{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CFGHH2PDSRPCEVKIXFF7GHELVQ","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":"cce8570cfb2a68b5474c82bb3f5d3b414ea6349a952cefdc7e6b99e86330349e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-24T17:37:05Z","title_canon_sha256":"4c608852344156e31ae672c30983e8aa4310e0874aaf5912fa03bd99f0fff31c"},"schema_version":"1.0","source":{"id":"2407.17453","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.17453","created_at":"2026-07-05T09:29:32Z"},{"alias_kind":"arxiv_version","alias_value":"2407.17453v2","created_at":"2026-07-05T09:29:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.17453","created_at":"2026-07-05T09:29:32Z"},{"alias_kind":"pith_short_12","alias_value":"CFGHH2PDSRPC","created_at":"2026-07-05T09:29:32Z"},{"alias_kind":"pith_short_16","alias_value":"CFGHH2PDSRPCEVKI","created_at":"2026-07-05T09:29:32Z"},{"alias_kind":"pith_short_8","alias_value":"CFGHH2PD","created_at":"2026-07-05T09:29:32Z"}],"graph_snapshots":[{"event_id":"sha256:f25717a86ca4549b67fcb98da196e6efc9a2c381011b850cffe9343abe9918ce","target":"graph","created_at":"2026-07-05T09:29:32Z","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/2407.17453/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While visual language model architectures and training infrastructures advance rapidly, data curation remains under-explored where quantity and quality become a bottleneck. Existing work either crawls extra Internet data with a loose guarantee of quality or distills from black-box proprietary models, e.g., GPT-4V / Gemini that are API frequency and performance bounded. This work enables a VLM to improve itself via data enhancement, exploiting its generative nature. We introduce a simple yet effective VLM augmentation scheme that includes a self-augment step and a specialist-augment step to ite","authors_text":"Hongxu Yin, Jang Hyun Cho, Jan Kautz, Ligeng Zhu, Marco Pavone, Pavlo Molchanov, Song Han, Yan Wang, Yao Lu, Yunhao Fang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-24T17:37:05Z","title":"VILA$^2$: VILA Augmented VILA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.17453","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":"sha256:11e2b101e5f66a1547af2efc4d036f536dcfaf5747a303e35d7f04f4475714ad","target":"record","created_at":"2026-07-05T09:29:32Z","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":"cce8570cfb2a68b5474c82bb3f5d3b414ea6349a952cefdc7e6b99e86330349e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-24T17:37:05Z","title_canon_sha256":"4c608852344156e31ae672c30983e8aa4310e0874aaf5912fa03bd99f0fff31c"},"schema_version":"1.0","source":{"id":"2407.17453","kind":"arxiv","version":2}},"canonical_sha256":"114c73e9e3945e225548b94bf31c8bac23f07ef85d22b3628273b2e43694b938","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"114c73e9e3945e225548b94bf31c8bac23f07ef85d22b3628273b2e43694b938","first_computed_at":"2026-07-05T09:29:32.026709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:29:32.026709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"d4JlqlW3vaSIjE8ku1qPC2QSANkOuYoR6uTLnyTNn7Dd7W1JNiO/K9Ds72BBoHLotsml+YiSH+gmmNKdplbfBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:29:32.027425Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.17453","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11e2b101e5f66a1547af2efc4d036f536dcfaf5747a303e35d7f04f4475714ad","sha256:f25717a86ca4549b67fcb98da196e6efc9a2c381011b850cffe9343abe9918ce"],"state_sha256":"c06fbc66f0b5c63dde6c441b40e4727d20fe9c8bd5e62fe37e66648c2db39197"}