{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3DAQF37YGCP6BBQJCKQWIXLG5Y","short_pith_number":"pith:3DAQF37Y","schema_version":"1.0","canonical_sha256":"d8c102eff8309fe0860912a1645d66ee2a7f8ee718d3d1d5b07ab2da29d08f30","source":{"kind":"arxiv","id":"2607.09818","version":1},"attestation_state":"computed","paper":{"title":"TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chuanjie Lv, Hang Yu, Jiajun Lv, Jie Ren, Linpeng Peng, Ronghao Yu, Shengzhuo Yang, Yong Liu","submitted_at":"2026-07-10T07:06:02Z","abstract_excerpt":"Vision-language-action (VLA) models aim to understand natural-language instructions and visual observations, and to generate and execute corresponding actions as embodied agents. Recently, autoregressive token-based action generation has driven the development of many representative VLA models. However, this paradigm often reduces action generation to next-token prediction, thereby lacking explicit modeling of the spatiotemporal structure of action sequences and the disentanglement between vision-language representations and actions, which can limit performance in long-horizon and complex scen"},"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":"2607.09818","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-07-10T07:06:02Z","cross_cats_sorted":["cs.AI","cs.CV"],"title_canon_sha256":"5e07f846151b6f0348bd26f0038b4a96fb36db90b48ca426b60edad741d5e747","abstract_canon_sha256":"febaf5ee2da39e487d21527fd7002cf7bae79ad1d858b55b1a3f60452ebf6a1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T00:18:37.466114Z","signature_b64":"veHrTocAdMRet9upQMM9CBFb8p758aW8mWPUeOkhzGOiT7WLhl6gxKfZ0CBCGlqSV1CG9V8CLj6uuuXa2G66Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8c102eff8309fe0860912a1645d66ee2a7f8ee718d3d1d5b07ab2da29d08f30","last_reissued_at":"2026-07-14T00:18:37.465282Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T00:18:37.465282Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TS-Mask VLA: 2D Temporal-Spatial Masking for Vision-Language-Action Model with Effective Bridging","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV"],"primary_cat":"cs.RO","authors_text":"Chuanjie Lv, Hang Yu, Jiajun Lv, Jie Ren, Linpeng Peng, Ronghao Yu, Shengzhuo Yang, Yong Liu","submitted_at":"2026-07-10T07:06:02Z","abstract_excerpt":"Vision-language-action (VLA) models aim to understand natural-language instructions and visual observations, and to generate and execute corresponding actions as embodied agents. Recently, autoregressive token-based action generation has driven the development of many representative VLA models. However, this paradigm often reduces action generation to next-token prediction, thereby lacking explicit modeling of the spatiotemporal structure of action sequences and the disentanglement between vision-language representations and actions, which can limit performance in long-horizon and complex scen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.09818","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/2607.09818/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":"2607.09818","created_at":"2026-07-14T00:18:37.465720+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.09818v1","created_at":"2026-07-14T00:18:37.465720+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.09818","created_at":"2026-07-14T00:18:37.465720+00:00"},{"alias_kind":"pith_short_12","alias_value":"3DAQF37YGCP6","created_at":"2026-07-14T00:18:37.465720+00:00"},{"alias_kind":"pith_short_16","alias_value":"3DAQF37YGCP6BBQJ","created_at":"2026-07-14T00:18:37.465720+00:00"},{"alias_kind":"pith_short_8","alias_value":"3DAQF37Y","created_at":"2026-07-14T00:18:37.465720+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/3DAQF37YGCP6BBQJCKQWIXLG5Y","json":"https://pith.science/pith/3DAQF37YGCP6BBQJCKQWIXLG5Y.json","graph_json":"https://pith.science/api/pith-number/3DAQF37YGCP6BBQJCKQWIXLG5Y/graph.json","events_json":"https://pith.science/api/pith-number/3DAQF37YGCP6BBQJCKQWIXLG5Y/events.json","paper":"https://pith.science/paper/3DAQF37Y"},"agent_actions":{"view_html":"https://pith.science/pith/3DAQF37YGCP6BBQJCKQWIXLG5Y","download_json":"https://pith.science/pith/3DAQF37YGCP6BBQJCKQWIXLG5Y.json","view_paper":"https://pith.science/paper/3DAQF37Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.09818&json=true","fetch_graph":"https://pith.science/api/pith-number/3DAQF37YGCP6BBQJCKQWIXLG5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/3DAQF37YGCP6BBQJCKQWIXLG5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3DAQF37YGCP6BBQJCKQWIXLG5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3DAQF37YGCP6BBQJCKQWIXLG5Y/action/storage_attestation","attest_author":"https://pith.science/pith/3DAQF37YGCP6BBQJCKQWIXLG5Y/action/author_attestation","sign_citation":"https://pith.science/pith/3DAQF37YGCP6BBQJCKQWIXLG5Y/action/citation_signature","submit_replication":"https://pith.science/pith/3DAQF37YGCP6BBQJCKQWIXLG5Y/action/replication_record"}},"created_at":"2026-07-14T00:18:37.465720+00:00","updated_at":"2026-07-14T00:18:37.465720+00:00"}