{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OYDDQXYVTKFSPNTF4SAMHXYQYP","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":"90dfbb23500e66606c04217c8adc1b94d273937c729ab70917fdb27a347ff806","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-12T09:58:16Z","title_canon_sha256":"5d4388d409930e3f8fc96c02b615cce4281af6e4808e03cc377bbdb73d4b6e80"},"schema_version":"1.0","source":{"id":"2311.06791","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.06791","created_at":"2026-07-05T07:20:55Z"},{"alias_kind":"arxiv_version","alias_value":"2311.06791v2","created_at":"2026-07-05T07:20:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06791","created_at":"2026-07-05T07:20:55Z"},{"alias_kind":"pith_short_12","alias_value":"OYDDQXYVTKFS","created_at":"2026-07-05T07:20:55Z"},{"alias_kind":"pith_short_16","alias_value":"OYDDQXYVTKFSPNTF","created_at":"2026-07-05T07:20:55Z"},{"alias_kind":"pith_short_8","alias_value":"OYDDQXYV","created_at":"2026-07-05T07:20:55Z"}],"graph_snapshots":[{"event_id":"sha256:cbfc96dc8b248f6cabce0f28155c99a17a29480aad1d2bd5c95e21d039dcbe41","target":"graph","created_at":"2026-07-05T07:20:55Z","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/2311.06791/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have proven their remarkable versatility in handling a comprehensive range of language-centric applications. To expand LLMs' capabilities to a broader spectrum of modal inputs, multimodal large language models (MLLMs) have attracted growing interest. This work delves into enabling LLMs to tackle more vision-language-related tasks, particularly image captioning, visual question answering (VQA,) and visual grounding. To this end, we implemented a three-stage training scheme: starting with lightweight alignment pretraining, then moderate-weight multitask hybrid traini","authors_text":"Hao Li, Qiang Zhou, Wei Chu, Yinghui Xu, Yuan Qi, Zhibin Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-12T09:58:16Z","title":"InfMLLM: A Unified Framework for Visual-Language Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06791","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":"sha256:892e5d0d2273660962377df30115ee0eebb9d55443fc51b8ab58cd1e65682604","target":"record","created_at":"2026-07-05T07:20:55Z","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":"90dfbb23500e66606c04217c8adc1b94d273937c729ab70917fdb27a347ff806","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-11-12T09:58:16Z","title_canon_sha256":"5d4388d409930e3f8fc96c02b615cce4281af6e4808e03cc377bbdb73d4b6e80"},"schema_version":"1.0","source":{"id":"2311.06791","kind":"arxiv","version":2}},"canonical_sha256":"7606385f159a8b27b665e480c3df10c3ce11a79cd865d6123e0113fd2a8690a1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7606385f159a8b27b665e480c3df10c3ce11a79cd865d6123e0113fd2a8690a1","first_computed_at":"2026-07-05T07:20:55.108663Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:20:55.108663Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Des8sRd5PIHstFU76F/odtlI0MVyE/ze6nP7ikXqxByYREsr496e07PAsqR0HR69SHbYMbSuJi45PwgafZYAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:20:55.109142Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.06791","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:892e5d0d2273660962377df30115ee0eebb9d55443fc51b8ab58cd1e65682604","sha256:cbfc96dc8b248f6cabce0f28155c99a17a29480aad1d2bd5c95e21d039dcbe41"],"state_sha256":"ed8350dba470d250c10b3a248be83f70e90e9bdf4be9bb3d818361f3a647a2bd"}