{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UCU4JFFC26WB3SVFRB7HIGHMQP","short_pith_number":"pith:UCU4JFFC","canonical_record":{"source":{"id":"2411.00394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T06:43:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"846efe6d0fc4cc0c19d9098d04b6984d63c02b17a055133285009e6a68fc8287","abstract_canon_sha256":"6e38ffe127b6ed8360b81baec5edbbeea5ccc5f74310f7f6b97ac9646152bd3c"},"schema_version":"1.0"},"canonical_sha256":"a0a9c494a2d7ac1dcaa5887e7418ec83f67a8e5600a620c0a7e54d1290870e82","source":{"kind":"arxiv","id":"2411.00394","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00394","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00394v1","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00394","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"pith_short_12","alias_value":"UCU4JFFC26WB","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"pith_short_16","alias_value":"UCU4JFFC26WB3SVF","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"pith_short_8","alias_value":"UCU4JFFC","created_at":"2026-07-05T09:29:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UCU4JFFC26WB3SVFRB7HIGHMQP","target":"record","payload":{"canonical_record":{"source":{"id":"2411.00394","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T06:43:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"846efe6d0fc4cc0c19d9098d04b6984d63c02b17a055133285009e6a68fc8287","abstract_canon_sha256":"6e38ffe127b6ed8360b81baec5edbbeea5ccc5f74310f7f6b97ac9646152bd3c"},"schema_version":"1.0"},"canonical_sha256":"a0a9c494a2d7ac1dcaa5887e7418ec83f67a8e5600a620c0a7e54d1290870e82","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:41.848193Z","signature_b64":"CtsPtlTnOkbyNilHW8pTX1UuMG3jHAAzerR5642nGFpHABZRjyGIzuDqdKMZ4f+NXzDOgVq1tpUjG4lbKRJ8BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0a9c494a2d7ac1dcaa5887e7418ec83f67a8e5600a620c0a7e54d1290870e82","last_reissued_at":"2026-07-05T09:29:41.847677Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:41.847677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.00394","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":"2026-07-05T09:29:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QK/5GxmKNgiJeiBKo1aoMiylW/0yekB72pimeI31PfF27R6Ug+/xXMB0D2Bp4QaI6VuaiqMryzk/rUurPcXfCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:35:20.088332Z"},"content_sha256":"f1b02a12f81090aa27527e25ea32b220fde9a23583945caf56189c43371fb0e5","schema_version":"1.0","event_id":"sha256:f1b02a12f81090aa27527e25ea32b220fde9a23583945caf56189c43371fb0e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UCU4JFFC26WB3SVFRB7HIGHMQP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Diji Yang, Kalyana Suma Sree Tholeti, Lei Ding, Leilani H. Gilpin, Li Liu, Sijia Zhong, Yi Zhang","submitted_at":"2024-11-01T06:43:54Z","abstract_excerpt":"In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models (VLMs) typically generate direct, one-shot responses without evaluating the sufficiency of the information. To investigate this gap, we identify a critical and challenging task in the Visual Question Answering (VQA) scenario: can VLMs indicate how to adjust an image when the visual information is insufficient to answer a question? This capability is especially valuable for assi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00394","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/2411.00394/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":"2026-07-05T09:29:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tCyrckLNEBEeYTNG1HgAUsR3r7B42pVFLY1G0wQ08sQW4rp/miQj8LoV6DoOUvrdfUO7fSM/IDob1hnKYpf8Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T02:35:20.088909Z"},"content_sha256":"5d4397c3c989c8f714102f767b3cb9c77e7f318deb5a622159c1881a896c4b35","schema_version":"1.0","event_id":"sha256:5d4397c3c989c8f714102f767b3cb9c77e7f318deb5a622159c1881a896c4b35"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UCU4JFFC26WB3SVFRB7HIGHMQP/bundle.json","state_url":"https://pith.science/pith/UCU4JFFC26WB3SVFRB7HIGHMQP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UCU4JFFC26WB3SVFRB7HIGHMQP/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