{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:UOOVP6KNB3N3PH6Q6NKB4P653J","short_pith_number":"pith:UOOVP6KN","schema_version":"1.0","canonical_sha256":"a39d57f94d0edbb79fd0f3541e3fddda713de0c62bb0e3d9d235df20a1976d1a","source":{"kind":"arxiv","id":"2107.14795","version":3},"attestation_state":"computed","paper":{"title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Perceiver IO adds a flexible querying mechanism to the Perceiver so one architecture processes arbitrary structured inputs and produces outputs of any size or type while scaling linearly.","cross_cats":["cs.CL","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Andrew Brock, Andrew Jaegle, Andrew Zisserman, Carl Doersch, Catalin Ionescu, Daniel Zoran, David Ding, Evan Shelhamer, Jean-Baptiste Alayrac, Jo\\=ao Carreira, Matthew M. Botvinick, Olivier H\\'enaff, Oriol Vinyals, Sebastian Borgeaud, Skanda Koppula","submitted_at":"2021-07-30T17:53:34Z","abstract_excerpt":"A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible. Current architectures, however, cannot be applied beyond a small set of stereotyped settings, as they bake in domain & task assumptions or scale poorly to large inputs or outputs. In this work, we propose Perceiver IO, a general-purpose architecture that handles data from arbitrary settings while scaling linearly with the size of inputs and outputs. Our model augments the Perceiver with a flexible querying mechanism that enables outputs of various sizes and semanti"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2107.14795","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-07-30T17:53:34Z","cross_cats_sorted":["cs.CL","cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"51e3957195f6b7855e23f45785d8f55e645d412b477cb4d44eb01f3219901580","abstract_canon_sha256":"c328ae9fb67839fb9efacc3ad0e9364bcf672c3b4a0802fcf8968ada843530e7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:50.367844Z","signature_b64":"SESehukw0mbbDbRxrzElronUko+joVfuLqsGcOWkLOpHEocMfT0uqrc5t7A33M2MmqX3bHE/+85lKFNLTW8fAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a39d57f94d0edbb79fd0f3541e3fddda713de0c62bb0e3d9d235df20a1976d1a","last_reissued_at":"2026-05-17T23:38:50.367308Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:50.367308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Perceiver IO: A General Architecture for Structured Inputs & Outputs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Perceiver IO adds a flexible querying mechanism to the Perceiver so one architecture processes arbitrary structured inputs and produces outputs of any size or type while scaling linearly.","cross_cats":["cs.CL","cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.LG","authors_text":"Andrew Brock, Andrew Jaegle, Andrew Zisserman, Carl Doersch, Catalin Ionescu, Daniel Zoran, David Ding, Evan Shelhamer, Jean-Baptiste Alayrac, Jo\\=ao Carreira, Matthew M. Botvinick, Olivier H\\'enaff, Oriol Vinyals, Sebastian Borgeaud, Skanda Koppula","submitted_at":"2021-07-30T17:53:34Z","abstract_excerpt":"A central goal of machine learning is the development of systems that can solve many problems in as many data domains as possible. Current architectures, however, cannot be applied beyond a small set of stereotyped settings, as they bake in domain & task assumptions or scale poorly to large inputs or outputs. In this work, we propose Perceiver IO, a general-purpose architecture that handles data from arbitrary settings while scaling linearly with the size of inputs and outputs. Our model augments the Perceiver with a flexible querying mechanism that enables outputs of various sizes and semanti"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The same architecture achieves strong results on tasks spanning natural language and visual understanding, multi-task and multi-modal reasoning, and StarCraft II. As highlights, Perceiver IO outperforms a Transformer-based BERT baseline on the GLUE language benchmark despite removing input tokenization and achieves state-of-the-art performance on Sintel optical flow estimation with no explicit mechanisms for multiscale correspondence.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the added flexible querying mechanism can produce outputs of arbitrary sizes and semantics across domains without introducing hidden task-specific assumptions or requiring per-task architectural changes that undermine the generality claim.