{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:Y4IJ3YGVEANK2T7YDSFX6I4ZPQ","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":"2babfd8908b96f9ff9e92b59d351a4b2f0d597bbad54cec0fe70b36b4c560160","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:58Z","title_canon_sha256":"c483e345076de920924a08cdee262b03ff7182b9fcbfbca2659867526dcd4b61"},"schema_version":"1.0","source":{"id":"2606.01621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.01621","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"arxiv_version","alias_value":"2606.01621v1","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01621","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_12","alias_value":"Y4IJ3YGVEANK","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_16","alias_value":"Y4IJ3YGVEANK2T7Y","created_at":"2026-06-02T02:04:38Z"},{"alias_kind":"pith_short_8","alias_value":"Y4IJ3YGV","created_at":"2026-06-02T02:04:38Z"}],"graph_snapshots":[{"event_id":"sha256:4a4ca3918d26329a6e84acaf62587b8cdabb55f71e9178ef7caf6d79fe6cfaa8","target":"graph","created_at":"2026-06-02T02:04:38Z","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/2606.01621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-language models (VLMs) have become a common foundation for vision-and-language navigation in continuous environments (VLN-CE). Yet most VLM-based methods cast navigation as low-level action prediction, an interface that is ambiguous, tied to short-horizon motion primitives, and inefficient due to repeated VLM querying. We propose Goal2Pixel, a pure pixel-based paradigm that reformulates VLN-CE as navigable pixel grounding. Rather than predicting actions, Goal2Pixel uses the image plane as a unified spatial interface between VLM reasoning and robot motion: the model predicts a visible na","authors_text":"Chen Lv, Hang Xu, Jingfan Tang, Jinxi He, Ji Zhang, Muyi Bao, Wenshan Wang, Yaqi Xie, Yuxin Cai, Zongtai Li","cross_cats":["cs.RO"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:58Z","title":"Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01621","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":"sha256:8e1a246a3ccc3dcc01c38df8a0cc70e31a6c45df622082054202aec3cd0ada52","target":"record","created_at":"2026-06-02T02:04:38Z","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":"2babfd8908b96f9ff9e92b59d351a4b2f0d597bbad54cec0fe70b36b4c560160","cross_cats_sorted":["cs.RO"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:58Z","title_canon_sha256":"c483e345076de920924a08cdee262b03ff7182b9fcbfbca2659867526dcd4b61"},"schema_version":"1.0","source":{"id":"2606.01621","kind":"arxiv","version":1}},"canonical_sha256":"c7109de0d5201aad4ff81c8b7f23997c29c500c775f9d426c2e8193581ded0bc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7109de0d5201aad4ff81c8b7f23997c29c500c775f9d426c2e8193581ded0bc","first_computed_at":"2026-06-02T02:04:38.305348Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T02:04:38.305348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WfNPkoohY5MusY2kRDAzYXRKxMM3I3fuqU8eTHUJAytQrMz7vx8dVUO5BObLwy1YD1eNjAmcDHo00NMmFBhAAQ==","signature_status":"signed_v1","signed_at":"2026-06-02T02:04:38.305742Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.01621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e1a246a3ccc3dcc01c38df8a0cc70e31a6c45df622082054202aec3cd0ada52","sha256:4a4ca3918d26329a6e84acaf62587b8cdabb55f71e9178ef7caf6d79fe6cfaa8"],"state_sha256":"daf3033ceb35afde41d7c70289d84a43892d004d53d05fae4b20404fa593ee3a"}