL5SK3YBPQPO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.MM","authors_text":"Bin Chen, Haoqian Kang, Jinpeng Wang, Ke Chen, Kuofeng Gao, Liupeng Li, Yaowei Wang, Zhenyu Lu","submitted_at":"2026-08-04T10:46:10Z","abstract_excerpt":"Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based Chain-of-Thought (CoT) is computationally expensive and prone to visual hallucinations, while existing latent reasoning methods typically require costly training. Furthermore, directly adapting training-free LLM reasoning mechanisms to the multimodal setting yields unstable performance. We identify that this failure stems from their reliance on token-level entropy, which fundamentally conflates perceptual ambiguity (e.g., unclear visual details)"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03450","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/2608.03450/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":"2026-08-05T01:35:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qPkGkqise9YJsivuiOrsL4nVnf9LFMYRs5WGPK93daIPiDajsFi1TjtHfYnbL6C2iuJ4WYKfGQ3sfnaSzCOEAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T12:26:46.527138Z"},"content_sha256":"7be4ddaf285e18294b307389fabb343aceb6548ae7d65e1948e626d8ec950996","schema_version":"1.0","event_id":"sha256:7be4ddaf285e18294b307389fabb343aceb6548ae7d65e1948e626d8ec950996"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U5O6AB65OLRMIHKL5SK3YBPQPO/bundle.json","state_url":"https://pith.science/pith/U5O6AB65OLRMIHKL5SK3YBPQPO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U5O6AB65OLRMIHKL5SK3YBPQPO/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":"2026-08-14T12:26:46Z","links":{"resolver":"https://pith.science/pith/U5O6AB65OLRMIHKL5SK3YBPQPO","bundle":"https://pith.science/pith/U5O6AB65OLRMIHKL5SK3YBPQPO/bundle.json","state":"https://pith.science/pith/U5O6AB65OLRMIHKL5SK3YBPQPO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U5O6AB65OLRMIHKL5SK3YBPQPO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:U5O6AB65OLRMIHKL5SK3YBPQPO","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":"9164e9081e8b25cbbb06695919d7521e1c6a3e33d8024d616ef27cf7f15313b0","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-04T10:46:10Z","title_canon_sha256":"b48fed4f5de278969ceb8fe1c71dc4ed24f1fb0dfb4adb50e2795bd0cb3f61ff"},"schema_version":"1.0","source":{"id":"2608.03450","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.03450","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"arxiv_version","alias_value":"2608.03450v1","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03450","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"pith_short_12","alias_value":"U5O6AB65OLRM","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"pith_short_16","alias_value":"U5O6AB65OLRMIHKL","created_at":"2026-08-05T01:35:52Z"},{"alias_kind":"pith_short_8","alias_value":"U5O6AB65","created_at":"2026-08-05T01:35:52Z"}],"graph_snapshots":[{"event_id":"sha256:7be4ddaf285e18294b307389fabb343aceb6548ae7d65e1948e626d8ec950996","target":"graph","created_at":"2026-08-05T01:35:52Z","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/2608.03450/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception and rigorous logical deduction. Explicit text-based Chain-of-Thought (CoT) is computationally expensive and prone to visual hallucinations, while existing latent reasoning methods typically require costly training. Furthermore, directly adapting training-free LLM reasoning mechanisms to the multimodal setting yields unstable performance. We identify that this failure stems from their reliance on token-level entropy, which fundamentally conflates perceptual ambiguity (e.g., unclear visual details)","authors_text":"Bin Chen, Haoqian Kang, Jinpeng Wang, Ke Chen, Kuofeng Gao, Liupeng Li, Yaowei Wang, Zhenyu Lu","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-04T10:46:10Z","title":"Balancing Efficiency and Efficacy: Training-Free Attention-Guided Switching Between Explicit and Latent Thoughts for MLLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03450","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":"sha256:001d87bf8e9355632a35d5e0a5266e9dae11bd9dee11324579405fd9519a45ab","target":"record","created_at":"2026-08-05T01:35:52Z","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":"9164e9081e8b25cbbb06695919d7521e1c6a3e33d8024d616ef27cf7f15313b0","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2026-08-04T10:46:10Z","title_canon_sha256":"b48fed4f5de278969ceb8fe1c71dc4ed24f1fb0dfb4adb50e2795bd0cb3f61ff"},"schema_version":"1.0","source":{"id":"2608.03450","kind":"arxiv","version":1}},"canonical_sha256":"a75de007dd72e2c41d4bec95bc05f07b8a1e316679f1f9d592ef223d23410774","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a75de007dd72e2c41d4bec95bc05f07b8a1e316679f1f9d592ef223d23410774","first_computed_at":"2026-08-05T01:35:52.360311Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-05T01:35:52.360311Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/lQsAS266d5G5B3KYo8wKH5AXDc/RhEWE/EYBuClnh6n7R6R7vkUhdilQFeU6UTNcv4w1+wC9ibtdCO82cN7DQ==","signature_status":"signed_v1","signed_at":"2026-08-05T01:35:52.361687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.03450","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:001d87bf8e9355632a35d5e0a5266e9dae11bd9dee11324579405fd9519a45ab","sha256:7be4ddaf285e18294b307389fabb343aceb6548ae7d65e1948e626d8ec950996"],"state_sha256":"bc2ec54a2f22d2102b11efbc27ec2e4fcef9b13084b5629204268e71a44aee08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"m1liWD0GbqI8MXgxXK1gbzn/HK66pVMQ8Ufz3NBuM4adQlN5mN2vfMAPE3U4uPO0YwjtzpIN2ialJuY8efINCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T12:26:46.533508Z","bundle_sha256":"2ad79d988dfecb5f35f1ae1e506e647c789850afcc2fe259473e95f026041556"}}