{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3I667Z7IRJM73RI2XBKDU6PWQY","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":"a53812c667dbf17029bc495c75681a5e02b9db8194439b08c9ab46f69c07ebe9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T21:01:37Z","title_canon_sha256":"903b6e64f70181e8c0a7a368e8b068dc73c6ec4ccff8a2308a2e91c21920d1f0"},"schema_version":"1.0","source":{"id":"2411.12591","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.12591","created_at":"2026-07-05T09:37:45Z"},{"alias_kind":"arxiv_version","alias_value":"2411.12591v1","created_at":"2026-07-05T09:37:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.12591","created_at":"2026-07-05T09:37:45Z"},{"alias_kind":"pith_short_12","alias_value":"3I667Z7IRJM7","created_at":"2026-07-05T09:37:45Z"},{"alias_kind":"pith_short_16","alias_value":"3I667Z7IRJM73RI2","created_at":"2026-07-05T09:37:45Z"},{"alias_kind":"pith_short_8","alias_value":"3I667Z7I","created_at":"2026-07-05T09:37:45Z"}],"graph_snapshots":[{"event_id":"sha256:55e565ee790472cccea4c1f562ab53099ca47c17eb451ca675efda376490f9d3","target":"graph","created_at":"2026-07-05T09:37:45Z","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/2411.12591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have advanced the integration of visual and linguistic modalities, establishing themselves as the dominant paradigm for visual-language tasks. Current approaches like chain of thought (CoT) reasoning have augmented the cognitive capabilities of large language models (LLMs), yet their adaptation to MLLMs is hindered by heightened risks of hallucination in cross-modality comprehension. In this paper, we find that the thinking while looking paradigm in current multimodal CoT approaches--where reasoning chains are generated alongside visual input--fails to ","authors_text":"Hanchi Sun, Haojie Zheng, Lichao Sun, Ruoxi Chen, Shu Pu, Tianyang Xu","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T21:01:37Z","title":"Thinking Before Looking: Improving Multimodal LLM Reasoning via Mitigating Visual Hallucination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.12591","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:ebc8f9fbc4a798ff294b306f935462e27176a993c85e0057f4e82d35d579e247","target":"record","created_at":"2026-07-05T09:37:45Z","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":"a53812c667dbf17029bc495c75681a5e02b9db8194439b08c9ab46f69c07ebe9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-15T21:01:37Z","title_canon_sha256":"903b6e64f70181e8c0a7a368e8b068dc73c6ec4ccff8a2308a2e91c21920d1f0"},"schema_version":"1.0","source":{"id":"2411.12591","kind":"arxiv","version":1}},"canonical_sha256":"da3defe7e88a59fdc51ab8543a79f6860d10e6ef032690e16b86a444d292a6fa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"da3defe7e88a59fdc51ab8543a79f6860d10e6ef032690e16b86a444d292a6fa","first_computed_at":"2026-07-05T09:37:45.378154Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:37:45.378154Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"czdun1GBRaHVb4VQ+u8y6+L//A5OPok0+po+MzoRji1XZbDrKAC4LxS5+EYcS8puXIyYOqwC73ViR3et5iwyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:37:45.378638Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.12591","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ebc8f9fbc4a798ff294b306f935462e27176a993c85e0057f4e82d35d579e247","sha256:55e565ee790472cccea4c1f562ab53099ca47c17eb451ca675efda376490f9d3"],"state_sha256":"2a23650357dbbefd6fd49a52334269fea891ca310324949414dc9e714dd78b1a"}