{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UTVJ22VF25P25U22MRZNXRX2AA","short_pith_number":"pith:UTVJ22VF","schema_version":"1.0","canonical_sha256":"a4ea9d6aa5d75faed35a6472dbc6fa0037b9ba8d4d92e3f86872a762ef0ead09","source":{"kind":"arxiv","id":"2605.27885","version":1},"attestation_state":"computed","paper":{"title":"Reflective Dialogue between Teacher and Solver Agents for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Takuya Murakawa, Toru Tamaki","submitted_at":"2026-05-27T03:08:12Z","abstract_excerpt":"Various approaches have been proposed to adapt Vision-Language Models (VLMs) to specialized domains for Video Question Answering, including fine-tuning and in-context learning. However, acquiring task-specific knowledge at the inference phase from only a small labeled support set without fine-tuning remains a challenge. In this paper, we propose a method that achieves adaptation solely through inference-time context injection. Our method first constructs a Reflective Dialogue (RD) -- a multi-turn conversation between two agents, in which Teacher poses each support question and delivers correct"},"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":"2605.27885","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-27T03:08:12Z","cross_cats_sorted":[],"title_canon_sha256":"19d558850c23ef7ba660ed97770eadf0781603391c5cee1a0fafa48b4b66a5f7","abstract_canon_sha256":"02592911cb3d352ffd467925a8b6fe408e8cf38efcc1a9d28585e9d79d0e1689"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:04:51.234960Z","signature_b64":"FPvqiW9wrDOnWR5asPnj9+EozYL2oEwHVeQoCYLE9SkK2gNpPVtAMi26pNSfzbK3YwS3AzOWqS7X87IMl2aNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a4ea9d6aa5d75faed35a6472dbc6fa0037b9ba8d4d92e3f86872a762ef0ead09","last_reissued_at":"2026-05-28T01:04:51.234572Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:04:51.234572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reflective Dialogue between Teacher and Solver Agents for Video Question Answering","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Takuya Murakawa, Toru Tamaki","submitted_at":"2026-05-27T03:08:12Z","abstract_excerpt":"Various approaches have been proposed to adapt Vision-Language Models (VLMs) to specialized domains for Video Question Answering, including fine-tuning and in-context learning. However, acquiring task-specific knowledge at the inference phase from only a small labeled support set without fine-tuning remains a challenge. In this paper, we propose a method that achieves adaptation solely through inference-time context injection. Our method first constructs a Reflective Dialogue (RD) -- a multi-turn conversation between two agents, in which Teacher poses each support question and delivers correct"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27885","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/2605.27885/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":"2605.27885","created_at":"2026-05-28T01:04:51.234629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27885v1","created_at":"2026-05-28T01:04:51.234629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27885","created_at":"2026-05-28T01:04:51.234629+00:00"},{"alias_kind":"pith_short_12","alias_value":"UTVJ22VF25P2","created_at":"2026-05-28T01:04:51.234629+00:00"},{"alias_kind":"pith_short_16","alias_value":"UTVJ22VF25P25U22","created_at":"2026-05-28T01:04:51.234629+00:00"},{"alias_kind":"pith_short_8","alias_value":"UTVJ22VF","created_at":"2026-05-28T01:04:51.234629+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/UTVJ22VF25P25U22MRZNXRX2AA","json":"https://pith.science/pith/UTVJ22VF25P25U22MRZNXRX2AA.json","graph_json":"https://pith.science/api/pith-number/UTVJ22VF25P25U22MRZNXRX2AA/graph.json","events_json":"https://pith.science/api/pith-number/UTVJ22VF25P25U22MRZNXRX2AA/events.json","paper":"https://pith.science/paper/UTVJ22VF"},"agent_actions":{"view_html":"https://pith.science/pith/UTVJ22VF25P25U22MRZNXRX2AA","download_json":"https://pith.science/pith/UTVJ22VF25P25U22MRZNXRX2AA.json","view_paper":"https://pith.science/paper/UTVJ22VF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27885&json=true","fetch_graph":"https://pith.science/api/pith-number/UTVJ22VF25P25U22MRZNXRX2AA/graph.json","fetch_events":"https://pith.science/api/pith-number/UTVJ22VF25P25U22MRZNXRX2AA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UTVJ22VF25P25U22MRZNXRX2AA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UTVJ22VF25P25U22MRZNXRX2AA/action/storage_attestation","attest_author":"https://pith.science/pith/UTVJ22VF25P25U22MRZNXRX2AA/action/author_attestation","sign_citation":"https://pith.science/pith/UTVJ22VF25P25U22MRZNXRX2AA/action/citation_signature","submit_replication":"https://pith.science/pith/UTVJ22VF25P25U22MRZNXRX2AA/action/replication_record"}},"created_at":"2026-05-28T01:04:51.234629+00:00","updated_at":"2026-05-28T01:04:51.234629+00:00"}