{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JYY5WVNFWVEADDJVC74NKDKUJR","short_pith_number":"pith:JYY5WVNF","schema_version":"1.0","canonical_sha256":"4e31db55a5b548018d3517f8d50d544c769694ff6dcc58571cf27cb54696dc96","source":{"kind":"arxiv","id":"2608.03733","version":1},"attestation_state":"computed","paper":{"title":"Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chi-Min Chan, Chunyang Jiang, Mengyang Wu, Pingping Zhang, Senkang Hu, Sitong Cheng, Wei Xue, Wenao Ma, Yike Guo, Yiyang Cai, Yuzhi Zhao, Zhijian Hou","submitted_at":"2026-08-04T14:28:42Z","abstract_excerpt":"Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate. Self-augmentation offers a promising alternative by enabling models to expand their own training data without external supervision. However, existing MLLM self-augmentation methods are largely text-centric, while image augmentation remains underexplored and typically relies on generic or handcrafted transformations that are weakly aligned with the model's actual incapability. We 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":"2608.03733","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-04T14:28:42Z","cross_cats_sorted":[],"title_canon_sha256":"a866981be529d3e6012d3d439cc7580fecc49e1fb553ebbb8a3669e2e463d0d7","abstract_canon_sha256":"08861f5c1351741fd870639cf53cd2274df4e5f006c2602c02b4954a893f8012"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:36:58.879114Z","signature_b64":"pSrTsvYDbEhfhUh735HC9tZeTEaTpWzADPBl8/kkfQdYgTMMfsauBZoT9jwCzyvK2hVaedyB2Tax+Vq9CV4/Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4e31db55a5b548018d3517f8d50d544c769694ff6dcc58571cf27cb54696dc96","last_reissued_at":"2026-08-05T01:36:58.877345Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:36:58.877345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Failure-Informed Image Self-Augmentation for Multimodal Large Language Model Self-Improvement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chi-Min Chan, Chunyang Jiang, Mengyang Wu, Pingping Zhang, Senkang Hu, Sitong Cheng, Wei Xue, Wenao Ma, Yike Guo, Yiyang Cai, Yuzhi Zhao, Zhijian Hou","submitted_at":"2026-08-04T14:28:42Z","abstract_excerpt":"Multimodal large language models (MLLMs) have achieved remarkable performance across vision-language tasks, but their progress depends heavily on large-scale, high-quality multimodal data that are costly to annotate. Self-augmentation offers a promising alternative by enabling models to expand their own training data without external supervision. However, existing MLLM self-augmentation methods are largely text-centric, while image augmentation remains underexplored and typically relies on generic or handcrafted transformations that are weakly aligned with the model's actual incapability. We p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03733","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/2608.03733/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":"2608.03733","created_at":"2026-08-05T01:36:58.877999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03733v1","created_at":"2026-08-05T01:36:58.877999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03733","created_at":"2026-08-05T01:36:58.877999+00:00"},{"alias_kind":"pith_short_12","alias_value":"JYY5WVNFWVEA","created_at":"2026-08-05T01:36:58.877999+00:00"},{"alias_kind":"pith_short_16","alias_value":"JYY5WVNFWVEADDJV","created_at":"2026-08-05T01:36:58.877999+00:00"},{"alias_kind":"pith_short_8","alias_value":"JYY5WVNF","created_at":"2026-08-05T01:36:58.877999+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/JYY5WVNFWVEADDJVC74NKDKUJR","json":"https://pith.science/pith/JYY5WVNFWVEADDJVC74NKDKUJR.json","graph_json":"https://pith.science/api/pith-number/JYY5WVNFWVEADDJVC74NKDKUJR/graph.json","events_json":"https://pith.science/api/pith-number/JYY5WVNFWVEADDJVC74NKDKUJR/events.json","paper":"https://pith.science/paper/JYY5WVNF"},"agent_actions":{"view_html":"https://pith.science/pith/JYY5WVNFWVEADDJVC74NKDKUJR","download_json":"https://pith.science/pith/JYY5WVNFWVEADDJVC74NKDKUJR.json","view_paper":"https://pith.science/paper/JYY5WVNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03733&json=true","fetch_graph":"https://pith.science/api/pith-number/JYY5WVNFWVEADDJVC74NKDKUJR/graph.json","fetch_events":"https://pith.science/api/pith-number/JYY5WVNFWVEADDJVC74NKDKUJR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JYY5WVNFWVEADDJVC74NKDKUJR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JYY5WVNFWVEADDJVC74NKDKUJR/action/storage_attestation","attest_author":"https://pith.science/pith/JYY5WVNFWVEADDJVC74NKDKUJR/action/author_attestation","sign_citation":"https://pith.science/pith/JYY5WVNFWVEADDJVC74NKDKUJR/action/citation_signature","submit_replication":"https://pith.science/pith/JYY5WVNFWVEADDJVC74NKDKUJR/action/replication_record"}},"created_at":"2026-08-05T01:36:58.877999+00:00","updated_at":"2026-08-05T01:36:58.877999+00:00"}