{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:RNQKFATAI4SVR2OKILFH3IVSFB","short_pith_number":"pith:RNQKFATA","canonical_record":{"source":{"id":"2607.26567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T07:40:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"04bba39f17478438a9b78d9a906b3c62ec8c3197910fe98e95007dcd6dd9e0c9","abstract_canon_sha256":"4edd17691d1b5e93f89670815c6b79f4a63fef44b8e5e679255d33d4f9f4de0a"},"schema_version":"1.0"},"canonical_sha256":"8b60a28260472558e9ca42ca7da2b228799facf44c3fc31e0a739f04137043c0","source":{"kind":"arxiv","id":"2607.26567","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26567","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26567v1","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26567","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"RNQKFATAI4SV","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"RNQKFATAI4SVR2OK","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"RNQKFATA","created_at":"2026-07-30T01:20:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:RNQKFATAI4SVR2OKILFH3IVSFB","target":"record","payload":{"canonical_record":{"source":{"id":"2607.26567","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T07:40:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"04bba39f17478438a9b78d9a906b3c62ec8c3197910fe98e95007dcd6dd9e0c9","abstract_canon_sha256":"4edd17691d1b5e93f89670815c6b79f4a63fef44b8e5e679255d33d4f9f4de0a"},"schema_version":"1.0"},"canonical_sha256":"8b60a28260472558e9ca42ca7da2b228799facf44c3fc31e0a739f04137043c0","receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8b60a28260472558e9ca42ca7da2b228799facf44c3fc31e0a739f04137043c0","last_reissued_at":"2026-07-30T01:20:54.571282Z","signature_status":"unsigned_v0","first_computed_at":"2026-07-30T01:20:54.571282Z"},"source_kind":"arxiv","source_id":"2607.26567","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zGWfF+O41O0b3CNKSMrlBS0WcKlZFHl+jo/J0/YuW8YQz+NIthZ6vMh/7g7Rxjv/Bf89gKdhL7SZ9hYxFDdQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:13:25.518773Z"},"content_sha256":"4ee29a9c500bf7ab52d163362781d9d8cc939bf54374b14883d644f877bae1ed","schema_version":"1.0","event_id":"sha256:4ee29a9c500bf7ab52d163362781d9d8cc939bf54374b14883d644f877bae1ed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:RNQKFATAI4SVR2OKILFH3IVSFB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.RO","authors_text":"Dinh Tuan Nguyen, Hoang Huy Le, Hung Nguyen, Kim Nhat Minh Nguyen, Pham Tuyen Le, Quan Nguyen, Van-Danh Le, Van Duc Vu, Van-Truong Nguyen","submitted_at":"2026-07-29T07:40:00Z","abstract_excerpt":"Humanoid robots increasingly require multi-modal understanding for natural interaction with humans. Despite the prominence of vision-language models, they generally assume textual rather than the more natural speech inputs. In this paper, we investigate whether a well-established text-conditioned model can be transferred to speech in a data-efficient manner. Using ALBEF as a case study, we conduct diagnostic analyses showing that a lightweight MLP-based projector effectively adapts it to speech, while preserving semantic discrimination and robustness. Motivated by these findings, we introduce "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26567","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/2607.26567/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T01:20:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sFwS9FPOT8ur7fQCtHEW0YotD0EvrlgpsSo0jTXgWLzaqpFNBn/5oDj49o2IHpEAB9SuFlxTvrsLundslwasBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T06:13:25.519293Z"},"content_sha256":"2cff2189662f18197b41fdff75f0fb14162f7407920b38fe353a9daf88a5705c","schema_version":"1.0","event_id":"sha256:2cff2189662f18197b41fdff75f0fb14162f7407920b38fe353a9daf88a5705c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RNQKFATAI4SVR2OKILFH3IVSFB/bundle.json","state_url":"https://pith.science/pith/RNQKFATAI4SVR2OKILFH3IVSFB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RNQKFATAI4SVR2OKILFH3IVSFB