{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DMXUVTN3XW245J6XSFNCRMTCB2","short_pith_number":"pith:DMXUVTN3","schema_version":"1.0","canonical_sha256":"1b2f4acdbbbdb5cea7d7915a28b2620ea47852b61b99b63b080ae4309b6e272f","source":{"kind":"arxiv","id":"2405.16919","version":3},"attestation_state":"computed","paper":{"title":"VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiwen Zhang, Minghui Qiu, Ruipu Luo, Xuanjing Huang, Zejun Li, Zhongyu Wei","submitted_at":"2024-05-27T08:12:00Z","abstract_excerpt":"While large multi-modal models (LMMs) have exhibited impressive capabilities across diverse tasks, their effectiveness in handling complex tasks has been limited by the prevailing single-step reasoning paradigm. To this end, this paper proposes VoCoT, a multi-step Visually grounded object-centric Chain-of-Thought reasoning framework tailored for inference with LMMs. VoCoT is characterized by two key features: (1) object-centric reasoning paths that revolve around cross-modal shared object-level information, and (2) visually grounded representation of object concepts in a multi-modal interleave"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2405.16919","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T08:12:00Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"a9a819c0d24ab16737dcb386cd9ce66c31e8336d5d6ae559f25ec80f29ffd139","abstract_canon_sha256":"5603168df2bca55186b27e8e502a50ee9f545952011f4e822bc8044ee6a55f5d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:27:10.469103Z","signature_b64":"xeyHXZKHIHK5Vrccd7+cdCS7ibDBOkpr+TP/MI9DObvrl/SPgMi1uXKAFHlK3D+eG9u/lr8ZpbI9UG5tWRSFAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1b2f4acdbbbdb5cea7d7915a28b2620ea47852b61b99b63b080ae4309b6e272f","last_reissued_at":"2026-07-05T10:27:10.468476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:27:10.468476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jiwen Zhang, Minghui Qiu, Ruipu Luo, Xuanjing Huang, Zejun Li, Zhongyu Wei","submitted_at":"2024-05-27T08:12:00Z","abstract_excerpt":"While large multi-modal models (LMMs) have exhibited impressive capabilities across diverse tasks, their effectiveness in handling complex tasks has been limited by the prevailing single-step reasoning paradigm. To this end, this paper proposes VoCoT, a multi-step Visually grounded object-centric Chain-of-Thought reasoning framework tailored for inference with LMMs. VoCoT is characterized by two key features: (1) object-centric reasoning paths that revolve around cross-modal shared object-level information, and (2) visually grounded representation of object concepts in a multi-modal interleave"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16919","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/2405.16919/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2405.16919","created_at":"2026-07-05T10:27:10.468545+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.16919v3","created_at":"2026-07-05T10:27:10.468545+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16919","created_at":"2026-07-05T10:27:10.468545+00:00"},{"alias_kind":"pith_short_12","alias_value":"DMXUVTN3XW24","created_at":"2026-07-05T10:27:10.468545+00:00"},{"alias_kind":"pith_short_16","alias_value":"DMXUVTN3XW245J6X","created_at":"2026-07-05T10:27:10.468545+00:00"},{"alias_kind":"pith_short_8","alias_value":"DMXUVTN3","created_at":"2026-07-05T10:27:10.468545+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.26196","citing_title":"From Structure to Synergy: A Survey of Vision-Language Perception Paradigm Evolution in Multimodal Large Language Models","ref_index":134,"is_internal_anchor":false},{"citing_arxiv_id":"2505.23678","citing_title":"Grounded Reinforcement Learning for Visual Reasoning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2509.22746","citing_title":"Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DMXUVTN3XW245J6XSFNCRMTCB2","json":"https://pith.science/pith/DMXUVTN3XW245J6XSFNCRMTCB2.json","graph_json":"https://pith.science/api/pith-number/DMXUVTN3XW245J6XSFNCRMTCB2/graph.json","events_json":"https://pith.science/api/pith-number/DMXUVTN3XW245J6XSFNCRMTCB2/events.json","paper":"https://pith.science/paper/DMXUVTN3"},"agent_actions":{"view_html":"https://pith.science/pith/DMXUVTN3XW245J6XSFNCRMTCB2","download_json":"https://pith.science/pith/DMXUVTN3XW245J6XSFNCRMTCB2.json","view_paper":"https://pith.science/paper/DMXUVTN3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.16919&json=true","fetch_graph":"https://pith.science/api/pith-number/DMXUVTN3XW245J6XSFNCRMTCB2/graph.json","fetch_events":"https://pith.science/api/pith-number/DMXUVTN3XW245J6XSFNCRMTCB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DMXUVTN3XW245J6XSFNCRMTCB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DMXUVTN3XW245J6XSFNCRMTCB2/action/storage_attestation","attest_author":"https://pith.science/pith/DMXUVTN3XW245J6XSFNCRMTCB2/action/author_attestation","sign_citation":"https://pith.science/pith/DMXUVTN3XW245J6XSFNCRMTCB2/action/citation_signature","submit_replication":"https://pith.science/pith/DMXUVTN3XW245J6XSFNCRMTCB2/action/replication_record"}},"created_at":"2026-07-05T10:27:10.468545+00:00","updated_at":"2026-07-05T10:27:10.468545+00:00"}