{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T75FOIOJNMNZIXKT7ABDXLFGMI","short_pith_number":"pith:T75FOIOJ","schema_version":"1.0","canonical_sha256":"9ffa5721c96b1b945d53f8023baca662027d3f462e818710f475bebd51da346e","source":{"kind":"arxiv","id":"2509.11218","version":1},"attestation_state":"computed","paper":{"title":"Geometrically Constrained and Token-Based Probabilistic Spatial Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Johann Schmidt, Sebastian Stober","submitted_at":"2025-09-14T11:30:53Z","abstract_excerpt":"Fine-grained visual classification (FGVC) remains highly sensitive to geometric variability, where objects appear under arbitrary orientations, scales, and perspective distortions. While equivariant architectures address this issue, they typically require substantial computational resources and restrict the hypothesis space. We revisit Spatial Transformer Networks (STNs) as a canonicalization tool for transformer-based vision pipelines, emphasizing their flexibility, backbone-agnostic nature, and lack of architectural constraints. We propose a probabilistic, component-wise extension that impro"},"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":"2509.11218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-14T11:30:53Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2ad6b9d2e0b3f0248141518fc8c65529220425d7a0d30c14d012851b8e271fb8","abstract_canon_sha256":"f8a4851551f94a2d156f567512827013dd5c27c69f982c8005a6fa649bd8ee13"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:35.463522Z","signature_b64":"5ef/Wdj5yp9IorCYsoOmXsUYTocXsIGsTvIqfFC4NWmmSTa2fGDw9q6nSm4lIVY1aQUBtP7hVgyGMSrURjBgDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9ffa5721c96b1b945d53f8023baca662027d3f462e818710f475bebd51da346e","last_reissued_at":"2026-07-05T12:11:35.463044Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:35.463044Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Geometrically Constrained and Token-Based Probabilistic Spatial Transformers","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Johann Schmidt, Sebastian Stober","submitted_at":"2025-09-14T11:30:53Z","abstract_excerpt":"Fine-grained visual classification (FGVC) remains highly sensitive to geometric variability, where objects appear under arbitrary orientations, scales, and perspective distortions. While equivariant architectures address this issue, they typically require substantial computational resources and restrict the hypothesis space. We revisit Spatial Transformer Networks (STNs) as a canonicalization tool for transformer-based vision pipelines, emphasizing their flexibility, backbone-agnostic nature, and lack of architectural constraints. We propose a probabilistic, component-wise extension that impro"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.11218","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/2509.11218/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":"2509.11218","created_at":"2026-07-05T12:11:35.463101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.11218v1","created_at":"2026-07-05T12:11:35.463101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.11218","created_at":"2026-07-05T12:11:35.463101+00:00"},{"alias_kind":"pith_short_12","alias_value":"T75FOIOJNMNZ","created_at":"2026-07-05T12:11:35.463101+00:00"},{"alias_kind":"pith_short_16","alias_value":"T75FOIOJNMNZIXKT","created_at":"2026-07-05T12:11:35.463101+00:00"},{"alias_kind":"pith_short_8","alias_value":"T75FOIOJ","created_at":"2026-07-05T12:11:35.463101+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/T75FOIOJNMNZIXKT7ABDXLFGMI","json":"https://pith.science/pith/T75FOIOJNMNZIXKT7ABDXLFGMI.json","graph_json":"https://pith.science/api/pith-number/T75FOIOJNMNZIXKT7ABDXLFGMI/graph.json","events_json":"https://pith.science/api/pith-number/T75FOIOJNMNZIXKT7ABDXLFGMI/events.json","paper":"https://pith.science/paper/T75FOIOJ"},"agent_actions":{"view_html":"https://pith.science/pith/T75FOIOJNMNZIXKT7ABDXLFGMI","download_json":"https://pith.science/pith/T75FOIOJNMNZIXKT7ABDXLFGMI.json","view_paper":"https://pith.science/paper/T75FOIOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.11218&json=true","fetch_graph":"https://pith.science/api/pith-number/T75FOIOJNMNZIXKT7ABDXLFGMI/graph.json","fetch_events":"https://pith.science/api/pith-number/T75FOIOJNMNZIXKT7ABDXLFGMI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T75FOIOJNMNZIXKT7ABDXLFGMI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T75FOIOJNMNZIXKT7ABDXLFGMI/action/storage_attestation","attest_author":"https://pith.science/pith/T75FOIOJNMNZIXKT7ABDXLFGMI/action/author_attestation","sign_citation":"https://pith.science/pith/T75FOIOJNMNZIXKT7ABDXLFGMI/action/citation_signature","submit_replication":"https://pith.science/pith/T75FOIOJNMNZIXKT7ABDXLFGMI/action/replication_record"}},"created_at":"2026-07-05T12:11:35.463101+00:00","updated_at":"2026-07-05T12:11:35.463101+00:00"}