{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:Y4IJ3YGVEANK2T7YDSFX6I4ZPQ","short_pith_number":"pith:Y4IJ3YGV","schema_version":"1.0","canonical_sha256":"c7109de0d5201aad4ff81c8b7f23997c29c500c775f9d426c2e8193581ded0bc","source":{"kind":"arxiv","id":"2606.01621","version":1},"attestation_state":"computed","paper":{"title":"Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chen Lv, Hang Xu, Jingfan Tang, Jinxi He, Ji Zhang, Muyi Bao, Wenshan Wang, Yaqi Xie, Yuxin Cai, Zongtai Li","submitted_at":"2026-06-01T03:12:58Z","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"},"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":"2606.01621","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-06-01T03:12:58Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"c483e345076de920924a08cdee262b03ff7182b9fcbfbca2659867526dcd4b61","abstract_canon_sha256":"2babfd8908b96f9ff9e92b59d351a4b2f0d597bbad54cec0fe70b36b4c560160"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:38.305742Z","signature_b64":"WfNPkoohY5MusY2kRDAzYXRKxMM3I3fuqU8eTHUJAytQrMz7vx8dVUO5BObLwy1YD1eNjAmcDHo00NMmFBhAAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7109de0d5201aad4ff81c8b7f23997c29c500c775f9d426c2e8193581ded0bc","last_reissued_at":"2026-06-02T02:04:38.305348Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:38.305348Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Goal2Pixel: Grounding Goals to Pixels for Vision-Language Navigation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Chen Lv, Hang Xu, Jingfan Tang, Jinxi He, Ji Zhang, Muyi Bao, Wenshan Wang, Yaqi Xie, Yuxin Cai, Zongtai Li","submitted_at":"2026-06-01T03:12:58Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01621","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/2606.01621/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":"2606.01621","created_at":"2026-06-02T02:04:38.305405+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01621v1","created_at":"2026-06-02T02:04:38.305405+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01621","created_at":"2026-06-02T02:04:38.305405+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y4IJ3YGVEANK","created_at":"2026-06-02T02:04:38.305405+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y4IJ3YGVEANK2T7Y","created_at":"2026-06-02T02:04:38.305405+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y4IJ3YGV","created_at":"2026-06-02T02:04:38.305405+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/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ","json":"https://pith.science/pith/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ.json","graph_json":"https://pith.science/api/pith-number/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ/graph.json","events_json":"https://pith.science/api/pith-number/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ/events.json","paper":"https://pith.science/paper/Y4IJ3YGV"},"agent_actions":{"view_html":"https://pith.science/pith/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ","download_json":"https://pith.science/pith/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ.json","view_paper":"https://pith.science/paper/Y4IJ3YGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01621&json=true","fetch_graph":"https://pith.science/api/pith-number/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ/action/storage_attestation","attest_author":"https://pith.science/pith/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ/action/author_attestation","sign_citation":"https://pith.science/pith/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ/action/citation_signature","submit_replication":"https://pith.science/pith/Y4IJ3YGVEANK2T7YDSFX6I4ZPQ/action/replication_record"}},"created_at":"2026-06-02T02:04:38.305405+00:00","updated_at":"2026-06-02T02:04:38.305405+00:00"}