{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NJX4WB54LYUH6OOY3ZZCQRZ6UB","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":"2a8b94bb860a5f3060732e2c843c3c545e21616140973cf75edd90535d4f25b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T10:04:40Z","title_canon_sha256":"b7b266ddb74003f7666656ccc908c75b85f472cea9ffe0fc3018dd0c80f63218"},"schema_version":"1.0","source":{"id":"2410.20883","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.20883","created_at":"2026-07-05T09:29:34Z"},{"alias_kind":"arxiv_version","alias_value":"2410.20883v2","created_at":"2026-07-05T09:29:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.20883","created_at":"2026-07-05T09:29:34Z"},{"alias_kind":"pith_short_12","alias_value":"NJX4WB54LYUH","created_at":"2026-07-05T09:29:34Z"},{"alias_kind":"pith_short_16","alias_value":"NJX4WB54LYUH6OOY","created_at":"2026-07-05T09:29:34Z"},{"alias_kind":"pith_short_8","alias_value":"NJX4WB54","created_at":"2026-07-05T09:29:34Z"}],"graph_snapshots":[{"event_id":"sha256:954d26b5249485fa0c990253e3e342b500e6a1b6be4fbfbbbd168d4cf79514ab","target":"graph","created_at":"2026-07-05T09:29:34Z","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/2410.20883/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Anh-Tuan Quang-Hoang, Quang-Khai Tran, Tien-Huy Nguyen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T10:04:40Z","title":"Improving Generalization in Visual Reasoning via Self-Ensemble"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.20883","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":"sha256:5d52aa4c4a5a7e64e9042cf0816e5db263ada8422896cd1ff9a60f771eadc64d","target":"record","created_at":"2026-07-05T09:29:34Z","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":"2a8b94bb860a5f3060732e2c843c3c545e21616140973cf75edd90535d4f25b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-28T10:04:40Z","title_canon_sha256":"b7b266ddb74003f7666656ccc908c75b85f472cea9ffe0fc3018dd0c80f63218"},"schema_version":"1.0","source":{"id":"2410.20883","kind":"arxiv","version":2}},"canonical_sha256":"6a6fcb07bc5e287f39d8de7228473ea062ad013e153bfe7fe7e3cec2512db5e3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a6fcb07bc5e287f39d8de7228473ea062ad013e153bfe7fe7e3cec2512db5e3","first_computed_at":"2026-07-05T09:29:34.981410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:34.981410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uqxWjzS9ulFKGn6FMBqd6qUVCe0z73CSEc6MQ/uhjVhdsbkq30St1j7DFzANpOjDp6wXxkLico4pOIRPnOmDAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:34.981882Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.20883","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d52aa4c4a5a7e64e9042cf0816e5db263ada8422896cd1ff9a60f771eadc64d","sha256:954d26b5249485fa0c990253e3e342b500e6a1b6be4fbfbbbd168d4cf79514ab"],"state_sha256":"884ec6a73690b085413d717d6f8bf86566dd8a40236cb69b7cb60990d29a6d02"}