{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:V3LLMJETK5QJHSXLIBYESJEHTH","short_pith_number":"pith:V3LLMJET","schema_version":"1.0","canonical_sha256":"aed6b62493576093caeb407049248799fc2597996f78886250bb631392153768","source":{"kind":"arxiv","id":"2411.09439","version":2},"attestation_state":"computed","paper":{"title":"Spider: Any-to-Many Multimodal LLM","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Li, Jie Zhang, Jinxiang Lai, Jun Liu, Song Guo, Xiaocheng Lu","submitted_at":"2024-11-14T16:58:19Z","abstract_excerpt":"Multimodal LLMs (MLLMs) have emerged as an extension of Large Language Models (LLMs), enabling the integration of various modalities. However, Any-to-Any MLLMs are limited to generating pairwise modalities 'Text + X' within a single response, such as Text + {Image or Audio or Video}. To address this limitation, we introduce Spider, a novel efficient Any-to-Many Modalities Generation (AMMG) framework, which can generate an arbitrary combination of modalities 'Text + Xs', such as Text + {Image and Audio and Video}. To achieve efficient AMMG, our Spider integrates three core components: a Base Mo"},"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":"2411.09439","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-11-14T16:58:19Z","cross_cats_sorted":[],"title_canon_sha256":"a91c2e022d77394fd1fdc07cdfb2ac4d9f8dce1f9713867336c46f901e70204c","abstract_canon_sha256":"6383125eea5a9613a19d3e192f7717e5b839e0cac15a518d0126274cb8df6abc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:45:13.841811Z","signature_b64":"IiZzkG3i6WQ3nVoURqRXtv3oTAfR3UT4nGyWu94rrIIa6JADEIAT7lqDoGHuk2cP+vVwrWFCEJICWHxjdBbrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aed6b62493576093caeb407049248799fc2597996f78886250bb631392153768","last_reissued_at":"2026-07-05T10:45:13.841302Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:45:13.841302Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spider: Any-to-Many Multimodal LLM","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jian Li, Jie Zhang, Jinxiang Lai, Jun Liu, Song Guo, Xiaocheng Lu","submitted_at":"2024-11-14T16:58:19Z","abstract_excerpt":"Multimodal LLMs (MLLMs) have emerged as an extension of Large Language Models (LLMs), enabling the integration of various modalities. However, Any-to-Any MLLMs are limited to generating pairwise modalities 'Text + X' within a single response, such as Text + {Image or Audio or Video}. To address this limitation, we introduce Spider, a novel efficient Any-to-Many Modalities Generation (AMMG) framework, which can generate an arbitrary combination of modalities 'Text + Xs', such as Text + {Image and Audio and Video}. To achieve efficient AMMG, our Spider integrates three core components: a Base Mo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.09439","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/2411.09439/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":"2411.09439","created_at":"2026-07-05T10:45:13.841365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.09439v2","created_at":"2026-07-05T10:45:13.841365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.09439","created_at":"2026-07-05T10:45:13.841365+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3LLMJETK5QJ","created_at":"2026-07-05T10:45:13.841365+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3LLMJETK5QJHSXL","created_at":"2026-07-05T10:45:13.841365+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3LLMJET","created_at":"2026-07-05T10:45:13.841365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.10494","citing_title":"A Unified Multi-Agent Framework for Universal Multimodal Understanding and Generation","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V3LLMJETK5QJHSXLIBYESJEHTH","json":"https://pith.science/pith/V3LLMJETK5QJHSXLIBYESJEHTH.json","graph_json":"https://pith.science/api/pith-number/V3LLMJETK5QJHSXLIBYESJEHTH/graph.json","events_json":"https://pith.science/api/pith-number/V3LLMJETK5QJHSXLIBYESJEHTH/events.json","paper":"https://pith.science/paper/V3LLMJET"},"agent_actions":{"view_html":"https://pith.science/pith/V3LLMJETK5QJHSXLIBYESJEHTH","download_json":"https://pith.science/pith/V3LLMJETK5QJHSXLIBYESJEHTH.json","view_paper":"https://pith.science/paper/V3LLMJET","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.09439&json=true","fetch_graph":"https://pith.science/api/pith-number/V3LLMJETK5QJHSXLIBYESJEHTH/graph.json","fetch_events":"https://pith.science/api/pith-number/V3LLMJETK5QJHSXLIBYESJEHTH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3LLMJETK5QJHSXLIBYESJEHTH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3LLMJETK5QJHSXLIBYESJEHTH/action/storage_attestation","attest_author":"https://pith.science/pith/V3LLMJETK5QJHSXLIBYESJEHTH/action/author_attestation","sign_citation":"https://pith.science/pith/V3LLMJETK5QJHSXLIBYESJEHTH/action/citation_signature","submit_replication":"https://pith.science/pith/V3LLMJETK5QJHSXLIBYESJEHTH/action/replication_record"}},"created_at":"2026-07-05T10:45:13.841365+00:00","updated_at":"2026-07-05T10:45:13.841365+00:00"}