{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6W546EFX6KP7RNXN7SELJIPDBA","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":"de0c89cf52dd61a9228309cc2349b27adbd67f9e88a705873e153594a7774fa1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T02:40:35Z","title_canon_sha256":"ff1f7cfeafabae251c5332042e5c87aa6b742a9a9d68a4cbebc61d31bf41e64c"},"schema_version":"1.0","source":{"id":"2404.10241","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10241","created_at":"2026-07-05T08:08:27Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10241v1","created_at":"2026-07-05T08:08:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10241","created_at":"2026-07-05T08:08:27Z"},{"alias_kind":"pith_short_12","alias_value":"6W546EFX6KP7","created_at":"2026-07-05T08:08:27Z"},{"alias_kind":"pith_short_16","alias_value":"6W546EFX6KP7RNXN","created_at":"2026-07-05T08:08:27Z"},{"alias_kind":"pith_short_8","alias_value":"6W546EFX","created_at":"2026-07-05T08:08:27Z"}],"graph_snapshots":[{"event_id":"sha256:85d8d3bc3d64615e14e97f86fec94b95f1f4b4c6834d7c1ae520fd641a316991","target":"graph","created_at":"2026-07-05T08:08:27Z","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/2404.10241/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the pursuit of robust and generalizable environment perception and language understanding, the ubiquitous challenge of dataset bias continues to plague vision-and-language navigation (VLN) agents, hindering their performance in unseen environments. This paper introduces the generalized cross-modal causal transformer (GOAT), a pioneering solution rooted in the paradigm of causal inference. By delving into both observable and unobservable confounders within vision, language, and history, we propose the back-door and front-door adjustment causal learning (BACL and FACL) modules to promote unbi","authors_text":"Chengju Liu, Liuyi Wang, Mengjiao Shen, Qijun Chen, Ronghao Dang, Zongtao He","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T02:40:35Z","title":"Vision-and-Language Navigation via Causal Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10241","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:aebbe96ff999a60e08d6f9e971f0019a111c0ca61543212cfad7a25e78926929","target":"record","created_at":"2026-07-05T08:08:27Z","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":"de0c89cf52dd61a9228309cc2349b27adbd67f9e88a705873e153594a7774fa1","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T02:40:35Z","title_canon_sha256":"ff1f7cfeafabae251c5332042e5c87aa6b742a9a9d68a4cbebc61d31bf41e64c"},"schema_version":"1.0","source":{"id":"2404.10241","kind":"arxiv","version":1}},"canonical_sha256":"f5bbcf10b7f29ff8b6edfc88b4a1e308177ccf14654f2fa2b059f339be79774f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5bbcf10b7f29ff8b6edfc88b4a1e308177ccf14654f2fa2b059f339be79774f","first_computed_at":"2026-07-05T08:08:27.363699Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:27.363699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qBAKiXLUUug+NSnwjeMeVTTop3fKno+2t3V5UFySJ/R2yJ9QC4gNIUcXftgOVVNqLtkSMPW4FwKPIhUXx07tCA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:27.364106Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10241","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aebbe96ff999a60e08d6f9e971f0019a111c0ca61543212cfad7a25e78926929","sha256:85d8d3bc3d64615e14e97f86fec94b95f1f4b4c6834d7c1ae520fd641a316991"],"state_sha256":"0f57d1f6b3f923174ec99fd4962f12307a0da94fcbe8b64d636c78c1dd74e473"}