{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Q53SPQPCXA73TT3VCVE5LL77SD","short_pith_number":"pith:Q53SPQPC","schema_version":"1.0","canonical_sha256":"877727c1e2b83fb9cf751549d5afff90e9488754c1b8617d196bd7233fa012e4","source":{"kind":"arxiv","id":"2505.07455","version":1},"attestation_state":"computed","paper":{"title":"GelFusion: Enhancing Robotic Manipulation under Visual Constraints via Visuotactile Fusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Peng Yin, Shiqi Zhao, Shulong Jiang, Yuxuan Fan","submitted_at":"2025-05-12T11:37:35Z","abstract_excerpt":"Visuotactile sensing offers rich contact information that can help mitigate performance bottlenecks in imitation learning, particularly under vision-limited conditions, such as ambiguous visual cues or occlusions. Effectively fusing visual and visuotactile modalities, however, presents ongoing challenges. We introduce GelFusion, a framework designed to enhance policies by integrating visuotactile feedback, specifically from high-resolution GelSight sensors. GelFusion using a vision-dominated cross-attention fusion mechanism incorporates visuotactile information into policy learning. To better "},"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":"2505.07455","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-12T11:37:35Z","cross_cats_sorted":[],"title_canon_sha256":"5746a41e687e2487de5f9bb132ae065af8f96d2a94c50e4b2d47f7f6b02227f7","abstract_canon_sha256":"043181230541fc0e06111c1f95b81a5967cc9b774059d294c31352a5b5b304c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:01:48.001974Z","signature_b64":"uFa+LTHuMUxcXke36QCyjq8GMbQ5tDaAjHfdk59JktaM7X0ELC52XsHn9NQGnTG7QUnJJJ90g7pjwywqTRmqCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"877727c1e2b83fb9cf751549d5afff90e9488754c1b8617d196bd7233fa012e4","last_reissued_at":"2026-07-05T11:01:48.001499Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:01:48.001499Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GelFusion: Enhancing Robotic Manipulation under Visual Constraints via Visuotactile Fusion","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Peng Yin, Shiqi Zhao, Shulong Jiang, Yuxuan Fan","submitted_at":"2025-05-12T11:37:35Z","abstract_excerpt":"Visuotactile sensing offers rich contact information that can help mitigate performance bottlenecks in imitation learning, particularly under vision-limited conditions, such as ambiguous visual cues or occlusions. Effectively fusing visual and visuotactile modalities, however, presents ongoing challenges. We introduce GelFusion, a framework designed to enhance policies by integrating visuotactile feedback, specifically from high-resolution GelSight sensors. GelFusion using a vision-dominated cross-attention fusion mechanism incorporates visuotactile information into policy learning. To better "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.07455","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/2505.07455/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":"2505.07455","created_at":"2026-07-05T11:01:48.001556+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.07455v1","created_at":"2026-07-05T11:01:48.001556+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.07455","created_at":"2026-07-05T11:01:48.001556+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q53SPQPCXA73","created_at":"2026-07-05T11:01:48.001556+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q53SPQPCXA73TT3V","created_at":"2026-07-05T11:01:48.001556+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q53SPQPC","created_at":"2026-07-05T11:01:48.001556+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31236","citing_title":"TactX: Learning Shared Tactile Representations Across Diverse Sensors","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q53SPQPCXA73TT3VCVE5LL77SD","json":"https://pith.science/pith/Q53SPQPCXA73TT3VCVE5LL77SD.json","graph_json":"https://pith.science/api/pith-number/Q53SPQPCXA73TT3VCVE5LL77SD/graph.json","events_json":"https://pith.science/api/pith-number/Q53SPQPCXA73TT3VCVE5LL77SD/events.json","paper":"https://pith.science/paper/Q53SPQPC"},"agent_actions":{"view_html":"https://pith.science/pith/Q53SPQPCXA73TT3VCVE5LL77SD","download_json":"https://pith.science/pith/Q53SPQPCXA73TT3VCVE5LL77SD.json","view_paper":"https://pith.science/paper/Q53SPQPC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.07455&json=true","fetch_graph":"https://pith.science/api/pith-number/Q53SPQPCXA73TT3VCVE5LL77SD/graph.json","fetch_events":"https://pith.science/api/pith-number/Q53SPQPCXA73TT3VCVE5LL77SD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q53SPQPCXA73TT3VCVE5LL77SD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q53SPQPCXA73TT3VCVE5LL77SD/action/storage_attestation","attest_author":"https://pith.science/pith/Q53SPQPCXA73TT3VCVE5LL77SD/action/author_attestation","sign_citation":"https://pith.science/pith/Q53SPQPCXA73TT3VCVE5LL77SD/action/citation_signature","submit_replication":"https://pith.science/pith/Q53SPQPCXA73TT3VCVE5LL77SD/action/replication_record"}},"created_at":"2026-07-05T11:01:48.001556+00:00","updated_at":"2026-07-05T11:01:48.001556+00:00"}