{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JS4CBAAQ6OVGGJM7AAHRNIGQZW","short_pith_number":"pith:JS4CBAAQ","schema_version":"1.0","canonical_sha256":"4cb8208010f3aa63259f000f16a0d0cdb23b2608c579789dae0a55ec83c3e53d","source":{"kind":"arxiv","id":"2403.07720","version":2},"attestation_state":"computed","paper":{"title":"Multi-modal Auto-regressive Modeling via Visual Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Du, Hai Zhao, Lefei Zhang, Ping Wang, Tianshuo Peng, Zuchao Li","submitted_at":"2024-03-12T14:58:52Z","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"},"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":"2403.07720","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-03-12T14:58:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ef6e313f42c5a710fbea7e9c66b94f55bb527442b1f4e5b903a642ef86b9758","abstract_canon_sha256":"7154aa7670590138fbab061736d11d72363a84aefc7d6c75b9325b9d92f09d9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:09:57.127025Z","signature_b64":"zCm/YiCWPUIHylyIUgdkgjcmMj9xg06hZ4EKvereIexlvX/1PhYnWWOAb/oQ2Hq99DZZi5hs8l69y77OBr3HCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4cb8208010f3aa63259f000f16a0d0cdb23b2608c579789dae0a55ec83c3e53d","last_reissued_at":"2026-07-05T09:09:57.126499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:09:57.126499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multi-modal Auto-regressive Modeling via Visual Words","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Bo Du, Hai Zhao, Lefei Zhang, Ping Wang, Tianshuo Peng, Zuchao Li","submitted_at":"2024-03-12T14:58:52Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07720","kind":"arxiv","version":2},"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/2403.07720/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":"2403.07720","created_at":"2026-07-05T09:09:57.126560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.07720v2","created_at":"2026-07-05T09:09:57.126560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07720","created_at":"2026-07-05T09:09:57.126560+00:00"},{"alias_kind":"pith_short_12","alias_value":"JS4CBAAQ6OVG","created_at":"2026-07-05T09:09:57.126560+00:00"},{"alias_kind":"pith_short_16","alias_value":"JS4CBAAQ6OVGGJM7","created_at":"2026-07-05T09:09:57.126560+00:00"},{"alias_kind":"pith_short_8","alias_value":"JS4CBAAQ","created_at":"2026-07-05T09:09:57.126560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06895","citing_title":"BASIC: Boosting Visual Alignment with Intrinsic Refined Embeddings in Multimodal Large Language Models","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JS4CBAAQ6OVGGJM7AAHRNIGQZW","json":"https://pith.science/pith/JS4CBAAQ6OVGGJM7AAHRNIGQZW.json","graph_json":"https://pith.science/api/pith-number/JS4CBAAQ6OVGGJM7AAHRNIGQZW/graph.json","events_json":"https://pith.science/api/pith-number/JS4CBAAQ6OVGGJM7AAHRNIGQZW/events.json","paper":"https://pith.science/paper/JS4CBAAQ"},"agent_actions":{"view_html":"https://pith.science/pith/JS4CBAAQ6OVGGJM7AAHRNIGQZW","download_json":"https://pith.science/pith/JS4CBAAQ6OVGGJM7AAHRNIGQZW.json","view_paper":"https://pith.science/paper/JS4CBAAQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.07720&json=true","fetch_graph":"https://pith.science/api/pith-number/JS4CBAAQ6OVGGJM7AAHRNIGQZW/graph.json","fetch_events":"https://pith.science/api/pith-number/JS4CBAAQ6OVGGJM7AAHRNIGQZW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JS4CBAAQ6OVGGJM7AAHRNIGQZW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JS4CBAAQ6OVGGJM7AAHRNIGQZW/action/storage_attestation","attest_author":"https://pith.science/pith/JS4CBAAQ6OVGGJM7AAHRNIGQZW/action/author_attestation","sign_citation":"https://pith.science/pith/JS4CBAAQ6OVGGJM7AAHRNIGQZW/action/citation_signature","submit_replication":"https://pith.science/pith/JS4CBAAQ6OVGGJM7AAHRNIGQZW/action/replication_record"}},"created_at":"2026-07-05T09:09:57.126560+00:00","updated_at":"2026-07-05T09:09:57.126560+00:00"}