{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VXIPOCQQIUGZMVJOC2X6TQMHZI","short_pith_number":"pith:VXIPOCQQ","schema_version":"1.0","canonical_sha256":"add0f70a10450d96552e16afe9c187ca338b7497db594cd949f5a2d904cd1668","source":{"kind":"arxiv","id":"2410.16020","version":2},"attestation_state":"computed","paper":{"title":"START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jintao Guo, Lei Qi, Yang Gao, Yinghuan Shi","submitted_at":"2024-10-21T13:50:32Z","abstract_excerpt":"Domain Generalization (DG) aims to enable models to generalize to unseen target domains by learning from multiple source domains. Existing DG methods primarily rely on convolutional neural networks (CNNs), which inherently learn texture biases due to their limited receptive fields, making them prone to overfitting source domains. While some works have introduced transformer-based methods (ViTs) for DG to leverage the global receptive field, these methods incur high computational costs due to the quadratic complexity of self-attention. Recently, advanced state space models (SSMs), represented b"},"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":"2410.16020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-21T13:50:32Z","cross_cats_sorted":[],"title_canon_sha256":"6fb4b130167b3e8f93c099177b5c08f4cfdc33853ba8d1914422dad4d314b284","abstract_canon_sha256":"022431743796147436ab32d43d58ec6ebad48fae34b953a2344096223bbae1f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:57:47.753568Z","signature_b64":"KZaqSr1PREnvHppeqx0GC2JnXEroB1pffDa6Nvvn9saC23ZAaF3g2RQNxwOK8/OQ/6Grri+ST6cEgw6yjNBOAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"add0f70a10450d96552e16afe9c187ca338b7497db594cd949f5a2d904cd1668","last_reissued_at":"2026-07-05T09:57:47.753098Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:57:47.753098Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"START: A Generalized State Space Model with Saliency-Driven Token-Aware Transformation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Jintao Guo, Lei Qi, Yang Gao, Yinghuan Shi","submitted_at":"2024-10-21T13:50:32Z","abstract_excerpt":"Domain Generalization (DG) aims to enable models to generalize to unseen target domains by learning from multiple source domains. Existing DG methods primarily rely on convolutional neural networks (CNNs), which inherently learn texture biases due to their limited receptive fields, making them prone to overfitting source domains. While some works have introduced transformer-based methods (ViTs) for DG to leverage the global receptive field, these methods incur high computational costs due to the quadratic complexity of self-attention. Recently, advanced state space models (SSMs), represented b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16020","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/2410.16020/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":"2410.16020","created_at":"2026-07-05T09:57:47.753155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16020v2","created_at":"2026-07-05T09:57:47.753155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16020","created_at":"2026-07-05T09:57:47.753155+00:00"},{"alias_kind":"pith_short_12","alias_value":"VXIPOCQQIUGZ","created_at":"2026-07-05T09:57:47.753155+00:00"},{"alias_kind":"pith_short_16","alias_value":"VXIPOCQQIUGZMVJO","created_at":"2026-07-05T09:57:47.753155+00:00"},{"alias_kind":"pith_short_8","alias_value":"VXIPOCQQ","created_at":"2026-07-05T09:57:47.753155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.14088","citing_title":"Generalizable Multispectral Land Cover Classification via Frequency-Aware Mixture of Low-Rank Token Experts","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VXIPOCQQIUGZMVJOC2X6TQMHZI","json":"https://pith.science/pith/VXIPOCQQIUGZMVJOC2X6TQMHZI.json","graph_json":"https://pith.science/api/pith-number/VXIPOCQQIUGZMVJOC2X6TQMHZI/graph.json","events_json":"https://pith.science/api/pith-number/VXIPOCQQIUGZMVJOC2X6TQMHZI/events.json","paper":"https://pith.science/paper/VXIPOCQQ"},"agent_actions":{"view_html":"https://pith.science/pith/VXIPOCQQIUGZMVJOC2X6TQMHZI","download_json":"https://pith.science/pith/VXIPOCQQIUGZMVJOC2X6TQMHZI.json","view_paper":"https://pith.science/paper/VXIPOCQQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16020&json=true","fetch_graph":"https://pith.science/api/pith-number/VXIPOCQQIUGZMVJOC2X6TQMHZI/graph.json","fetch_events":"https://pith.science/api/pith-number/VXIPOCQQIUGZMVJOC2X6TQMHZI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VXIPOCQQIUGZMVJOC2X6TQMHZI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VXIPOCQQIUGZMVJOC2X6TQMHZI/action/storage_attestation","attest_author":"https://pith.science/pith/VXIPOCQQIUGZMVJOC2X6TQMHZI/action/author_attestation","sign_citation":"https://pith.science/pith/VXIPOCQQIUGZMVJOC2X6TQMHZI/action/citation_signature","submit_replication":"https://pith.science/pith/VXIPOCQQIUGZMVJOC2X6TQMHZI/action/replication_record"}},"created_at":"2026-07-05T09:57:47.753155+00:00","updated_at":"2026-07-05T09:57:47.753155+00:00"}