{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:DMXUVTN3XW245J6XSFNCRMTCB2","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":"5603168df2bca55186b27e8e502a50ee9f545952011f4e822bc8044ee6a55f5d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T08:12:00Z","title_canon_sha256":"a9a819c0d24ab16737dcb386cd9ce66c31e8336d5d6ae559f25ec80f29ffd139"},"schema_version":"1.0","source":{"id":"2405.16919","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.16919","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"arxiv_version","alias_value":"2405.16919v3","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.16919","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_12","alias_value":"DMXUVTN3XW24","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_16","alias_value":"DMXUVTN3XW245J6X","created_at":"2026-07-05T10:27:10Z"},{"alias_kind":"pith_short_8","alias_value":"DMXUVTN3","created_at":"2026-07-05T10:27:10Z"}],"graph_snapshots":[{"event_id":"sha256:b173a0e18d634a65b60c3e1d5adfbe854fb7d59bdfa2ac39c6121f06af451873","target":"graph","created_at":"2026-07-05T10:27:10Z","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/2405.16919/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Jiwen Zhang, Minghui Qiu, Ruipu Luo, Xuanjing Huang, Zejun Li, Zhongyu Wei","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T08:12:00Z","title":"VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.16919","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":"sha256:893315a3fc128d5656cccf89a1e8c8c44d3e1cc69c69710247a76226d0f1f7a7","target":"record","created_at":"2026-07-05T10:27:10Z","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":"5603168df2bca55186b27e8e502a50ee9f545952011f4e822bc8044ee6a55f5d","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-27T08:12:00Z","title_canon_sha256":"a9a819c0d24ab16737dcb386cd9ce66c31e8336d5d6ae559f25ec80f29ffd139"},"schema_version":"1.0","source":{"id":"2405.16919","kind":"arxiv","version":3}},"canonical_sha256":"1b2f4acdbbbdb5cea7d7915a28b2620ea47852b61b99b63b080ae4309b6e272f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b2f4acdbbbdb5cea7d7915a28b2620ea47852b61b99b63b080ae4309b6e272f","first_computed_at":"2026-07-05T10:27:10.468476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:27:10.468476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xeyHXZKHIHK5Vrccd7+cdCS7ibDBOkpr+TP/MI9DObvrl/SPgMi1uXKAFHlK3D+eG9u/lr8ZpbI9UG5tWRSFAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:27:10.469103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.16919","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:893315a3fc128d5656cccf89a1e8c8c44d3e1cc69c69710247a76226d0f1f7a7","sha256:b173a0e18d634a65b60c3e1d5adfbe854fb7d59bdfa2ac39c6121f06af451873"],"state_sha256":"3d8c1223b86761eb15306a7bb75ce609d06a3040d7cdc7055e89adb2592fc4ff"}