{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QM3YSB6RVXIGN6ACWEIDN66QJA","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":"414aea8cd130c28301b895eba5427aeca246b21d4eba3adf4abb6e66fb1b5af3","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T16:57:57Z","title_canon_sha256":"a2b1f8bc1103df688ec2428a4b06c252d8799fce256eb9050b695be26712ad98"},"schema_version":"1.0","source":{"id":"2310.05861","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.05861","created_at":"2026-07-05T08:03:27Z"},{"alias_kind":"arxiv_version","alias_value":"2310.05861v2","created_at":"2026-07-05T08:03:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.05861","created_at":"2026-07-05T08:03:27Z"},{"alias_kind":"pith_short_12","alias_value":"QM3YSB6RVXIG","created_at":"2026-07-05T08:03:27Z"},{"alias_kind":"pith_short_16","alias_value":"QM3YSB6RVXIGN6AC","created_at":"2026-07-05T08:03:27Z"},{"alias_kind":"pith_short_8","alias_value":"QM3YSB6R","created_at":"2026-07-05T08:03:27Z"}],"graph_snapshots":[{"event_id":"sha256:9726a27edb8f46fc6b0415ad5aafbbe1cbc02519071b14c6e7b9188d2a5f7fa0","target":"graph","created_at":"2026-07-05T08:03:27Z","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/2310.05861/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An increasing number of vision-language tasks can be handled with little to no training, i.e., in a zero and few-shot manner, by marrying large language models (LLMs) to vision encoders, resulting in large vision-language models (LVLMs). While this has huge upsides, such as not requiring training data or custom architectures, how an input is presented to an LVLM can have a major impact on zero-shot model performance. In particular, inputs phrased in an underspecified way can result in incorrect answers due to factors like missing visual information, complex implicit reasoning, or linguistic am","authors_text":"Archiki Prasad, Elias Stengel-Eskin, Mohit Bansal","cross_cats":["cs.AI","cs.CV","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T16:57:57Z","title":"Rephrase, Augment, Reason: Visual Grounding of Questions for Vision-Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.05861","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:b68720e4df9cc7835dffb84d2fdb115701364a3672d2268eb9e434320b8cc1a4","target":"record","created_at":"2026-07-05T08:03:27Z","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":"414aea8cd130c28301b895eba5427aeca246b21d4eba3adf4abb6e66fb1b5af3","cross_cats_sorted":["cs.AI","cs.CV","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-09T16:57:57Z","title_canon_sha256":"a2b1f8bc1103df688ec2428a4b06c252d8799fce256eb9050b695be26712ad98"},"schema_version":"1.0","source":{"id":"2310.05861","kind":"arxiv","version":2}},"canonical_sha256":"83378907d1add066f802b11036fbd0481f7473ac77fed2c79a5f60b17c321916","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"83378907d1add066f802b11036fbd0481f7473ac77fed2c79a5f60b17c321916","first_computed_at":"2026-07-05T08:03:27.162760Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:27.162760Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"msuvqffiIO8XGrRznG+J2qNLM3LH/yK/DZuUXaZtyHHu1xVgfBdhjLwq+CF0VVN9R1ixW17UEYceHKLIouJ7Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:27.163205Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.05861","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b68720e4df9cc7835dffb84d2fdb115701364a3672d2268eb9e434320b8cc1a4","sha256:9726a27edb8f46fc6b0415ad5aafbbe1cbc02519071b14c6e7b9188d2a5f7fa0"],"state_sha256":"6491c1fb852cc264675f6ba3e5c486478b58bab3b23cde4fc748659de0f1e553"}