{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4PDIW66BXJF72QDEKIBQR2ENXC","short_pith_number":"pith:4PDIW66B","canonical_record":{"source":{"id":"2310.15166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T17:59:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ada1188a305cd229198a2cff933cc6c96244a5ef35a17faa028180dcdf9ec9d2","abstract_canon_sha256":"cc1696ac49376c111b0896351c326da3884e8ea0be5c84578579127bb3ddb9c7"},"schema_version":"1.0"},"canonical_sha256":"e3c68b7bc1ba4bfd4064520308e88db8ad846953ac99de91ed95dfee4ed483df","source":{"kind":"arxiv","id":"2310.15166","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15166","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15166v1","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15166","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"4PDIW66BXJF7","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"4PDIW66BXJF72QDE","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"4PDIW66B","created_at":"2026-07-05T07:04:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4PDIW66BXJF72QDEKIBQR2ENXC","target":"record","payload":{"canonical_record":{"source":{"id":"2310.15166","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T17:59:31Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ada1188a305cd229198a2cff933cc6c96244a5ef35a17faa028180dcdf9ec9d2","abstract_canon_sha256":"cc1696ac49376c111b0896351c326da3884e8ea0be5c84578579127bb3ddb9c7"},"schema_version":"1.0"},"canonical_sha256":"e3c68b7bc1ba4bfd4064520308e88db8ad846953ac99de91ed95dfee4ed483df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:06.963221Z","signature_b64":"YMNd70h+bJas/CCu6dj89XQDTl4r7Bw5jUw/4qKgOfdrFtekeVIUlWA1KLhcEcr2VgOIgkbCEDNEwlW9x8mQDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3c68b7bc1ba4bfd4064520308e88db8ad846953ac99de91ed95dfee4ed483df","last_reissued_at":"2026-07-05T07:04:06.962704Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:06.962704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.15166","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":"2026-07-05T07:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T3c5FRbAp3RgCWwUfAMxN7aCq4N6HRol5QL0AmlA57e6A9fb4ONJZ6GYez/f+4MpGymNyY4U9/Z32LboOK/MCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:54:51.711559Z"},"content_sha256":"f810966116080b50c22113065693e94dee35f07cca74f45b742514e87300dcdf","schema_version":"1.0","event_id":"sha256:f810966116080b50c22113065693e94dee35f07cca74f45b742514e87300dcdf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4PDIW66BXJF72QDEKIBQR2ENXC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large Language Models are Visual Reasoning Coordinators","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Li, Chunyuan Li, Jingkang Yang, Kurt Keutzer, Liangyu Chen, Sheng Shen, Trevor Darrell, Ziwei Liu","submitted_at":"2023-10-23T17:59:31Z","abstract_excerpt":"Visual reasoning requires multimodal perception and commonsense cognition of the world. Recently, multiple vision-language models (VLMs) have been proposed with excellent commonsense reasoning ability in various domains. However, how to harness the collective power of these complementary VLMs is rarely explored. Existing methods like ensemble still struggle to aggregate these models with the desired higher-order communications. In this work, we propose Cola, a novel paradigm that coordinates multiple VLMs for visual reasoning. Our key insight is that a large language model (LLM) can efficientl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15166","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/2310.15166/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":"2026-07-05T07:04:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KZjzLpIAGmipJidciqc+2nQqCcJ5bblh8ytnAuC/fNN7XISIwZvErjvQweTrdsNEWNTgfPQzHdwGNndx9gYkAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T16:54:51.712166Z"},"content_sha256":"c66feb77a9839f2e62f3bb2667943fe8f30f81956fd23ca8608a78ffcbe04992","schema_version":"1.0","event_id":"sha256:c66feb77a9839f2e62f3bb2667943fe8f30f81956fd23ca8608a78ffcbe04992"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4PDIW66BXJF72QDEKIBQR2ENXC/bundle.json","state_url":"https://pith.science/pith/4PDIW66BXJF72QDEKIBQR2ENXC