{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:WZXWSFP5EVLJHMREZG2TR77RBO","short_pith_number":"pith:WZXWSFP5","schema_version":"1.0","canonical_sha256":"b66f6915fd255693b224c9b538fff10bb0cdd9b8c0e599f8cde9b1799de0b3fb","source":{"kind":"arxiv","id":"2310.19731","version":2},"attestation_state":"computed","paper":{"title":"ViR: Towards Efficient Vision Retention Backbones","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Hatamizadeh, Jan Kautz, Jose M. Alvarez, Michael Ranzinger, Sanja Fidler, Shiyi Lan","submitted_at":"2023-10-30T16:55:50Z","abstract_excerpt":"Vision Transformers (ViTs) have attracted a lot of popularity in recent years, due to their exceptional capabilities in modeling long-range spatial dependencies and scalability for large scale training. Although the training parallelism of self-attention mechanism plays an important role in retaining great performance, its quadratic complexity baffles the application of ViTs in many scenarios which demand fast inference. This effect is even more pronounced in applications in which autoregressive modeling of input features is required. In Natural Language Processing (NLP), a new stream of effor"},"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":"2310.19731","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-10-30T16:55:50Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"0adbc69bfed49f331eb0ee5dfcfe92ce65bc4c26dc1b6e62b9d815466108d659","abstract_canon_sha256":"cd703b6a6ecec9a4c53255d7decf944a8ad2461f3c7cd81a26144c70965776c3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:37:52.893340Z","signature_b64":"ktF1wLU+4krNKWH43iXRUWIItdOfvmcjN1igQOBW1k3HW2PkpqMf6VutF8XXN2V23OY+uVncXpoTIAOa35OfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b66f6915fd255693b224c9b538fff10bb0cdd9b8c0e599f8cde9b1799de0b3fb","last_reissued_at":"2026-07-05T07:37:52.892882Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:37:52.892882Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ViR: Towards Efficient Vision Retention Backbones","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Ali Hatamizadeh, Jan Kautz, Jose M. Alvarez, Michael Ranzinger, Sanja Fidler, Shiyi Lan","submitted_at":"2023-10-30T16:55:50Z","abstract_excerpt":"Vision Transformers (ViTs) have attracted a lot of popularity in recent years, due to their exceptional capabilities in modeling long-range spatial dependencies and scalability for large scale training. Although the training parallelism of self-attention mechanism plays an important role in retaining great performance, its quadratic complexity baffles the application of ViTs in many scenarios which demand fast inference. This effect is even more pronounced in applications in which autoregressive modeling of input features is required. In Natural Language Processing (NLP), a new stream of effor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.19731","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/2310.19731/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":"2310.19731","created_at":"2026-07-05T07:37:52.892945+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.19731v2","created_at":"2026-07-05T07:37:52.892945+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.19731","created_at":"2026-07-05T07:37:52.892945+00:00"},{"alias_kind":"pith_short_12","alias_value":"WZXWSFP5EVLJ","created_at":"2026-07-05T07:37:52.892945+00:00"},{"alias_kind":"pith_short_16","alias_value":"WZXWSFP5EVLJHMRE","created_at":"2026-07-05T07:37:52.892945+00:00"},{"alias_kind":"pith_short_8","alias_value":"WZXWSFP5","created_at":"2026-07-05T07:37:52.892945+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.06708","citing_title":"A Survey of Retentive Network","ref_index":33,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WZXWSFP5EVLJHMREZG2TR77RBO","json":"https://pith.science/pith/WZXWSFP5EVLJHMREZG2TR77RBO.json","graph_json":"https://pith.science/api/pith-number/WZXWSFP5EVLJHMREZG2TR77RBO/graph.json","events_json":"https://pith.science/api/pith-number/WZXWSFP5EVLJHMREZG2TR77RBO/events.json","paper":"https://pith.science/paper/WZXWSFP5"},"agent_actions":{"view_html":"https://pith.science/pith/WZXWSFP5EVLJHMREZG2TR77RBO","download_json":"https://pith.science/pith/WZXWSFP5EVLJHMREZG2TR77RBO.json","view_paper":"https://pith.science/paper/WZXWSFP5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.19731&json=true","fetch_graph":"https://pith.science/api/pith-number/WZXWSFP5EVLJHMREZG2TR77RBO/graph.json","fetch_events":"https://pith.science/api/pith-number/WZXWSFP5EVLJHMREZG2TR77RBO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WZXWSFP5EVLJHMREZG2TR77RBO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WZXWSFP5EVLJHMREZG2TR77RBO/action/storage_attestation","attest_author":"https://pith.science/pith/WZXWSFP5EVLJHMREZG2TR77RBO/action/author_attestation","sign_citation":"https://pith.science/pith/WZXWSFP5EVLJHMREZG2TR77RBO/action/citation_signature","submit_replication":"https://pith.science/pith/WZXWSFP5EVLJHMREZG2TR77RBO/action/replication_record"}},"created_at":"2026-07-05T07:37:52.892945+00:00","updated_at":"2026-07-05T07:37:52.892945+00:00"}