{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:74DYU24LOKV4FRZ3EZ5O3YLUIB","short_pith_number":"pith:74DYU24L","canonical_record":{"source":{"id":"2501.18867","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T03:20:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09ecedf72a1981b181d96a35ec4dd501e7ed50301eaa757f3e9e512f60e9fee5","abstract_canon_sha256":"29fe6781ccdd5e088272c3dd956c7b6fa8144dd69137baf3bb8218e7f233afc7"},"schema_version":"1.0"},"canonical_sha256":"ff078a6b8b72abc2c73b267aede1744041de5ec3a37d57cff15d21bd5ee92156","source":{"kind":"arxiv","id":"2501.18867","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18867","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18867v3","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18867","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"74DYU24LOKV4","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"74DYU24LOKV4FRZ3","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"74DYU24L","created_at":"2026-07-05T11:27:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:74DYU24LOKV4FRZ3EZ5O3YLUIB","target":"record","payload":{"canonical_record":{"source":{"id":"2501.18867","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T03:20:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"09ecedf72a1981b181d96a35ec4dd501e7ed50301eaa757f3e9e512f60e9fee5","abstract_canon_sha256":"29fe6781ccdd5e088272c3dd956c7b6fa8144dd69137baf3bb8218e7f233afc7"},"schema_version":"1.0"},"canonical_sha256":"ff078a6b8b72abc2c73b267aede1744041de5ec3a37d57cff15d21bd5ee92156","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:23.680840Z","signature_b64":"+BWMRb9DGqKyUR4FKJgUIL14hvuBLO+GcDIR9X2S0Zrb+mYJ9lWOYJJQjmFLrlvd+BgFCtBmmFvDyVLdVrn2DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ff078a6b8b72abc2c73b267aede1744041de5ec3a37d57cff15d21bd5ee92156","last_reissued_at":"2026-07-05T11:27:23.680332Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:23.680332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2501.18867","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aViT+159bghYfvXmaUqnfduy4EOxYoft8Zvjzma4p0U4aK1+BdqVg3s11dcgMxXwMcjwsglzejFlH5KurVeSDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:27:43.098613Z"},"content_sha256":"be197e8d79e8662c53b18a0f3c2bcfe3810cd7bbb681d2b7359a6df32f45eddc","schema_version":"1.0","event_id":"sha256:be197e8d79e8662c53b18a0f3c2bcfe3810cd7bbb681d2b7359a6df32f45eddc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:74DYU24LOKV4FRZ3EZ5O3YLUIB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jianke Zhang, Jianyu Chen, Xiang Zhu, Xiaoyu Chen, Yanjiang Guo, Yucheng Hu","submitted_at":"2025-01-31T03:20:09Z","abstract_excerpt":"Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-trained on vision-language understanding tasks, provide rich semantic knowledge and reasoning abilities. However, prior research has shown that VLMs often focus on high-level semantic content and neglect low-level features, limiting their ability to capture detailed spatial information and understand physical dynamics. These aspects, which are crucial for embodied control tasks, remain underexplored in existing pre-t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18867","kind":"arxiv","version":3},"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/2501.18867/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":"2026-07-05T11:27:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JLPlCA7HRrxLb3RnF36enLPixhgum6JnUkjp8ivc6W9KrkadFhkEz+LT0MELFTN7iN1XUpFUeg8Gyh/yhwk5Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T07:27:43.099382Z"},"content_sha256":"0826b0cc7bad75784d08e3e649af4e69d2a58fee7a267131d6728bae3a49dfc9","schema_version":"1.0","event_id":"sha256:0826b0cc7bad75784d08e3e649af4e69d2a58fee7a267131d6728bae3a49dfc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/bundle.json","state_url":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/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":"2026-08-09T07:27:43Z","links":{"resolver":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB","bundle":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/bundle.json","state":"https://pith.science/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/74DYU24LOKV4FRZ3EZ5O3YLUIB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:74DYU24LOKV4FRZ3EZ5O3YLUIB","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":"29fe6781ccdd5e088272c3dd956c7b6fa8144dd69137baf3bb8218e7f233afc7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T03:20:09Z","title_canon_sha256":"09ecedf72a1981b181d96a35ec4dd501e7ed50301eaa757f3e9e512f60e9fee5"},"schema_version":"1.0","source":{"id":"2501.18867","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2501.18867","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"arxiv_version","alias_value":"2501.18867v3","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.18867","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"pith_short_12","alias_value":"74DYU24LOKV4","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"pith_short_16","alias_value":"74DYU24LOKV4FRZ3","created_at":"2026-07-05T11:27:23Z"},{"alias_kind":"pith_short_8","alias_value":"74DYU24L","created_at":"2026-07-05T11:27:23Z"}],"graph_snapshots":[{"event_id":"sha256:0826b0cc7bad75784d08e3e649af4e69d2a58fee7a267131d6728bae3a49dfc9","target":"graph","created_at":"2026-07-05T11:27:23Z","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/2501.18867/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in Vision-Language-Action (VLA) models have leveraged pre-trained Vision-Language Models (VLMs) to improve the generalization capabilities. VLMs, typically pre-trained on vision-language understanding tasks, provide rich semantic knowledge and reasoning abilities. However, prior research has shown that VLMs often focus on high-level semantic content and neglect low-level features, limiting their ability to capture detailed spatial information and understand physical dynamics. These aspects, which are crucial for embodied control tasks, remain underexplored in existing pre-t","authors_text":"Jianke Zhang, Jianyu Chen, Xiang Zhu, Xiaoyu Chen, Yanjiang Guo, Yucheng Hu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T03:20:09Z","title":"UP-VLA: A Unified Understanding and Prediction Model for Embodied Agent"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.18867","kind":"arxiv","version":3},"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:be197e8d79e8662c53b18a0f3c2bcfe3810cd7bbb681d2b7359a6df32f45eddc","target":"record","created_at":"2026-07-05T11:27:23Z","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":"29fe6781ccdd5e088272c3dd956c7b6fa8144dd69137baf3bb8218e7f233afc7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-01-31T03:20:09Z","title_canon_sha256":"09ecedf72a1981b181d96a35ec4dd501e7ed50301eaa757f3e9e512f60e9fee5"},"schema_version":"1.0","source":{"id":"2501.18867","kind":"arxiv","version":3}},"canonical_sha256":"ff078a6b8b72abc2c73b267aede1744041de5ec3a37d57cff15d21bd5ee92156","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ff078a6b8b72abc2c73b267aede1744041de5ec3a37d57cff15d21bd5ee92156","first_computed_at":"2026-07-05T11:27:23.680332Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:23.680332Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+BWMRb9DGqKyUR4FKJgUIL14hvuBLO+GcDIR9X2S0Zrb+mYJ9lWOYJJQjmFLrlvd+BgFCtBmmFvDyVLdVrn2DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:23.680840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2501.18867","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:be197e8d79e8662c53b18a0f3c2bcfe3810cd7bbb681d2b7359a6df32f45eddc","sha256:0826b0cc7bad75784d08e3e649af4e69d2a58fee7a267131d6728bae3a49dfc9"],"state_sha256":"5b47e6751430343f74317a400f8fb21096d07f6a9605a46658570b01907f79ac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lHKtXIdUx0bxsIL3hUpNLzLkAr7YCLWJlEdU1KR7Re5W7VDRCUDwRVUtC0OFEWrNHSzDthRpghsZk+r6pyhmAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T07:27:43.105812Z","bundle_sha256":"8f2db18bd98756522f4cee2cb8cb8ee428ca5796332ad755502bf1069619c630"}}