{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NUDHDQENULAVL7RUJFSXRHKI66","short_pith_number":"pith:NUDHDQEN","canonical_record":{"source":{"id":"2503.12799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T04:07:47Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"d7f5e3be1507ccf15d66d2257c7dfd6d73d5fa949543e7ccfa832ed087802d45","abstract_canon_sha256":"4ecee4a0b89b392990c9d0d25df53169f73bb897523c720107862da8cda02169"},"schema_version":"1.0"},"canonical_sha256":"6d0671c08da2c155fe344965789d48f78c118af11a67f99002121ab4b8dd133b","source":{"kind":"arxiv","id":"2503.12799","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12799","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12799v2","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12799","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_12","alias_value":"NUDHDQENULAV","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_16","alias_value":"NUDHDQENULAVL7RU","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_8","alias_value":"NUDHDQEN","created_at":"2026-07-05T10:37:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NUDHDQENULAVL7RUJFSXRHKI66","target":"record","payload":{"canonical_record":{"source":{"id":"2503.12799","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T04:07:47Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"d7f5e3be1507ccf15d66d2257c7dfd6d73d5fa949543e7ccfa832ed087802d45","abstract_canon_sha256":"4ecee4a0b89b392990c9d0d25df53169f73bb897523c720107862da8cda02169"},"schema_version":"1.0"},"canonical_sha256":"6d0671c08da2c155fe344965789d48f78c118af11a67f99002121ab4b8dd133b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:47.613065Z","signature_b64":"IQsOMS3MKv95ZLjuca09s++M9fx1cgSRaVnej5cCbGLET+oPwwzvYnsjrMI+sex5BGFM1jJAM0XAywpTYX8NDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6d0671c08da2c155fe344965789d48f78c118af11a67f99002121ab4b8dd133b","last_reissued_at":"2026-07-05T10:37:47.612560Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:47.612560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2503.12799","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:37:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XEkqJCOrJMVggPr/2CxzH59Wi1orL+xJsElynDqQSCWfS0+JMYZjycVoURxvSWDCHn5YGcF9GE3pe7dH101rDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T12:08:08.412768Z"},"content_sha256":"bc5598d01490907b5f904f2e83f16756e0fa52c7797469462b8594305b546a66","schema_version":"1.0","event_id":"sha256:bc5598d01490907b5f904f2e83f16756e0fa52c7797469462b8594305b546a66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NUDHDQENULAVL7RUJFSXRHKI66","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Grounded Chain-of-Thought for Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"cs.CV","authors_text":"Baiyang Song, Chenxin Fang, Qiong Wu, Rongrong Ji, Xiangcong Yang, Xiaoshuai Sun, Yiyi Zhou","submitted_at":"2025-03-17T04:07:47Z","abstract_excerpt":"Despite great progress, existing multimodal large language models (MLLMs) are prone to visual hallucination, greatly impeding their trustworthy applications. In this paper, we study this problem from the perspective of visual-spatial reasoning, and propose a new learning task for MLLMs, termed Grounded Chain-of-Thought (GCoT). Different from recent visual CoT studies, which focus more on visual knowledge reasoning, GCoT is keen to helping MLLMs to recognize and ground the relevant visual cues step by step, thereby predicting the correct answer with grounding coordinates as the intuitive basis."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12799","kind":"arxiv","version":2},"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/2503.12799/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":"2026-07-05T10:37:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O+CELwjlx7VE3QzgrTTMKtyfF2TwKereO2FSdELgQ2YYrzuNvRMyKV/c1WPuoPfXL7lzdNKY9OmYzIjl665xDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-23T12:08:08.413147Z"},"content_sha256":"3a8c0312e5347aa59bd9606406e17108e1d05cd6c53b3a1d4034eb1a6c5f5c38","schema_version":"1.0","event_id":"sha256:3a8c0312e5347aa59bd9606406e17108e1d05cd6c53b3a1d4034eb1a6c5f5c38"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NUDHDQENULAVL7RUJFSXRHKI66/bundle.json","state_url":"https://pith.science/pith/NUDHDQENULAVL7RUJFSXRHKI66/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NUDHDQENULAVL7RUJFSXRHKI66/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":"2026-07-23T12:08:08Z","links":{"resolver":"https://pith.science/pith/NUDHDQENULAVL7RUJFSXRHKI66","bundle":"https://pith.science/pith/NUDHDQENULAVL7RUJFSXRHKI66/bundle.json","state":"https://pith.science/pith/NUDHDQENULAVL7RUJFSXRHKI66/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NUDHDQENULAVL7RUJFSXRHKI66/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NUDHDQENULAVL7RUJFSXRHKI66","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":"4ecee4a0b89b392990c9d0d25df53169f73bb897523c720107862da8cda02169","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T04:07:47Z","title_canon_sha256":"d7f5e3be1507ccf15d66d2257c7dfd6d73d5fa949543e7ccfa832ed087802d45"},"schema_version":"1.0","source":{"id":"2503.12799","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.12799","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"arxiv_version","alias_value":"2503.12799v2","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.12799","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_12","alias_value":"NUDHDQENULAV","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_16","alias_value":"NUDHDQENULAVL7RU","created_at":"2026-07-05T10:37:47Z"},{"alias_kind":"pith_short_8","alias_value":"NUDHDQEN","created_at":"2026-07-05T10:37:47Z"}],"graph_snapshots":[{"event_id":"sha256:3a8c0312e5347aa59bd9606406e17108e1d05cd6c53b3a1d4034eb1a6c5f5c38","target":"graph","created_at":"2026-07-05T10:37:47Z","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/2503.12799/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite great progress, existing multimodal large language models (MLLMs) are prone to visual hallucination, greatly impeding their trustworthy applications. In this paper, we study this problem from the perspective of visual-spatial reasoning, and propose a new learning task for MLLMs, termed Grounded Chain-of-Thought (GCoT). Different from recent visual CoT studies, which focus more on visual knowledge reasoning, GCoT is keen to helping MLLMs to recognize and ground the relevant visual cues step by step, thereby predicting the correct answer with grounding coordinates as the intuitive basis.","authors_text":"Baiyang Song, Chenxin Fang, Qiong Wu, Rongrong Ji, Xiangcong Yang, Xiaoshuai Sun, Yiyi Zhou","cross_cats":["cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T04:07:47Z","title":"Grounded Chain-of-Thought for Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.12799","kind":"arxiv","version":2},"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:bc5598d01490907b5f904f2e83f16756e0fa52c7797469462b8594305b546a66","target":"record","created_at":"2026-07-05T10:37:47Z","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":"4ecee4a0b89b392990c9d0d25df53169f73bb897523c720107862da8cda02169","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-17T04:07:47Z","title_canon_sha256":"d7f5e3be1507ccf15d66d2257c7dfd6d73d5fa949543e7ccfa832ed087802d45"},"schema_version":"1.0","source":{"id":"2503.12799","kind":"arxiv","version":2}},"canonical_sha256":"6d0671c08da2c155fe344965789d48f78c118af11a67f99002121ab4b8dd133b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6d0671c08da2c155fe344965789d48f78c118af11a67f99002121ab4b8dd133b","first_computed_at":"2026-07-05T10:37:47.612560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:37:47.612560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IQsOMS3MKv95ZLjuca09s++M9fx1cgSRaVnej5cCbGLET+oPwwzvYnsjrMI+sex5BGFM1jJAM0XAywpTYX8NDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:37:47.613065Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.12799","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc5598d01490907b5f904f2e83f16756e0fa52c7797469462b8594305b546a66","sha256:3a8c0312e5347aa59bd9606406e17108e1d05cd6c53b3a1d4034eb1a6c5f5c38"],"state_sha256":"19176963052582150636cd4a48acf13c4e7089c14f49ff691fb9edbe140708cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"L5M/u6z3DvOncvU1CRrqMnOMpKOqsLRlZ8Z70CkrmDxO46VHp89YstLcbOistH+Ixc/Vq2JMfGENhl6/fHUpDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-23T12:08:08.415349Z","bundle_sha256":"8f325c9f7684754b492b905090d820aceeced4501b6e6fe37032511e557c1275"}}