{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:LR5H5IOWOGAWWDQRMVMARCCFE4","short_pith_number":"pith:LR5H5IOW","schema_version":"1.0","canonical_sha256":"5c7a7ea1d671816b0e116558088845271b02c5c6cfc71b591c2e22e4c4bd7820","source":{"kind":"arxiv","id":"2410.07599","version":2},"attestation_state":"computed","paper":{"title":"Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Angtian Wang, Cihang Xie, Feng Wang, Guoyizhe Wei, Sucheng Ren, Timing Yang, Wei Shao, Yaodong Yu, Yuyin Zhou","submitted_at":"2024-10-10T04:14:52Z","abstract_excerpt":"In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations. This modeling paradigm allows us to process images in a recurrent formulation with linear complexity relative to the sequence length, which can effectively address the memory and computation explosion issues posed by high-resolution and fine-grained images. In detail, we introduce two simple designs that seamlessly integrate image inputs into the causal inference framework: a global pooling token placed at the beg"},"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":"2410.07599","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-10T04:14:52Z","cross_cats_sorted":[],"title_canon_sha256":"c744fd35da3290223451e764032210b3ccd6dc482d232d897fc9e7cecb8eb266","abstract_canon_sha256":"bfcd6fb1a9c9d2c9e0fe6cf0325e5f10129641aa26b3d212f3225e59620a6124"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:21.171706Z","signature_b64":"WhMcLnuhw8tI/yLqdcrD8e8tzVLeZi/PfkiXvs41d4pk1tfL4RbviuR+guYK/gjksoGSXcfwZ6y9SIgO/JSWBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5c7a7ea1d671816b0e116558088845271b02c5c6cfc71b591c2e22e4c4bd7820","last_reissued_at":"2026-07-05T11:12:21.171192Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:21.171192Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adventurer: Optimizing Vision Mamba Architecture Designs for Efficiency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Alan Yuille, Angtian Wang, Cihang Xie, Feng Wang, Guoyizhe Wei, Sucheng Ren, Timing Yang, Wei Shao, Yaodong Yu, Yuyin Zhou","submitted_at":"2024-10-10T04:14:52Z","abstract_excerpt":"In this work, we introduce the Adventurer series models where we treat images as sequences of patch tokens and employ uni-directional language models to learn visual representations. This modeling paradigm allows us to process images in a recurrent formulation with linear complexity relative to the sequence length, which can effectively address the memory and computation explosion issues posed by high-resolution and fine-grained images. In detail, we introduce two simple designs that seamlessly integrate image inputs into the causal inference framework: a global pooling token placed at the beg"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07599","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/2410.07599/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":"2410.07599","created_at":"2026-07-05T11:12:21.171252+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07599v2","created_at":"2026-07-05T11:12:21.171252+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07599","created_at":"2026-07-05T11:12:21.171252+00:00"},{"alias_kind":"pith_short_12","alias_value":"LR5H5IOWOGAW","created_at":"2026-07-05T11:12:21.171252+00:00"},{"alias_kind":"pith_short_16","alias_value":"LR5H5IOWOGAWWDQR","created_at":"2026-07-05T11:12:21.171252+00:00"},{"alias_kind":"pith_short_8","alias_value":"LR5H5IOW","created_at":"2026-07-05T11:12:21.171252+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25377","citing_title":"Adversarial Orthogonal Disentanglement for LVLM Hallucination Mitigation","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LR5H5IOWOGAWWDQRMVMARCCFE4","json":"https://pith.science/pith/LR5H5IOWOGAWWDQRMVMARCCFE4.json","graph_json":"https://pith.science/api/pith-number/LR5H5IOWOGAWWDQRMVMARCCFE4/graph.json","events_json":"https://pith.science/api/pith-number/LR5H5IOWOGAWWDQRMVMARCCFE4/events.json","paper":"https://pith.science/paper/LR5H5IOW"},"agent_actions":{"view_html":"https://pith.science/pith/LR5H5IOWOGAWWDQRMVMARCCFE4","download_json":"https://pith.science/pith/LR5H5IOWOGAWWDQRMVMARCCFE4.json","view_paper":"https://pith.science/paper/LR5H5IOW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07599&json=true","fetch_graph":"https://pith.science/api/pith-number/LR5H5IOWOGAWWDQRMVMARCCFE4/graph.json","fetch_events":"https://pith.science/api/pith-number/LR5H5IOWOGAWWDQRMVMARCCFE4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LR5H5IOWOGAWWDQRMVMARCCFE4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LR5H5IOWOGAWWDQRMVMARCCFE4/action/storage_attestation","attest_author":"https://pith.science/pith/LR5H5IOWOGAWWDQRMVMARCCFE4/action/author_attestation","sign_citation":"https://pith.science/pith/LR5H5IOWOGAWWDQRMVMARCCFE4/action/citation_signature","submit_replication":"https://pith.science/pith/LR5H5IOWOGAWWDQRMVMARCCFE4/action/replication_record"}},"created_at":"2026-07-05T11:12:21.171252+00:00","updated_at":"2026-07-05T11:12:21.171252+00:00"}