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4PDIW66BXJF72QDEKIBQR2ENXC/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":"2026-08-03T16:54:51Z","links":{"resolver":"https://pith.science/pith/4PDIW66BXJF72QDEKIBQR2ENXC","bundle":"https://pith.science/pith/4PDIW66BXJF72QDEKIBQR2ENXC/bundle.json","state":"https://pith.science/pith/4PDIW66BXJF72QDEKIBQR2ENXC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4PDIW66BXJF72QDEKIBQR2ENXC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4PDIW66BXJF72QDEKIBQR2ENXC","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":"cc1696ac49376c111b0896351c326da3884e8ea0be5c84578579127bb3ddb9c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T17:59:31Z","title_canon_sha256":"ada1188a305cd229198a2cff933cc6c96244a5ef35a17faa028180dcdf9ec9d2"},"schema_version":"1.0","source":{"id":"2310.15166","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.15166","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"arxiv_version","alias_value":"2310.15166v1","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.15166","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"pith_short_12","alias_value":"4PDIW66BXJF7","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"pith_short_16","alias_value":"4PDIW66BXJF72QDE","created_at":"2026-07-05T07:04:06Z"},{"alias_kind":"pith_short_8","alias_value":"4PDIW66B","created_at":"2026-07-05T07:04:06Z"}],"graph_snapshots":[{"event_id":"sha256:c66feb77a9839f2e62f3bb2667943fe8f30f81956fd23ca8608a78ffcbe04992","target":"graph","created_at":"2026-07-05T07:04:06Z","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/2310.15166/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual reasoning requires multimodal perception and commonsense cognition of the world. Recently, multiple vision-language models (VLMs) have been proposed with excellent commonsense reasoning ability in various domains. However, how to harness the collective power of these complementary VLMs is rarely explored. Existing methods like ensemble still struggle to aggregate these models with the desired higher-order communications. In this work, we propose Cola, a novel paradigm that coordinates multiple VLMs for visual reasoning. Our key insight is that a large language model (LLM) can efficientl","authors_text":"Bo Li, Chunyuan Li, Jingkang Yang, Kurt Keutzer, Liangyu Chen, Sheng Shen, Trevor Darrell, Ziwei Liu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T17:59:31Z","title":"Large Language Models are Visual Reasoning Coordinators"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.15166","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:f810966116080b50c22113065693e94dee35f07cca74f45b742514e87300dcdf","target":"record","created_at":"2026-07-05T07:04:06Z","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":"cc1696ac49376c111b0896351c326da3884e8ea0be5c84578579127bb3ddb9c7","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-23T17:59:31Z","title_canon_sha256":"ada1188a305cd229198a2cff933cc6c96244a5ef35a17faa028180dcdf9ec9d2"},"schema_version":"1.0","source":{"id":"2310.15166","kind":"arxiv","version":1}},"canonical_sha256":"e3c68b7bc1ba4bfd4064520308e88db8ad846953ac99de91ed95dfee4ed483df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3c68b7bc1ba4bfd4064520308e88db8ad846953ac99de91ed95dfee4ed483df","first_computed_at":"2026-07-05T07:04:06.962704Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:06.962704Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YMNd70h+bJas/CCu6dj89XQDTl4r7Bw5jUw/4qKgOfdrFtekeVIUlWA1KLhcEcr2VgOIgkbCEDNEwlW9x8mQDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:06.963221Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.15166","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f810966116080b50c22113065693e94dee35f07cca74f45b742514e87300dcdf","sha256:c66feb77a9839f2e62f3bb2667943fe8f30f81956fd23ca8608a78ffcbe04992"],"state_sha256":"77c9de66678d744707d631611113fe90ef83e454e0b696ba0e87cf6541176def"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DOzrT10h6fbGy1iCIHKAkhg267JOS0zvKjIL+VQsS3yprOnhzzC8ltUk5ZrvslGflIS6GfULlELhQ/XQSJ45Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T16:54:51.717337Z","bundle_sha256":"77162e62ef4d4ea86d7e8cbef0d0ab5c8e59e9f9426d582334a89b61e27f42b8"}}