{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NJX4WB54LYUH6OOY3ZZCQRZ6UB","short_pith_number":"pith:NJX4WB54","schema_version":"1.0","canonical_sha256":"6a6fcb07bc5e287f39d8de7228473ea062ad013e153bfe7fe7e3cec2512db5e3","source":{"kind":"arxiv","id":"2410.20883","version":2},"attestation_state":"computed","paper":{"title":"Improving Generalization in Visual Reasoning via Self-Ensemble","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh-Tuan Quang-Hoang, Quang-Khai Tran, Tien-Huy Nguyen","submitted_at":"2024-10-28T10:04:40Z","abstract_excerpt":"The cognitive faculty of visual reasoning necessitates the integration of multimodal perceptual processing and commonsense and external knowledge of the world. In recent years, a plethora of large vision-language models (LVLMs) have been proposed, demonstrating outstanding power and exceptional proficiency in commonsense reasoning across diverse domains and tasks. Nevertheless, training such LVLMs requires a lot of costly resources. Recent approaches, instead of training LVLMs from scratch on various large datasets, focus on exploring ways to take advantage of the capabilities of many differen"},"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":"2410.20883","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T10:04:40Z","cross_cats_sorted":[],"title_canon_sha256":"b7b266ddb74003f7666656ccc908c75b85f472cea9ffe0fc3018dd0c80f63218","abstract_canon_sha256":"2a8b94bb860a5f3060732e2c843c3c545e21616140973cf75edd90535d4f25b1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:29:34.981882Z","signature_b64":"uqxWjzS9ulFKGn6FMBqd6qUVCe0z73CSEc6MQ/uhjVhdsbkq30St1j7DFzANpOjDp6wXxkLico4pOIRPnOmDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a6fcb07bc5e287f39d8de7228473ea062ad013e153bfe7fe7e3cec2512db5e3","last_reissued_at":"2026-07-05T09:29:34.981410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:29:34.981410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Improving Generalization in Visual Reasoning via Self-Ensemble","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Anh-Tuan Quang-Hoang, Quang-Khai Tran, Tien-Huy Nguyen","submitted_at":"2024-10-28T10:04:40Z","abstract_excerpt":"The cognitive faculty of visual reasoning necessitates the integration of multimodal perceptual processing and commonsense and external knowledge of the world. In recent years, a plethora of large vision-language models (LVLMs) have been proposed, demonstrating outstanding power and exceptional proficiency in commonsense reasoning across diverse domains and tasks. Nevertheless, training such LVLMs requires a lot of costly resources. Recent approaches, instead of training LVLMs from scratch on various large datasets, focus on exploring ways to take advantage of the capabilities of many differen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20883","kind":"arxiv","version":2},"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/2410.20883/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":"2410.20883","created_at":"2026-07-05T09:29:34.981467+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.20883v2","created_at":"2026-07-05T09:29:34.981467+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20883","created_at":"2026-07-05T09:29:34.981467+00:00"},{"alias_kind":"pith_short_12","alias_value":"NJX4WB54LYUH","created_at":"2026-07-05T09:29:34.981467+00:00"},{"alias_kind":"pith_short_16","alias_value":"NJX4WB54LYUH6OOY","created_at":"2026-07-05T09:29:34.981467+00:00"},{"alias_kind":"pith_short_8","alias_value":"NJX4WB54","created_at":"2026-07-05T09:29:34.981467+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02089","citing_title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models","ref_index":61,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NJX4WB54LYUH6OOY3ZZCQRZ6UB","json":"https://pith.science/pith/NJX4WB54LYUH6OOY3ZZCQRZ6UB.json","graph_json":"https://pith.science/api/pith-number/NJX4WB54LYUH6OOY3ZZCQRZ6UB/graph.json","events_json":"https://pith.science/api/pith-number/NJX4WB54LYUH6OOY3ZZCQRZ6UB/events.json","paper":"https://pith.science/paper/NJX4WB54"},"agent_actions":{"view_html":"https://pith.science/pith/NJX4WB54LYUH6OOY3ZZCQRZ6UB","download_json":"https://pith.science/pith/NJX4WB54LYUH6OOY3ZZCQRZ6UB.json","view_paper":"https://pith.science/paper/NJX4WB54","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.20883&json=true","fetch_graph":"https://pith.science/api/pith-number/NJX4WB54LYUH6OOY3ZZCQRZ6UB/graph.json","fetch_events":"https://pith.science/api/pith-number/NJX4WB54LYUH6OOY3ZZCQRZ6UB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NJX4WB54LYUH6OOY3ZZCQRZ6UB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NJX4WB54LYUH6OOY3ZZCQRZ6UB/action/storage_attestation","attest_author":"https://pith.science/pith/NJX4WB54LYUH6OOY3ZZCQRZ6UB/action/author_attestation","sign_citation":"https://pith.science/pith/NJX4WB54LYUH6OOY3ZZCQRZ6UB/action/citation_signature","submit_replication":"https://pith.science/pith/NJX4WB54LYUH6OOY3ZZCQRZ6UB/action/replication_record"}},"created_at":"2026-07-05T09:29:34.981467+00:00","updated_at":"2026-07-05T09:29:34.981467+00:00"}