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Perceiver IO is a general architecture that processes arbitrary structured inputs and outputs with linear scaling and achieves strong results on GLUE, Sintel optical flow, multi-task reasoning, and StarCraft II without task-specific components.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Perceiver IO adds a flexible querying mechanism to the Perceiver so one architecture processes arbitrary structured inputs and produces outputs of any size or type while scaling linearly.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"96f5fabd157d02586b1607250c9aec59ae2e9087dbfbf6f42b6bf819c6df6cf1"},"source":{"id":"2107.14795","kind":"arxiv","version":3},"verdict":{"id":"c6c19aed-5b3e-443d-8004-adc57417d892","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T19:43:58.764181Z","strongest_claim":"The same architecture achieves strong results on tasks spanning natural language and visual understanding, multi-task and multi-modal reasoning, and StarCraft II. As highlights, Perceiver IO outperforms a Transformer-based BERT baseline on the GLUE language benchmark despite removing input tokenization and achieves state-of-the-art performance on Sintel optical flow estimation with no explicit mechanisms for multiscale correspondence.","one_line_summary":"Perceiver IO is a general architecture that processes arbitrary structured inputs and outputs with linear scaling and achieves strong results on GLUE, Sintel optical flow, multi-task reasoning, and StarCraft II without task-specific components.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the added flexible querying mechanism can produce outputs of arbitrary sizes and semantics across domains without introducing hidden task-specific assumptions or requiring per-task architectural changes that undermine the generality claim.","pith_extraction_headline":"Perceiver IO adds a flexible querying mechanism to the Perceiver so one architecture processes arbitrary structured inputs and produces outputs of any size or type while scaling linearly."},"references":{"count":103,"sample":[{"doi":"","year":2012,"title":"Imitating interactive intelligence, 2021, 2012.05672 http://arxiv.org/abs/2012.05672","work_id":"993f94c8-0c91-4ae3-9f40-68c03b5723d3","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"VATT : Transformers for multimodal self-supervised learning from raw video, audio and text","work_id":"40471e6e-c402-41c0-9da0-b94ca27bc316","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"Self-supervised multimodal versatile networks","work_id":"222413c3-71e9-4e35-afe9-7d3cb141429e","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2020,"title":"The D eep M ind JAX E cosystem, 2020","work_id":"c47be3c1-be1b-4120-8234-644c5355e25f","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2004,"title":"Longformer: The Long-Document Transformer","work_id":"abea7a44-6668-4de7-aab6-f53a6e5aa088","ref_index":5,"cited_arxiv_id":"2004.05150","is_internal_anchor":true}],"resolved_work":103,"snapshot_sha256":"bc2a8846c668d4d21559628741d95fc4c8692ae1ee00a33e534a8bb0e002d42b","internal_anchors":7},"formal_canon":{"evidence_count":1,"snapshot_sha256":"83adb9dc241655ce4a3529e67ad4544ec9ccf4b3fb6fa1c1ee015b7a34a21465"},"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":"2107.14795","created_at":"2026-05-17T23:38:50.367418+00:00"},{"alias_kind":"arxiv_version","alias_value":"2107.14795v3","created_at":"2026-05-17T23:38:50.367418+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.14795","created_at":"2026-05-17T23:38:50.367418+00:00"},{"alias_kind":"pith_short_12","alias_value":"UOOVP6KNB3N3","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"UOOVP6KNB3N3PH6Q","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"UOOVP6KN","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":32,"internal_anchor_count":32,"sample":[{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2605.23712","citing_title":"Operator Learning for Reconstructing Flow Fields from Sparse Measurements: a Language Model Approach","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2504.06176","citing_title":"A Self-Supervised Framework for Space Object Behaviour Characterisation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2512.14692","citing_title":"Native and Compact Structured Latents for 3D Generation","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18816","citing_title":"Symmetry in the Wild: The Role of Equivariance in Neural Fluid Surrogates","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16411","citing_title":"Reducing