{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:FEAOCOWRECFLUVR7VM2XC54PJ4","short_pith_number":"pith:FEAOCOWR","canonical_record":{"source":{"id":"2505.09577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:29:35Z","cross_cats_sorted":[],"title_canon_sha256":"4c82b137251e5e6ef7b706f89d86c5086eb8adaf68aef3cd23e986ef7437e2de","abstract_canon_sha256":"0ba518deef6f094e18ac2c62c4ca9bc6cec1dc6abe495fd66d6cd4602192a55b"},"schema_version":"1.0"},"canonical_sha256":"2900e13ad1208aba563fab3571778f4f29ec409d32930ed38ee05895153f7597","source":{"kind":"arxiv","id":"2505.09577","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09577","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09577v1","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09577","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"FEAOCOWRECFL","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"FEAOCOWRECFLUVR7","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"FEAOCOWR","created_at":"2026-07-05T11:03:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:FEAOCOWRECFLUVR7VM2XC54PJ4","target":"record","payload":{"canonical_record":{"source":{"id":"2505.09577","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:29:35Z","cross_cats_sorted":[],"title_canon_sha256":"4c82b137251e5e6ef7b706f89d86c5086eb8adaf68aef3cd23e986ef7437e2de","abstract_canon_sha256":"0ba518deef6f094e18ac2c62c4ca9bc6cec1dc6abe495fd66d6cd4602192a55b"},"schema_version":"1.0"},"canonical_sha256":"2900e13ad1208aba563fab3571778f4f29ec409d32930ed38ee05895153f7597","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:03:10.772628Z","signature_b64":"qYUTeE5nLpBjcS8eMSIK1Hl14Z/sl3rqdqRRAjG8Uw2MjAc6BigL0aAP798CEquaz++ykKzIeQv5Q9jZDQKBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2900e13ad1208aba563fab3571778f4f29ec409d32930ed38ee05895153f7597","last_reissued_at":"2026-07-05T11:03:10.772091Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:03:10.772091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.09577","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":"2026-07-05T11:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dljUEcldSZP6nE61I46VJY3Pw5DovTN94pK8fcMPtFHPRmOraMpLORPuEQBXe7Wzx5p+N6HpCgyls6cfSXEqDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:08:57.471139Z"},"content_sha256":"cd0fe16624aa5a675b74f4c6afc635829cf02a3591830d3786830bf8d6779c44","schema_version":"1.0","event_id":"sha256:cd0fe16624aa5a675b74f4c6afc635829cf02a3591830d3786830bf8d6779c44"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:FEAOCOWRECFLUVR7VM2XC54PJ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Chaofan Zhang, Peng Hao, Shaowei Cui, Shuo Wang, Xiaoge Cao, Xiaoshuai Hao","submitted_at":"2025-05-14T17:29:35Z","abstract_excerpt":"While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place scenarios. To bridge this gap, we introduce Vision-Tactile-Language-Action model, a novel framework that enables robust policy generation in contact-intensive scenarios by effectively integrating visual and tactile inputs through cross-modal language grounding. A low-cost, multi-modal dataset has been constructed in a simulation environment, containing vision-tactile"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09577","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/2505.09577/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":"2026-07-05T11:03:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sGsyXEOYDw4ZnNNcgj0SnhRHHBofgHymOvlt2CFBiJkBqwga/Oibr48L7L15R3jAjtQt/WC1GOu18yFZ6X8NBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:08:57.471826Z"},"content_sha256":"67e30697ba1e5283efc6b2cb6e9d9431d128c775214673496a0c8321f893a326","schema_version":"1.0","event_id":"sha256:67e30697ba1e5283efc6b2cb6e9d9431d128c775214673496a0c8321f893a326"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/bundle.json","state_url":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/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":"2026-08-06T06:08:57Z","links":{"resolver":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4","bundle":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/bundle.json","state":"https://pith.science/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FEAOCOWRECFLUVR7VM2XC54PJ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:FEAOCOWRECFLUVR7VM2XC54PJ4","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":"0ba518deef6f094e18ac2c62c4ca9bc6cec1dc6abe495fd66d6cd4602192a55b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:29:35Z","title_canon_sha256":"4c82b137251e5e6ef7b706f89d86c5086eb8adaf68aef3cd23e986ef7437e2de"},"schema_version":"1.0","source":{"id":"2505.09577","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.09577","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"arxiv_version","alias_value":"2505.09577v1","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09577","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"pith_short_12","alias_value":"FEAOCOWRECFL","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"pith_short_16","alias_value":"FEAOCOWRECFLUVR7","created_at":"2026-07-05T11:03:10Z"},{"alias_kind":"pith_short_8","alias_value":"FEAOCOWR","created_at":"2026-07-05T11:03:10Z"}],"graph_snapshots":[{"event_id":"sha256:67e30697ba1e5283efc6b2cb6e9d9431d128c775214673496a0c8321f893a326","target":"graph","created_at":"2026-07-05T11:03:10Z","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/2505.09577/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While vision-language models have advanced significantly, their application in language-conditioned robotic manipulation is still underexplored, especially for contact-rich tasks that extend beyond visually dominant pick-and-place scenarios. To bridge this gap, we introduce Vision-Tactile-Language-Action model, a novel framework that enables robust policy generation in contact-intensive scenarios by effectively integrating visual and tactile inputs through cross-modal language grounding. A low-cost, multi-modal dataset has been constructed in a simulation environment, containing vision-tactile","authors_text":"Chaofan Zhang, Peng Hao, Shaowei Cui, Shuo Wang, Xiaoge Cao, Xiaoshuai Hao","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:29:35Z","title":"VTLA: Vision-Tactile-Language-Action Model with Preference Learning for Insertion Manipulation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09577","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:cd0fe16624aa5a675b74f4c6afc635829cf02a3591830d3786830bf8d6779c44","target":"record","created_at":"2026-07-05T11:03:10Z","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":"0ba518deef6f094e18ac2c62c4ca9bc6cec1dc6abe495fd66d6cd4602192a55b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.RO","submitted_at":"2025-05-14T17:29:35Z","title_canon_sha256":"4c82b137251e5e6ef7b706f89d86c5086eb8adaf68aef3cd23e986ef7437e2de"},"schema_version":"1.0","source":{"id":"2505.09577","kind":"arxiv","version":1}},"canonical_sha256":"2900e13ad1208aba563fab3571778f4f29ec409d32930ed38ee05895153f7597","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2900e13ad1208aba563fab3571778f4f29ec409d32930ed38ee05895153f7597","first_computed_at":"2026-07-05T11:03:10.772091Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:10.772091Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qYUTeE5nLpBjcS8eMSIK1Hl14Z/sl3rqdqRRAjG8Uw2MjAc6BigL0aAP798CEquaz++ykKzIeQv5Q9jZDQKBDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:10.772628Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.09577","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd0fe16624aa5a675b74f4c6afc635829cf02a3591830d3786830bf8d6779c44","sha256:67e30697ba1e5283efc6b2cb6e9d9431d128c775214673496a0c8321f893a326"],"state_sha256":"6319fa3bd16bd8dea916bd6d9c9a13678c0f8d7922520309754c47e358c748d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0jJCb1ZVLbBL75JB/+afYOGjFXAT3kgdJUE3kT1J9Z0y8/gpqyhkjVGHEUQGXmbIzv2z21lwM5Bp2saa2td6Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:08:57.476551Z","bundle_sha256":"dd3d2f179d6e38413ba9cdee280d69205ec93ecfa6355dacba137c6eee279502"}}