{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:OTJSW2M5IXDQDNEMI5SVU2PI2K","short_pith_number":"pith:OTJSW2M5","schema_version":"1.0","canonical_sha256":"74d32b699d45c701b48c47655a69e8d29147bf5922d42dab96b9b22892026013","source":{"kind":"arxiv","id":"2206.06336","version":1},"attestation_state":"computed","paper":{"title":"Language Models are General-Purpose Interfaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Haoyu Song, Li Dong, Shaohan Huang, Shuming Ma, Wenhui Wang, Yaru Hao, Zewen Chi","submitted_at":"2022-06-13T17:34:22Z","abstract_excerpt":"Foundation models have received much attention due to their effectiveness across a broad range of downstream applications. Though there is a big convergence in terms of architecture, most pretrained models are typically still developed for specific tasks or modalities. In this work, we propose to use language models as a general-purpose interface to various foundation models. A collection of pretrained encoders perceive diverse modalities (such as vision, and language), and they dock with a language model that plays the role of a universal task layer. We propose a semi-causal language modeling"},"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":"2206.06336","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-06-13T17:34:22Z","cross_cats_sorted":[],"title_canon_sha256":"40bd8454094caa9abc96f0699f40fd9bb5bb70f82208ffc48f7b8ef91a29ba62","abstract_canon_sha256":"1a44e93bd45a385f0655ae89294dada10de0d1ddb6e745a5afe10eb9b3eb7e3f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:31:18.157041Z","signature_b64":"BFraOHZFJgfi91o5NROBY+NMr2qrVTpIpFRibGQvfaXIG/YQkzWpg/zkPF4U3sGdJePFia1i4thZqtDBImi1Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"74d32b699d45c701b48c47655a69e8d29147bf5922d42dab96b9b22892026013","last_reissued_at":"2026-07-05T04:31:18.156422Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:31:18.156422Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Language Models are General-Purpose Interfaces","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Furu Wei, Haoyu Song, Li Dong, Shaohan Huang, Shuming Ma, Wenhui Wang, Yaru Hao, Zewen Chi","submitted_at":"2022-06-13T17:34:22Z","abstract_excerpt":"Foundation models have received much attention due to their effectiveness across a broad range of downstream applications. Though there is a big convergence in terms of architecture, most pretrained models are typically still developed for specific tasks or modalities. In this work, we propose to use language models as a general-purpose interface to various foundation models. A collection of pretrained encoders perceive diverse modalities (such as vision, and language), and they dock with a language model that plays the role of a universal task layer. We propose a semi-causal language modeling"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.06336","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/2206.06336/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":"2206.06336","created_at":"2026-07-05T04:31:18.156511+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.06336v1","created_at":"2026-07-05T04:31:18.156511+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.06336","created_at":"2026-07-05T04:31:18.156511+00:00"},{"alias_kind":"pith_short_12","alias_value":"OTJSW2M5IXDQ","created_at":"2026-07-05T04:31:18.156511+00:00"},{"alias_kind":"pith_short_16","alias_value":"OTJSW2M5IXDQDNEM","created_at":"2026-07-05T04:31:18.156511+00:00"},{"alias_kind":"pith_short_8","alias_value":"OTJSW2M5","created_at":"2026-07-05T04:31:18.156511+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07861","citing_title":"The Last Visible Pixel: Probing Fine-Scale Perception in Vision-Language Models","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2302.14045","citing_title":"Language Is Not All You Need: Aligning Perception with Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2306.14824","citing_title":"Kosmos-2: Grounding Multimodal Large Language Models to the World","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2307.08621","citing_title":"Retentive Network: A Successor to Transformer for Large Language Models","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2402.06196","citing_title":"Large Language Models: A Survey","ref_index":104,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07379","citing_title":"RELO: Reinforcement Learning to Localize for Visual Object Tracking","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2303.03378","citing_title":"PaLM-E: An Embodied Multimodal Language Model","ref_index":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OTJSW2M5IXDQDNEMI5SVU2PI2K","json":"https://pith.science/pith/OTJSW2M5IXDQDNEMI5SVU2PI2K.json","graph_json":"https://pith.science/api/pith-number/OTJSW2M5IXDQDNEMI5SVU2PI2K/graph.json","events_json":"https://pith.science/api/pith-number/OTJSW2M5IXDQDNEMI5SVU2PI2K/events.json","paper":"https://pith.science/paper/OTJSW2M5"},"agent_actions":{"view_html":"https://pith.science/pith/OTJSW2M5IXDQDNEMI5SVU2PI2K","download_json":"https://pith.science/pith/OTJSW2M5IXDQDNEMI5SVU2PI2K.json","view_paper":"https://pith.science/paper/OTJSW2M5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.06336&json=true","fetch_graph":"https://pith.science/api/pith-number/OTJSW2M5IXDQDNEMI5SVU2PI2K/graph.json","fetch_events":"https://pith.science/api/pith-number/OTJSW2M5IXDQDNEMI5SVU2PI2K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OTJSW2M5IXDQDNEMI5SVU2PI2K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OTJSW2M5IXDQDNEMI5SVU2PI2K/action/storage_attestation","attest_author":"https://pith.science/pith/OTJSW2M5IXDQDNEMI5SVU2PI2K/action/author_attestation","sign_citation":"https://pith.science/pith/OTJSW2M5IXDQDNEMI5SVU2PI2K/action/citation_signature","submit_replication":"https://pith.science/pith/OTJSW2M5IXDQDNEMI5SVU2PI2K/action/replication_record"}},"created_at":"2026-07-05T04:31:18.156511+00:00","updated_at":"2026-07-05T04:31:18.156511+00:00"}