Hallucination in Vision-Language Models via Stage-wise Preference Optimization under Distribution Shift","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17366","citing_title":"Text-Guided Visual Representation Learning for Robust Multimodal E-Commerce Recommendation","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2511.17171","citing_title":"FireScope: Wildfire Risk Raster Prediction with a Chain-of-Thought Oracle","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2601.22197","citing_title":"Neural Signals Generate Clinical Notes in the Wild","ref_index":3,"is_internal_anchor":true},{"citing_arxiv_id":"2602.00937","citing_title":"CLAMP: Contrastive Learning for 3D Multi-View Action-Conditioned Robotic Manipulation Pretraining","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2404.12377","citing_title":"RoboDreamer: Learning Compositional World Models for Robot Imagination","ref_index":75,"is_internal_anchor":true},{"citing_arxiv_id":"2602.22779","citing_title":"TrajTok: Learning Trajectory Tokens enables better Video Understanding","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13789","citing_title":"ENSEMBITS: an alphabet of protein conformational ensembles","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14594","citing_title":"TOPOS: High-Fidelity and Efficient Industry-Grade 3D Head Generation","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2405.17428","citing_title":"NV-Embed: Improved Techniques for Training LLMs as Generalist Embedding Models","ref_index":131,"is_internal_anchor":true},{"citing_arxiv_id":"2604.13986","citing_title":"PRiMeFlow: Capturing Complex Expression Heterogeneity in Perturbation Response Modelling","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13789","citing_title":"ENSEMBITS: an alphabet of protein conformational ensembles","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2205.06175","citing_title":"A Generalist Agent","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08744","citing_title":"MeshFIM: Local Low-Poly Mesh Editing via Fill-in-the-Middle Autoregressive Generation","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09630","citing_title":"Scratchpad Patching: Decoupling Compute from Patch Size in Byte-Level Language Models","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2112.10752","citing_title":"High-Resolution Image Synthesis with Latent Diffusion Models","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.04326","citing_title":"A foundation model of vision, audition, and language for in-silico neuroscience","ref_index":69,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00351","citing_title":"Hypergraph and Latent ODE Learning for Multimodal Root Cause Localization in Microservices","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18827","citing_title":"OmniMouse: Scaling properties of multi-modal, multi-task Brain Models on 150B Neural Tokens","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2405.09818","citing_title":"Chameleon: Mixed-Modal Early-Fusion Foundation Models","ref_index":12,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UOOVP6KNB3N3PH6Q6NKB4P653J","json":"https://pith.science/pith/UOOVP6KNB3N3PH6Q6NKB4P653J.json","graph_json":"https://pith.science/api/pith-number/UOOVP6KNB3N3PH6Q6NKB4P653J/graph.json","events_json":"https://pith.science/api/pith-number/UOOVP6KNB3N3PH6Q6NKB4P653J/events.json","paper":"https://pith.science/paper/UOOVP6KN"},"agent_actions":{"view_html":"https://pith.science/pith/UOOVP6KNB3N3PH6Q6NKB4P653J","download_json":"https://pith.science/pith/UOOVP6KNB3N3PH6Q6NKB4P653J.json","view_paper":"https://pith.science/paper/UOOVP6KN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2107.14795&json=true","fetch_graph":"https://pith.science/api/pith-number/UOOVP6KNB3N3PH6Q6NKB4P653J/graph.json","fetch_events":"https://pith.science/api/pith-number/UOOVP6KNB3N3PH6Q6NKB4P653J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UOOVP6KNB3N3PH6Q6NKB4P653J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UOOVP6KNB3N3PH6Q6NKB4P653J/action/storage_attestation","attest_author":"https://pith.science/pith/UOOVP6KNB3N3PH6Q6NKB4P653J/action/author_attestation","sign_citation":"https://pith.science/pith/UOOVP6KNB3N3PH6Q6NKB4P653J/action/citation_signature","submit_replication":"https://pith.science/pith/UOOVP6KNB3N3PH6Q6NKB4P653J/action/replication_record"}},"created_at":"2026-05-17T23:38:50.367418+00:00","updated_at":"2026-05-17T23:38:50.367418+00:00"}