{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VCHEE3M72EMLXDP6BS6XRTPM4F","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":"b2bb74e343baa3ec5de9937014342f70a91be7f8f8985d577cdcb9758cde64d9","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T02:16:35Z","title_canon_sha256":"bcd6b421fc3e6ccab52b5925012bd75272351053104af96766b0dbd3b3c4148c"},"schema_version":"1.0","source":{"id":"2501.18096","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18096","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18096v1","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18096","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"pith_short_12","alias_value":"VCHEE3M72EML","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"pith_short_16","alias_value":"VCHEE3M72EMLXDP6","created_at":"2026-07-05T10:07:06Z"},{"alias_kind":"pith_short_8","alias_value":"VCHEE3M7","created_at":"2026-07-05T10:07:06Z"}],"graph_snapshots":[{"event_id":"sha256:fffdb8ab743f041fe8975c32e65188ef4c3b4a61f820cad94f0987290ad3a76a","target":"graph","created_at":"2026-07-05T10:07:06Z","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/2501.18096/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present MILS: Multimodal Iterative LLM Solver, a surprisingly simple, training-free approach, to imbue multimodal capabilities into your favorite LLM. Leveraging their innate ability to perform multi-step reasoning, MILS prompts the LLM to generate candidate outputs, each of which are scored and fed back iteratively, eventually generating a solution to the task. This enables various applications that typically require training specialized models on task-specific data. In particular, we establish a new state-of-the-art on emergent zero-shot image, video and audio captioning. MILS seamlessly ","authors_text":"Ishan Misra, Kumar Ashutosh, Rohit Girdhar, Xinlei Chen, Yossi Gandelsman","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T02:16:35Z","title":"LLMs can see and hear without any training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18096","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:b0e0ab0f1ed7db566a362b07623615c60be5857b2e5fe6619dce123cffed7aea","target":"record","created_at":"2026-07-05T10:07:06Z","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":"b2bb74e343baa3ec5de9937014342f70a91be7f8f8985d577cdcb9758cde64d9","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-30T02:16:35Z","title_canon_sha256":"bcd6b421fc3e6ccab52b5925012bd75272351053104af96766b0dbd3b3c4148c"},"schema_version":"1.0","source":{"id":"2501.18096","kind":"arxiv","version":1}},"canonical_sha256":"a88e426d9fd118bb8dfe0cbd78cdece17791709132953930893245620c56f97e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a88e426d9fd118bb8dfe0cbd78cdece17791709132953930893245620c56f97e","first_computed_at":"2026-07-05T10:07:06.971750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:07:06.971750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvHKWDdz1J3/tpUKFzOgLhGczJyvwDpZ0posMms9Bx5RSMDiZgkon+qZ1KccpgrJ4CXHP1+ZBzaRFWgW18VRCA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:07:06.972196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18096","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b0e0ab0f1ed7db566a362b07623615c60be5857b2e5fe6619dce123cffed7aea","sha256:fffdb8ab743f041fe8975c32e65188ef4c3b4a61f820cad94f0987290ad3a76a"],"state_sha256":"7a9789b47da38e6b70e11ae74ae4c740f1fe3a468a41c269fde441e74fd9e3e4"}