{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:F32ECJ47SPHK7UQIGH4ZINQJLH","short_pith_number":"pith:F32ECJ47","schema_version":"1.0","canonical_sha256":"2ef441279f93ceafd20831f994360959d625ca7ba48e8db5ebef6b20455c3cdd","source":{"kind":"arxiv","id":"2606.29089","version":1},"attestation_state":"computed","paper":{"title":"TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dmitry Berenson, Jayjun Lee, Mark Van der Merwe, Mohamad Louai Shehab, Nima Fazeli, Yinpei Dai, Youngsun Wi","submitted_at":"2026-06-27T21:06:06Z","abstract_excerpt":"Vision-Language-Action (VLA) models demonstrate impressive reasoning over visual, semantic, and spatial task variations by leveraging large-scale vision and language pre-training. They remain, however, largely blind to contact forces, which seldom manifest clearly in visual feedback but are central to contact-rich manipulation. Tactile sensing measures these forces directly, but integrating it into VLAs is difficult: tactile data is absent from the large-scale corpora used to pre-train VLAs, so adding it as a new input modality induces a distribution shift that erodes the very pre-training tha"},"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":"2606.29089","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-06-27T21:06:06Z","cross_cats_sorted":[],"title_canon_sha256":"c5897f1ad34fc81ec5a7b2de2c49bf775a6ddcfc38a6786b58141b3e2b96587a","abstract_canon_sha256":"d10b9ad6b4e8f7403d37bf6f42f102280559083a381405a0eb88ddf5b7028ef7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T01:17:52.468961Z","signature_b64":"HxZvoWF8lT6macGBI+7cdZw/1Fp8mDcHA33+GpefU5FcAHTnpqVpm4kebW7ghb4iR3PIbcJs0Jl+VNzbcnxVAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ef441279f93ceafd20831f994360959d625ca7ba48e8db5ebef6b20455c3cdd","last_reissued_at":"2026-06-30T01:17:52.468493Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T01:17:52.468493Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TAP-VLA: Tactile Annotation Prompting for Vision Language Action Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Dmitry Berenson, Jayjun Lee, Mark Van der Merwe, Mohamad Louai Shehab, Nima Fazeli, Yinpei Dai, Youngsun Wi","submitted_at":"2026-06-27T21:06:06Z","abstract_excerpt":"Vision-Language-Action (VLA) models demonstrate impressive reasoning over visual, semantic, and spatial task variations by leveraging large-scale vision and language pre-training. They remain, however, largely blind to contact forces, which seldom manifest clearly in visual feedback but are central to contact-rich manipulation. Tactile sensing measures these forces directly, but integrating it into VLAs is difficult: tactile data is absent from the large-scale corpora used to pre-train VLAs, so adding it as a new input modality induces a distribution shift that erodes the very pre-training tha"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29089","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/2606.29089/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":"2606.29089","created_at":"2026-06-30T01:17:52.468561+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29089v1","created_at":"2026-06-30T01:17:52.468561+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29089","created_at":"2026-06-30T01:17:52.468561+00:00"},{"alias_kind":"pith_short_12","alias_value":"F32ECJ47SPHK","created_at":"2026-06-30T01:17:52.468561+00:00"},{"alias_kind":"pith_short_16","alias_value":"F32ECJ47SPHK7UQI","created_at":"2026-06-30T01:17:52.468561+00:00"},{"alias_kind":"pith_short_8","alias_value":"F32ECJ47","created_at":"2026-06-30T01:17:52.468561+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/F32ECJ47SPHK7UQIGH4ZINQJLH","json":"https://pith.science/pith/F32ECJ47SPHK7UQIGH4ZINQJLH.json","graph_json":"https://pith.science/api/pith-number/F32ECJ47SPHK7UQIGH4ZINQJLH/graph.json","events_json":"https://pith.science/api/pith-number/F32ECJ47SPHK7UQIGH4ZINQJLH/events.json","paper":"https://pith.science/paper/F32ECJ47"},"agent_actions":{"view_html":"https://pith.science/pith/F32ECJ47SPHK7UQIGH4ZINQJLH","download_json":"https://pith.science/pith/F32ECJ47SPHK7UQIGH4ZINQJLH.json","view_paper":"https://pith.science/paper/F32ECJ47","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29089&json=true","fetch_graph":"https://pith.science/api/pith-number/F32ECJ47SPHK7UQIGH4ZINQJLH/graph.json","fetch_events":"https://pith.science/api/pith-number/F32ECJ47SPHK7UQIGH4ZINQJLH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F32ECJ47SPHK7UQIGH4ZINQJLH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F32ECJ47SPHK7UQIGH4ZINQJLH/action/storage_attestation","attest_author":"https://pith.science/pith/F32ECJ47SPHK7UQIGH4ZINQJLH/action/author_attestation","sign_citation":"https://pith.science/pith/F32ECJ47SPHK7UQIGH4ZINQJLH/action/citation_signature","submit_replication":"https://pith.science/pith/F32ECJ47SPHK7UQIGH4ZINQJLH/action/replication_record"}},"created_at":"2026-06-30T01:17:52.468561+00:00","updated_at":"2026-06-30T01:17:52.468561+00:00"}