{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MFMAXDZXE5FFWZJUEWD4EW5M4P","short_pith_number":"pith:MFMAXDZX","schema_version":"1.0","canonical_sha256":"61580b8f37274a5b65342587c25bace3df03292438a80a6dba33d1df22739ec3","source":{"kind":"arxiv","id":"2607.14099","version":1},"attestation_state":"computed","paper":{"title":"Just Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Bishoy Galoaa, Lorena Genua, Sarah Ostadabbas, Shayda Moezzi, Taskin Padir","submitted_at":"2026-05-01T17:02:19Z","abstract_excerpt":"Deploying Vision-Language Models (VLMs) in real-world settings requires not only strong visual reasoning but also stability under sustained conversational pressure. We introduce Just Keep Prompting (JKP), a multi-turn evaluation framework that measures VLM epistemic stability when users repeatedly challenge, question, or contradict a model's answer. JKP probes models for up to 10 follow-up turns using three strategies: Adversarial Negation (repeated rejection), Pure Socratic Interrogation (repeated calls to reassess certainty), and Context-Aware Socratic Summarization (reflecting the model's p"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2607.14099","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-01T17:02:19Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"74a1658dbcf4007e9e19f474f6beb2864fbd406b7a6eed2ad8706a49656d8af2","abstract_canon_sha256":"1dd2c520dffff0311715a82093d29042509c25d63f6d424b1b9497c45d93df9d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T00:20:52.041396Z","signature_b64":"UPS+YSK9CIWFNt+l6CpMXld9RPJRfDFEaiXzMF+Cl6lyxdspFsYNc+Jjm/fJZ4rwusCl1ejth1w6859sotURCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"61580b8f37274a5b65342587c25bace3df03292438a80a6dba33d1df22739ec3","last_reissued_at":"2026-07-17T00:20:52.040628Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T00:20:52.040628Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Just Keep Prompting: Evaluating Repetitive Socratic Prompting in VLMs","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.CL","authors_text":"Bishoy Galoaa, Lorena Genua, Sarah Ostadabbas, Shayda Moezzi, Taskin Padir","submitted_at":"2026-05-01T17:02:19Z","abstract_excerpt":"Deploying Vision-Language Models (VLMs) in real-world settings requires not only strong visual reasoning but also stability under sustained conversational pressure. We introduce Just Keep Prompting (JKP), a multi-turn evaluation framework that measures VLM epistemic stability when users repeatedly challenge, question, or contradict a model's answer. JKP probes models for up to 10 follow-up turns using three strategies: Adversarial Negation (repeated rejection), Pure Socratic Interrogation (repeated calls to reassess certainty), and Context-Aware Socratic Summarization (reflecting the model's p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.14099","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/2607.14099/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2607.14099","created_at":"2026-07-17T00:20:52.041006+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.14099v1","created_at":"2026-07-17T00:20:52.041006+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.14099","created_at":"2026-07-17T00:20:52.041006+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFMAXDZXE5FF","created_at":"2026-07-17T00:20:52.041006+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFMAXDZXE5FFWZJU","created_at":"2026-07-17T00:20:52.041006+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFMAXDZX","created_at":"2026-07-17T00:20:52.041006+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFMAXDZXE5FFWZJUEWD4EW5M4P","json":"https://pith.science/pith/MFMAXDZXE5FFWZJUEWD4EW5M4P.json","graph_json":"https://pith.science/api/pith-number/MFMAXDZXE5FFWZJUEWD4EW5M4P/graph.json","events_json":"https://pith.science/api/pith-number/MFMAXDZXE5FFWZJUEWD4EW5M4P/events.json","paper":"https://pith.science/paper/MFMAXDZX"},"agent_actions":{"view_html":"https://pith.science/pith/MFMAXDZXE5FFWZJUEWD4EW5M4P","download_json":"https://pith.science/pith/MFMAXDZXE5FFWZJUEWD4EW5M4P.json","view_paper":"https://pith.science/paper/MFMAXDZX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.14099&json=true","fetch_graph":"https://pith.science/api/pith-number/MFMAXDZXE5FFWZJUEWD4EW5M4P/graph.json","fetch_events":"https://pith.science/api/pith-number/MFMAXDZXE5FFWZJUEWD4EW5M4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFMAXDZXE5FFWZJUEWD4EW5M4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFMAXDZXE5FFWZJUEWD4EW5M4P/action/storage_attestation","attest_author":"https://pith.science/pith/MFMAXDZXE5FFWZJUEWD4EW5M4P/action/author_attestation","sign_citation":"https://pith.science/pith/MFMAXDZXE5FFWZJUEWD4EW5M4P/action/citation_signature","submit_replication":"https://pith.science/pith/MFMAXDZXE5FFWZJUEWD4EW5M4P/action/replication_record"}},"created_at":"2026-07-17T00:20:52.041006+00:00","updated_at":"2026-07-17T00:20:52.041006+00:00"}