{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E6M5UKD7WUCLBN42FV36FU7PWR","short_pith_number":"pith:E6M5UKD7","schema_version":"1.0","canonical_sha256":"2799da287fb504b0b79a2d77e2d3efb46a1a788daec87b1facfeed24662eb624","source":{"kind":"arxiv","id":"2501.06040","version":2},"attestation_state":"computed","paper":{"title":"MSCViT: A Small-size ViT architecture with Multi-Scale Self-Attention Mechanism for Tiny Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowei Zhang, Yi Zhang","submitted_at":"2025-01-10T15:18:05Z","abstract_excerpt":"Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real applications, the large-scale datasets are not always available, and ViT performs worse than Convolutional Neural Networks (CNNs) if it is only trained on small scale dataset (called tiny dataset), since it requires large amount of training data to ensure its representational capacity. In this paper, a small-size ViT architecture with multi-scale self-attention mech"},"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":"2501.06040","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-10T15:18:05Z","cross_cats_sorted":[],"title_canon_sha256":"c006b5bc9cd1e509db00a657536f85f19bbec7eb2e12c82335637aece85abd23","abstract_canon_sha256":"2424a2282c97373197ac34205ec085eb28483b6e9906cf298ed614def7326cbe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:00:46.379691Z","signature_b64":"oO8cy3AcjR12so/U01m7bCDSMRZoB7MezYrcXddncavWYVkF5+TBMkx6LvvZ3CJe1OH7YLib/9NP6/wo1RADDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2799da287fb504b0b79a2d77e2d3efb46a1a788daec87b1facfeed24662eb624","last_reissued_at":"2026-07-05T10:00:46.379343Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:00:46.379343Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MSCViT: A Small-size ViT architecture with Multi-Scale Self-Attention Mechanism for Tiny Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bowei Zhang, Yi Zhang","submitted_at":"2025-01-10T15:18:05Z","abstract_excerpt":"Vision Transformer (ViT) has demonstrated significant potential in various vision tasks due to its strong ability in modelling long-range dependencies. However, such success is largely fueled by training on massive samples. In real applications, the large-scale datasets are not always available, and ViT performs worse than Convolutional Neural Networks (CNNs) if it is only trained on small scale dataset (called tiny dataset), since it requires large amount of training data to ensure its representational capacity. In this paper, a small-size ViT architecture with multi-scale self-attention mech"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.06040","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/2501.06040/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":"2501.06040","created_at":"2026-07-05T10:00:46.379407+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.06040v2","created_at":"2026-07-05T10:00:46.379407+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.06040","created_at":"2026-07-05T10:00:46.379407+00:00"},{"alias_kind":"pith_short_12","alias_value":"E6M5UKD7WUCL","created_at":"2026-07-05T10:00:46.379407+00:00"},{"alias_kind":"pith_short_16","alias_value":"E6M5UKD7WUCLBN42","created_at":"2026-07-05T10:00:46.379407+00:00"},{"alias_kind":"pith_short_8","alias_value":"E6M5UKD7","created_at":"2026-07-05T10:00:46.379407+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E6M5UKD7WUCLBN42FV36FU7PWR","json":"https://pith.science/pith/E6M5UKD7WUCLBN42FV36FU7PWR.json","graph_json":"https://pith.science/api/pith-number/E6M5UKD7WUCLBN42FV36FU7PWR/graph.json","events_json":"https://pith.science/api/pith-number/E6M5UKD7WUCLBN42FV36FU7PWR/events.json","paper":"https://pith.science/paper/E6M5UKD7"},"agent_actions":{"view_html":"https://pith.science/pith/E6M5UKD7WUCLBN42FV36FU7PWR","download_json":"https://pith.science/pith/E6M5UKD7WUCLBN42FV36FU7PWR.json","view_paper":"https://pith.science/paper/E6M5UKD7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.06040&json=true","fetch_graph":"https://pith.science/api/pith-number/E6M5UKD7WUCLBN42FV36FU7PWR/graph.json","fetch_events":"https://pith.science/api/pith-number/E6M5UKD7WUCLBN42FV36FU7PWR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E6M5UKD7WUCLBN42FV36FU7PWR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E6M5UKD7WUCLBN42FV36FU7PWR/action/storage_attestation","attest_author":"https://pith.science/pith/E6M5UKD7WUCLBN42FV36FU7PWR/action/author_attestation","sign_citation":"https://pith.science/pith/E6M5UKD7WUCLBN42FV36FU7PWR/action/citation_signature","submit_replication":"https://pith.science/pith/E6M5UKD7WUCLBN42FV36FU7PWR/action/replication_record"}},"created_at":"2026-07-05T10:00:46.379407+00:00","updated_at":"2026-07-05T10:00:46.379407+00:00"}