{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:JS4CBAAQ6OVGGJM7AAHRNIGQZW","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":"7154aa7670590138fbab061736d11d72363a84aefc7d6c75b9325b9d92f09d9e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T14:58:52Z","title_canon_sha256":"2ef6e313f42c5a710fbea7e9c66b94f55bb527442b1f4e5b903a642ef86b9758"},"schema_version":"1.0","source":{"id":"2403.07720","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07720","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07720v2","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07720","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"pith_short_12","alias_value":"JS4CBAAQ6OVG","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"pith_short_16","alias_value":"JS4CBAAQ6OVGGJM7","created_at":"2026-07-05T09:09:57Z"},{"alias_kind":"pith_short_8","alias_value":"JS4CBAAQ","created_at":"2026-07-05T09:09:57Z"}],"graph_snapshots":[{"event_id":"sha256:e18856b37437afaeedb6a07068bb8214d2fb4cf67ddd487b414c7112866f4da5","target":"graph","created_at":"2026-07-05T09:09:57Z","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/2403.07720/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs), benefiting from the auto-regressive modelling approach performed on massive unannotated texts corpora, demonstrates powerful perceptual and reasoning capabilities. However, as for extending auto-regressive modelling to multi-modal scenarios to build Large Multi-modal Models (LMMs), there lies a great difficulty that the image information is processed in the LMM as continuous visual embeddings, which cannot obtain discrete supervised labels for classification.In this paper, we successfully perform multi-modal auto-regressive modeling with a unified objective for th","authors_text":"Bo Du, Hai Zhao, Lefei Zhang, Ping Wang, Tianshuo Peng, Zuchao Li","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T14:58:52Z","title":"Multi-modal Auto-regressive Modeling via Visual Words"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07720","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":"sha256:29765942cfa8243e21758eecd939ef82543353e48126b0375e4cbad150895d26","target":"record","created_at":"2026-07-05T09:09:57Z","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":"7154aa7670590138fbab061736d11d72363a84aefc7d6c75b9325b9d92f09d9e","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T14:58:52Z","title_canon_sha256":"2ef6e313f42c5a710fbea7e9c66b94f55bb527442b1f4e5b903a642ef86b9758"},"schema_version":"1.0","source":{"id":"2403.07720","kind":"arxiv","version":2}},"canonical_sha256":"4cb8208010f3aa63259f000f16a0d0cdb23b2608c579789dae0a55ec83c3e53d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4cb8208010f3aa63259f000f16a0d0cdb23b2608c579789dae0a55ec83c3e53d","first_computed_at":"2026-07-05T09:09:57.126499Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:09:57.126499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zCm/YiCWPUIHylyIUgdkgjcmMj9xg06hZ4EKvereIexlvX/1PhYnWWOAb/oQ2Hq99DZZi5hs8l69y77OBr3HCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:09:57.127025Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07720","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29765942cfa8243e21758eecd939ef82543353e48126b0375e4cbad150895d26","sha256:e18856b37437afaeedb6a07068bb8214d2fb4cf67ddd487b414c7112866f4da5"],"state_sha256":"a7c3061b059017680103cf43cb401c612e06e034d95997711c32a145af7c1037"}