{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:WCLCKU62QUO7DGEQO4FBLEPEIB","short_pith_number":"pith:WCLCKU62","schema_version":"1.0","canonical_sha256":"b0962553da851df19890770a1591e440697180c3bf7c67d188fae1f3e02f16ad","source":{"kind":"arxiv","id":"1912.12180","version":1},"attestation_state":"computed","paper":{"title":"Axial Attention in Multidimensional Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dirk Weissenborn, Jonathan Ho, Nal Kalchbrenner, Tim Salimans","submitted_at":"2019-12-20T13:27:27Z","abstract_excerpt":"We propose Axial Transformers, a self-attention-based autoregressive model for images and other data organized as high dimensional tensors. Existing autoregressive models either suffer from excessively large computational resource requirements for high dimensional data, or make compromises in terms of distribution expressiveness or ease of implementation in order to decrease resource requirements. Our architecture, by contrast, maintains both full expressiveness over joint distributions over data and ease of implementation with standard deep learning frameworks, while requiring reasonable memo"},"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":"1912.12180","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2019-12-20T13:27:27Z","cross_cats_sorted":[],"title_canon_sha256":"e56303efc8b9a6704ab6cf810ac5eb9ef0fd4b64b0545307cb9dbc35b189bef9","abstract_canon_sha256":"244154dc53ae231ced6f0f3a384ebb71728a414a514c896f294bb2a9bdf3a97d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:28:41.153263Z","signature_b64":"DSCmfy6YsT29oXFhKP+AMHUIWOqWu/tYqgv/iH4FoJ/luc+O3val/vHPW/dbvxou2ZVjaRPK6rVNBRphSVMyAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b0962553da851df19890770a1591e440697180c3bf7c67d188fae1f3e02f16ad","last_reissued_at":"2026-07-05T00:28:41.152853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:28:41.152853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Axial Attention in Multidimensional Transformers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dirk Weissenborn, Jonathan Ho, Nal Kalchbrenner, Tim Salimans","submitted_at":"2019-12-20T13:27:27Z","abstract_excerpt":"We propose Axial Transformers, a self-attention-based autoregressive model for images and other data organized as high dimensional tensors. Existing autoregressive models either suffer from excessively large computational resource requirements for high dimensional data, or make compromises in terms of distribution expressiveness or ease of implementation in order to decrease resource requirements. Our architecture, by contrast, maintains both full expressiveness over joint distributions over data and ease of implementation with standard deep learning frameworks, while requiring reasonable memo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1912.12180","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/1912.12180/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":"1912.12180","created_at":"2026-07-05T00:28:41.152909+00:00"},{"alias_kind":"arxiv_version","alias_value":"1912.12180v1","created_at":"2026-07-05T00:28:41.152909+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1912.12180","created_at":"2026-07-05T00:28:41.152909+00:00"},{"alias_kind":"pith_short_12","alias_value":"WCLCKU62QUO7","created_at":"2026-07-05T00:28:41.152909+00:00"},{"alias_kind":"pith_short_16","alias_value":"WCLCKU62QUO7DGEQ","created_at":"2026-07-05T00:28:41.152909+00:00"},{"alias_kind":"pith_short_8","alias_value":"WCLCKU62","created_at":"2026-07-05T00:28:41.152909+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":18,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.05257","citing_title":"GeoFlow: Geo-Aware Modeling of Inter-Area Relationships in Origin-Destination Flow Prediction and Generation","ref_index":32,"is_internal_anchor":true},{"citing_arxiv_id":"2606.23503","citing_title":"UniverSat: Resolution- and Modality-Agnostic Transformers for Earth Observation","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27481","citing_title":"Sampling the Schwinger Model with Gauge-Equivariant Diffusion","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30309","citing_title":"A Point Cloud Transformer for Remote Monitoring and Automated Assessment of Physical Rehabilitation Exercises","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2605.29954","citing_title":"SwInception -- Local Attention Meets Convolutions","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.31156","citing_title":"TabCausal: Pretraining Across Causal Environments for Tabular Causal Discovery","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00746","citing_title":"Scaling Parallel Sequence Models to Foundation-Scale Vision Encoders","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2005.00341","citing_title":"Jukebox: A Generative Model for Music","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13189","citing_title":"MoBA: Mixture of Block Attention for Long-Context LLMs","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15032","citing_title":"Multi-Block Attention for Efficient Channel Estimation in IRS-Assisted mmWave MIMO","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2509.24527","citing_title":"Training Agents Inside of Scalable World Models","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2502.12524","citing_title":"YOLOv12: Attention-Centric Real-Time Object Detectors","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2204.03458","citing_title":"Video Diffusion Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2401.10774","citing_title":"Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads","ref_index":155,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12491","citing_title":"Elastic Attention Cores for Scalable Vision Transformers","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11007","citing_title":"The Transformer as a Polar State Estimator","ref_index":87,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00850","citing_title":"Earth System Foundation Model (ESFM): A unified framework for heterogeneous data integration and forecasting","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2010.04159","citing_title":"Deformable DETR: Deformable Transformers for End-to-End Object Detection","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WCLCKU62QUO7DGEQO4FBLEPEIB","json":"https://pith.science/pith/WCLCKU62QUO7DGEQO4FBLEPEIB.json","graph_json":"https://pith.science/api/pith-number/WCLCKU62QUO7DGEQO4FBLEPEIB/graph.json","events_json":"https://pith.science/api/pith-number/WCLCKU62QUO7DGEQO4FBLEPEIB/events.json","paper":"https://pith.science/paper/WCLCKU62"},"agent_actions":{"view_html":"https://pith.science/pith/WCLCKU62QUO7DGEQO4FBLEPEIB","download_json":"https://pith.science/pith/WCLCKU62QUO7DGEQO4FBLEPEIB.json","view_paper":"https://pith.science/paper/WCLCKU62","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1912.12180&json=true","fetch_graph":"https://pith.science/api/pith-number/WCLCKU62QUO7DGEQO4FBLEPEIB/graph.json","fetch_events":"https://pith.science/api/pith-number/WCLCKU62QUO7DGEQO4FBLEPEIB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WCLCKU62QUO7DGEQO4FBLEPEIB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WCLCKU62QUO7DGEQO4FBLEPEIB/action/storage_attestation","attest_author":"https://pith.science/pith/WCLCKU62QUO7DGEQO4FBLEPEIB/action/author_attestation","sign_citation":"https://pith.science/pith/WCLCKU62QUO7DGEQO4FBLEPEIB/action/citation_signature","submit_replication":"https://pith.science/pith/WCLCKU62QUO7DGEQO4FBLEPEIB/action/replication_record"}},"created_at":"2026-07-05T00:28:41.152909+00:00","updated_at":"2026-07-05T00:28:41.152909+00:00"}