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T06:13:25Z","links":{"resolver":"https://pith.science/pith/RNQKFATAI4SVR2OKILFH3IVSFB","bundle":"https://pith.science/pith/RNQKFATAI4SVR2OKILFH3IVSFB/bundle.json","state":"https://pith.science/pith/RNQKFATAI4SVR2OKILFH3IVSFB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RNQKFATAI4SVR2OKILFH3IVSFB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:RNQKFATAI4SVR2OKILFH3IVSFB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"4edd17691d1b5e93f89670815c6b79f4a63fef44b8e5e679255d33d4f9f4de0a","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T07:40:00Z","title_canon_sha256":"04bba39f17478438a9b78d9a906b3c62ec8c3197910fe98e95007dcd6dd9e0c9"},"schema_version":"1.0","source":{"id":"2607.26567","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.26567","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.26567v1","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.26567","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"pith_short_12","alias_value":"RNQKFATAI4SV","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"pith_short_16","alias_value":"RNQKFATAI4SVR2OK","created_at":"2026-07-30T01:20:54Z"},{"alias_kind":"pith_short_8","alias_value":"RNQKFATA","created_at":"2026-07-30T01:20:54Z"}],"graph_snapshots":[{"event_id":"sha256:2cff2189662f18197b41fdff75f0fb14162f7407920b38fe353a9daf88a5705c","target":"graph","created_at":"2026-07-30T01:20:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.26567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Humanoid robots increasingly require multi-modal understanding for natural interaction with humans. Despite the prominence of vision-language models, they generally assume textual rather than the more natural speech inputs. In this paper, we investigate whether a well-established text-conditioned model can be transferred to speech in a data-efficient manner. Using ALBEF as a case study, we conduct diagnostic analyses showing that a lightweight MLP-based projector effectively adapts it to speech, while preserving semantic discrimination and robustness. Motivated by these findings, we introduce ","authors_text":"Dinh Tuan Nguyen, Hoang Huy Le, Hung Nguyen, Kim Nhat Minh Nguyen, Pham Tuyen Le, Quan Nguyen, Van-Danh Le, Van Duc Vu, Van-Truong Nguyen","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T07:40:00Z","title":"Speech2Grasp: Data-Efficient Transfer of Text-Conditioned Grasp Detection to Speech in Humanoid Robots"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.26567","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4ee29a9c500bf7ab52d163362781d9d8cc939bf54374b14883d644f877bae1ed","target":"record","created_at":"2026-07-30T01:20:54Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"4edd17691d1b5e93f89670815c6b79f4a63fef44b8e5e679255d33d4f9f4de0a","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-29T07:40:00Z","title_canon_sha256":"04bba39f17478438a9b78d9a906b3c62ec8c3197910fe98e95007dcd6dd9e0c9"},"schema_version":"1.0","source":{"id":"2607.26567","kind":"arxiv","version":1}},"canonical_sha256":"8b60a28260472558e9ca42ca7da2b228799facf44c3fc31e0a739f04137043c0","receipt":{"builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b60a28260472558e9ca42ca7da2b228799facf44c3fc31e0a739f04137043c0","first_computed_at":"2026-07-30T01:20:54.571282Z","kind":"pith_receipt","last_reissued_at":"2026-07-30T01:20:54.571282Z","receipt_version":"0.3","signature_status":"unsigned_v0"},"source_id":"2607.26567","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ee29a9c500bf7ab52d163362781d9d8cc939bf54374b14883d644f877bae1ed","sha256:2cff2189662f18197b41fdff75f0fb14162f7407920b38fe353a9daf88a5705c"],"state_sha256":"3a5e25f616f02f6569f8fc0bd700d3955be77c6fe5c77624804fc2270ab92579"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fv7cWhQWHKvaVkRbbMy/7u/yaA5dCNK9BF4H8Sa6vLFfkDKGsi9HDxuXZ9RlG837VUZ2RNfM3wfUEJpQubDXBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T06:13:25.523452Z","bundle_sha256":"e027e9fa00cf7d2c788f74f133524cbe3deafaacfcab2fee168617effc9b7b7e"}}