{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PCU4P7YYP7PFJPESFVTMEZBFOK","short_pith_number":"pith:PCU4P7YY","schema_version":"1.0","canonical_sha256":"78a9c7ff187fde54bc922d66c2642572b027e53974421c84312f08f2012a6477","source":{"kind":"arxiv","id":"2509.04658","version":1},"attestation_state":"computed","paper":{"title":"Surformer v2: A Multimodal Classifier for Surface Understanding from Touch and Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Manish Kansana, Noorbakhsh Amiri Golilarz, Shahram Rahimi, Sindhuja Penchala","submitted_at":"2025-09-04T21:05:33Z","abstract_excerpt":"Multimodal surface material classification plays a critical role in advancing tactile perception for robotic manipulation and interaction. In this paper, we present Surformer v2, an enhanced multi-modal classification architecture designed to integrate visual and tactile sensory streams through a late(decision level) fusion mechanism. Building on our earlier Surformer v1 framework [1], which employed handcrafted feature extraction followed by mid-level fusion architecture with multi-head cross-attention layers, Surformer v2 integrates the feature extraction process within the model itself and "},"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":"2509.04658","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2025-09-04T21:05:33Z","cross_cats_sorted":[],"title_canon_sha256":"ac2160845fe3a1966d29e2097cc52a5d4f469056a85ef97453cf093814faa933","abstract_canon_sha256":"086debc171605338a4f366adaca2536d8c0dc895c48f973ed35e46737912feb9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:27.029859Z","signature_b64":"k8mR/UIoJEJlS4EY3ThZ8pJDnbP7ZFJ7RvS7wJf2R4kv+sCwR3XLcylmJezuKQygFkgSpY2CZjkIDAi2KhlJBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78a9c7ff187fde54bc922d66c2642572b027e53974421c84312f08f2012a6477","last_reissued_at":"2026-07-05T12:05:27.029357Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:27.029357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Surformer v2: A Multimodal Classifier for Surface Understanding from Touch and Vision","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Manish Kansana, Noorbakhsh Amiri Golilarz, Shahram Rahimi, Sindhuja Penchala","submitted_at":"2025-09-04T21:05:33Z","abstract_excerpt":"Multimodal surface material classification plays a critical role in advancing tactile perception for robotic manipulation and interaction. In this paper, we present Surformer v2, an enhanced multi-modal classification architecture designed to integrate visual and tactile sensory streams through a late(decision level) fusion mechanism. Building on our earlier Surformer v1 framework [1], which employed handcrafted feature extraction followed by mid-level fusion architecture with multi-head cross-attention layers, Surformer v2 integrates the feature extraction process within the model itself and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.04658","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/2509.04658/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":"2509.04658","created_at":"2026-07-05T12:05:27.029424+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.04658v1","created_at":"2026-07-05T12:05:27.029424+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.04658","created_at":"2026-07-05T12:05:27.029424+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCU4P7YYP7PF","created_at":"2026-07-05T12:05:27.029424+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCU4P7YYP7PFJPES","created_at":"2026-07-05T12:05:27.029424+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCU4P7YY","created_at":"2026-07-05T12:05:27.029424+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17336","citing_title":"Tactile-based Multimodal Fusion in Embodied Intelligence: A Survey of Vision, Language, and Contact-Driven Paradigms","ref_index":88,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCU4P7YYP7PFJPESFVTMEZBFOK","json":"https://pith.science/pith/PCU4P7YYP7PFJPESFVTMEZBFOK.json","graph_json":"https://pith.science/api/pith-number/PCU4P7YYP7PFJPESFVTMEZBFOK/graph.json","events_json":"https://pith.science/api/pith-number/PCU4P7YYP7PFJPESFVTMEZBFOK/events.json","paper":"https://pith.science/paper/PCU4P7YY"},"agent_actions":{"view_html":"https://pith.science/pith/PCU4P7YYP7PFJPESFVTMEZBFOK","download_json":"https://pith.science/pith/PCU4P7YYP7PFJPESFVTMEZBFOK.json","view_paper":"https://pith.science/paper/PCU4P7YY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.04658&json=true","fetch_graph":"https://pith.science/api/pith-number/PCU4P7YYP7PFJPESFVTMEZBFOK/graph.json","fetch_events":"https://pith.science/api/pith-number/PCU4P7YYP7PFJPESFVTMEZBFOK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCU4P7YYP7PFJPESFVTMEZBFOK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCU4P7YYP7PFJPESFVTMEZBFOK/action/storage_attestation","attest_author":"https://pith.science/pith/PCU4P7YYP7PFJPESFVTMEZBFOK/action/author_attestation","sign_citation":"https://pith.science/pith/PCU4P7YYP7PFJPESFVTMEZBFOK/action/citation_signature","submit_replication":"https://pith.science/pith/PCU4P7YYP7PFJPESFVTMEZBFOK/action/replication_record"}},"created_at":"2026-07-05T12:05:27.029424+00:00","updated_at":"2026-07-05T12:05:27.029424+00:00"}