":"2026-08-09T02:35:20Z","links":{"resolver":"https://pith.science/pith/UCU4JFFC26WB3SVFRB7HIGHMQP","bundle":"https://pith.science/pith/UCU4JFFC26WB3SVFRB7HIGHMQP/bundle.json","state":"https://pith.science/pith/UCU4JFFC26WB3SVFRB7HIGHMQP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UCU4JFFC26WB3SVFRB7HIGHMQP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UCU4JFFC26WB3SVFRB7HIGHMQP","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":"6e38ffe127b6ed8360b81baec5edbbeea5ccc5f74310f7f6b97ac9646152bd3c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T06:43:54Z","title_canon_sha256":"846efe6d0fc4cc0c19d9098d04b6984d63c02b17a055133285009e6a68fc8287"},"schema_version":"1.0","source":{"id":"2411.00394","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.00394","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"arxiv_version","alias_value":"2411.00394v1","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00394","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"pith_short_12","alias_value":"UCU4JFFC26WB","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"pith_short_16","alias_value":"UCU4JFFC26WB3SVF","created_at":"2026-07-05T09:29:41Z"},{"alias_kind":"pith_short_8","alias_value":"UCU4JFFC","created_at":"2026-07-05T09:29:41Z"}],"graph_snapshots":[{"event_id":"sha256:5d4397c3c989c8f714102f767b3cb9c77e7f318deb5a622159c1881a896c4b35","target":"graph","created_at":"2026-07-05T09:29:41Z","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/2411.00394/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In question-answering scenarios, humans can assess whether the available information is sufficient and seek additional information if necessary, rather than providing a forced answer. In contrast, Vision Language Models (VLMs) typically generate direct, one-shot responses without evaluating the sufficiency of the information. To investigate this gap, we identify a critical and challenging task in the Visual Question Answering (VQA) scenario: can VLMs indicate how to adjust an image when the visual information is insufficient to answer a question? This capability is especially valuable for assi","authors_text":"Diji Yang, Kalyana Suma Sree Tholeti, Lei Ding, Leilani H. Gilpin, Li Liu, Sijia Zhong, Yi Zhang","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T06:43:54Z","title":"Right this way: Can VLMs Guide Us to See More to Answer Questions?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00394","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:f1b02a12f81090aa27527e25ea32b220fde9a23583945caf56189c43371fb0e5","target":"record","created_at":"2026-07-05T09:29:41Z","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":"6e38ffe127b6ed8360b81baec5edbbeea5ccc5f74310f7f6b97ac9646152bd3c","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-01T06:43:54Z","title_canon_sha256":"846efe6d0fc4cc0c19d9098d04b6984d63c02b17a055133285009e6a68fc8287"},"schema_version":"1.0","source":{"id":"2411.00394","kind":"arxiv","version":1}},"canonical_sha256":"a0a9c494a2d7ac1dcaa5887e7418ec83f67a8e5600a620c0a7e54d1290870e82","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a0a9c494a2d7ac1dcaa5887e7418ec83f67a8e5600a620c0a7e54d1290870e82","first_computed_at":"2026-07-05T09:29:41.847677Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:41.847677Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CtsPtlTnOkbyNilHW8pTX1UuMG3jHAAzerR5642nGFpHABZRjyGIzuDqdKMZ4f+NXzDOgVq1tpUjG4lbKRJ8BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:41.848193Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.00394","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f1b02a12f81090aa27527e25ea32b220fde9a23583945caf56189c43371fb0e5","sha256:5d4397c3c989c8f714102f767b3cb9c77e7f318deb5a622159c1881a896c4b35"],"state_sha256":"6dee2bd5da56ec65fc030e4001f0120b9ffd5d1c97ec245afbf672210673b25c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DHT6+bRqSv8iw4d8iKzWwWKMNu56ZDMhFB7chW3vLS5PEz6ym6nKl201fkw5nxI6d9RH/UWaGdjtSMCCnnK6AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T02:35:20.093717Z","bundle_sha256":"7fcb611eaacb91985b304049c188c0fe46a415121fe0dcca897891da126ad3f2"}}