{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SQYMHGI4U6RXIJUW7D5OV2IG4G","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":"c2f0c8787d081fa679531c23df51a52c098bebc74f777da4febe61aecb4bcf21","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T19:47:25Z","title_canon_sha256":"346752f3b5a0b469d48b6568cc7b0de502d9fdc23a0b5f5b7d94258ffe506383"},"schema_version":"1.0","source":{"id":"2509.00210","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00210","created_at":"2026-07-05T12:02:11Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00210v1","created_at":"2026-07-05T12:02:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00210","created_at":"2026-07-05T12:02:11Z"},{"alias_kind":"pith_short_12","alias_value":"SQYMHGI4U6RX","created_at":"2026-07-05T12:02:11Z"},{"alias_kind":"pith_short_16","alias_value":"SQYMHGI4U6RXIJUW","created_at":"2026-07-05T12:02:11Z"},{"alias_kind":"pith_short_8","alias_value":"SQYMHGI4","created_at":"2026-07-05T12:02:11Z"}],"graph_snapshots":[{"event_id":"sha256:2b0d9da6c800bdd098e60afbdf035049942a417e085eb38c8b1005b9985f430d","target":"graph","created_at":"2026-07-05T12:02:11Z","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/2509.00210/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Achieving human-like reasoning in deep learning models for complex tasks in unknown environments remains a critical challenge in embodied intelligence. While advanced vision-language models (VLMs) excel in static scene understanding, their limitations in spatio-temporal reasoning and adaptation to dynamic, open-set tasks like task-oriented navigation and embodied question answering (EQA) persist due to inadequate modeling of fine-grained spatio-temporal cues and physical world comprehension. To address this, we propose VEME, a novel cross-modal alignment method that enhances generalization in ","authors_text":"Jinzhou Tang, Jusheng Zhang, Qinhan Lv, Sidi Liu, Waikit Xiu, Xiying Li","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T19:47:25Z","title":"Beyond Pixels: Introducing Geometric-Semantic World Priors for Video-based Embodied Models via Spatio-temporal Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00210","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:c450bbff56b5819970c8fd60cc7272ef72009267aa4d9a7dd754d0e4ab96e590","target":"record","created_at":"2026-07-05T12:02:11Z","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":"c2f0c8787d081fa679531c23df51a52c098bebc74f777da4febe61aecb4bcf21","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-29T19:47:25Z","title_canon_sha256":"346752f3b5a0b469d48b6568cc7b0de502d9fdc23a0b5f5b7d94258ffe506383"},"schema_version":"1.0","source":{"id":"2509.00210","kind":"arxiv","version":1}},"canonical_sha256":"9430c3991ca7a3742696f8faeae906e191bb084a416b3e91fbcc07bb20fb39aa","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9430c3991ca7a3742696f8faeae906e191bb084a416b3e91fbcc07bb20fb39aa","first_computed_at":"2026-07-05T12:02:11.293986Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:11.293986Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RDn5EJ6fIyLkhQPy5zTO5U7Vs83fFAeiXbqS7qf4Y9SBO+Gw5SOupkf0zWbQUGJdRR3BRDty86tsSa4xkw6xDg==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:11.294454Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00210","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c450bbff56b5819970c8fd60cc7272ef72009267aa4d9a7dd754d0e4ab96e590","sha256:2b0d9da6c800bdd098e60afbdf035049942a417e085eb38c8b1005b9985f430d"],"state_sha256":"6a5adc684b15aea9495bd0794a64e313ca208eafec08e71c83710aeb03e66536"}