{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:44BFTXAJOQRINHXTHVSPZ4JJFP","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":"74da2e40eccdafd83aa5ae6a828154704a91bbd984663140d83c3edb64ea3ae2","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-16T00:46:29Z","title_canon_sha256":"3331b9d9854a1bfacc4cdde377b5a862dabc2d0518a09888d32eae32d11ee55d"},"schema_version":"1.0","source":{"id":"2401.08025","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.08025","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.08025v2","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.08025","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"pith_short_12","alias_value":"44BFTXAJOQRI","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"pith_short_16","alias_value":"44BFTXAJOQRINHXT","created_at":"2026-07-05T07:48:02Z"},{"alias_kind":"pith_short_8","alias_value":"44BFTXAJ","created_at":"2026-07-05T07:48:02Z"}],"graph_snapshots":[{"event_id":"sha256:cc3a5c17aa0c684eefcbad5735bc312f6d43e5b0dbb6972b7894a55468d746c8","target":"graph","created_at":"2026-07-05T07:48:02Z","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/2401.08025/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The potential of Vision-Language Models (VLMs) often remains underutilized in handling complex text-based problems, particularly when these problems could benefit from visual representation. Resonating with humans' ability to solve complex text-based problems by (1) creating a visual diagram from the problem and (2) deducing what steps they need to take to solve it, we propose Self-Imagine. We leverage a single Vision-Language Model (VLM) to generate a structured representation of the question using HTML, then render the HTML as an image, and finally use the same VLM to answer the question usi","authors_text":"Aman Madaan, Eric Nyberg, Sangwu Lee, Syeda Nahida Akter, Yiming Yang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-16T00:46:29Z","title":"Self-Imagine: Effective Unimodal Reasoning with Multimodal Models using Self-Imagination"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.08025","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:b175352df2616456d79a4ee16293bb35a86fc2d38978af95cc4be2bfb26f4ba1","target":"record","created_at":"2026-07-05T07:48:02Z","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":"74da2e40eccdafd83aa5ae6a828154704a91bbd984663140d83c3edb64ea3ae2","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-01-16T00:46:29Z","title_canon_sha256":"3331b9d9854a1bfacc4cdde377b5a862dabc2d0518a09888d32eae32d11ee55d"},"schema_version":"1.0","source":{"id":"2401.08025","kind":"arxiv","version":2}},"canonical_sha256":"e70259dc097422869ef33d64fcf1292be190feb705846b82da00ead95da225da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e70259dc097422869ef33d64fcf1292be190feb705846b82da00ead95da225da","first_computed_at":"2026-07-05T07:48:02.686184Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:48:02.686184Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vOcGsi6x7Nb8Tc3qMTiMN45pg37ZvnM1dVoBDtlN6tpnfkwp7SZIJvsSINvsokgODz4mPCjHkNhGajyqk82pDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:48:02.686748Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.08025","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b175352df2616456d79a4ee16293bb35a86fc2d38978af95cc4be2bfb26f4ba1","sha256:cc3a5c17aa0c684eefcbad5735bc312f6d43e5b0dbb6972b7894a55468d746c8"],"state_sha256":"58756fa8c74e414f79b42e0472cc6349c82a533f0c4f3e34300b51d0da7b54c3"}