{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CM43XZS6BBLCJCL32JUPZEC6QA","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":"7c713254ebd4b8e8dba3d984d03e3508216ae246cc41371557b23cbd75e88b5a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T10:19:57Z","title_canon_sha256":"b7112ce4a41ba1d057d86d38f383b1c09813cd177ca04ecdb16fcc76f91acaaa"},"schema_version":"1.0","source":{"id":"2305.14985","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.14985","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"arxiv_version","alias_value":"2305.14985v3","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.14985","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"pith_short_12","alias_value":"CM43XZS6BBLC","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"pith_short_16","alias_value":"CM43XZS6BBLCJCL3","created_at":"2026-06-19T16:12:12Z"},{"alias_kind":"pith_short_8","alias_value":"CM43XZS6","created_at":"2026-06-19T16:12:12Z"}],"graph_snapshots":[{"event_id":"sha256:43c959d8485f9f10e90728611579970c11e3bf910c8faac61cb6120dc3eeeb79","target":"graph","created_at":"2026-06-19T16:12:12Z","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/2305.14985/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The field of vision-and-language (VL) understanding has made unprecedented progress with end-to-end large pre-trained VL models (VLMs). However, they still fall short in zero-shot reasoning tasks that require multi-step inferencing. To achieve this goal, previous works resort to a divide-and-conquer pipeline. In this paper, we argue that previous efforts have several inherent shortcomings: 1) They rely on domain-specific sub-question decomposing models. 2) They force models to predict the final answer even if the sub-questions or sub-answers provide insufficient information. We address these l","authors_text":"Gengyu Wang, Hammad A. Ayyubi, Haoxuan You, Kai-Wei Chang, Long Chen, Rui Sun, Shih-Fu Chang, Zhecan Wang","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T10:19:57Z","title":"IdealGPT: Iteratively Decomposing Vision and Language Reasoning via Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.14985","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":"sha256:8bdf1d3ac3bdfc3ad0835d08f37b821b621e597d7f0e3da12a24b9fcf76c97ba","target":"record","created_at":"2026-06-19T16:12:12Z","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":"7c713254ebd4b8e8dba3d984d03e3508216ae246cc41371557b23cbd75e88b5a","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-24T10:19:57Z","title_canon_sha256":"b7112ce4a41ba1d057d86d38f383b1c09813cd177ca04ecdb16fcc76f91acaaa"},"schema_version":"1.0","source":{"id":"2305.14985","kind":"arxiv","version":3}},"canonical_sha256":"1339bbe65e085624897bd268fc905e8029c4411b2e895f639b1b6afd6effb7c6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1339bbe65e085624897bd268fc905e8029c4411b2e895f639b1b6afd6effb7c6","first_computed_at":"2026-06-19T16:12:12.257733Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:12.257733Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"T8S1w3AeaUkiF1F/yyuLwIuyGoahfz9Nu0lwXuN4YhLuR02s+LDNiUby63q+PvJkFAEuY+z97nBL0qIvGTFFAw==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:12.258169Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.14985","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8bdf1d3ac3bdfc3ad0835d08f37b821b621e597d7f0e3da12a24b9fcf76c97ba","sha256:43c959d8485f9f10e90728611579970c11e3bf910c8faac61cb6120dc3eeeb79"],"state_sha256":"f788fff9a4ad3408cf16301b5dc052a5a10724b37413bc6c87da7f8fcd6da162"}