{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6W546EFX6KP7RNXN7SELJIPDBA","short_pith_number":"pith:6W546EFX","schema_version":"1.0","canonical_sha256":"f5bbcf10b7f29ff8b6edfc88b4a1e308177ccf14654f2fa2b059f339be79774f","source":{"kind":"arxiv","id":"2404.10241","version":1},"attestation_state":"computed","paper":{"title":"Vision-and-Language Navigation via Causal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengju Liu, Liuyi Wang, Mengjiao Shen, Qijun Chen, Ronghao Dang, Zongtao He","submitted_at":"2024-04-16T02:40:35Z","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"},"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":"2404.10241","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T02:40:35Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"ff1f7cfeafabae251c5332042e5c87aa6b742a9a9d68a4cbebc61d31bf41e64c","abstract_canon_sha256":"de0c89cf52dd61a9228309cc2349b27adbd67f9e88a705873e153594a7774fa1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:27.364106Z","signature_b64":"qBAKiXLUUug+NSnwjeMeVTTop3fKno+2t3V5UFySJ/R2yJ9QC4gNIUcXftgOVVNqLtkSMPW4FwKPIhUXx07tCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5bbcf10b7f29ff8b6edfc88b4a1e308177ccf14654f2fa2b059f339be79774f","last_reissued_at":"2026-07-05T08:08:27.363699Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:27.363699Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Vision-and-Language Navigation via Causal Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chengju Liu, Liuyi Wang, Mengjiao Shen, Qijun Chen, Ronghao Dang, Zongtao He","submitted_at":"2024-04-16T02:40:35Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10241","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/2404.10241/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":"2404.10241","created_at":"2026-07-05T08:08:27.363757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.10241v1","created_at":"2026-07-05T08:08:27.363757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10241","created_at":"2026-07-05T08:08:27.363757+00:00"},{"alias_kind":"pith_short_12","alias_value":"6W546EFX6KP7","created_at":"2026-07-05T08:08:27.363757+00:00"},{"alias_kind":"pith_short_16","alias_value":"6W546EFX6KP7RNXN","created_at":"2026-07-05T08:08:27.363757+00:00"},{"alias_kind":"pith_short_8","alias_value":"6W546EFX","created_at":"2026-07-05T08:08:27.363757+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/6W546EFX6KP7RNXN7SELJIPDBA","json":"https://pith.science/pith/6W546EFX6KP7RNXN7SELJIPDBA.json","graph_json":"https://pith.science/api/pith-number/6W546EFX6KP7RNXN7SELJIPDBA/graph.json","events_json":"https://pith.science/api/pith-number/6W546EFX6KP7RNXN7SELJIPDBA/events.json","paper":"https://pith.science/paper/6W546EFX"},"agent_actions":{"view_html":"https://pith.science/pith/6W546EFX6KP7RNXN7SELJIPDBA","download_json":"https://pith.science/pith/6W546EFX6KP7RNXN7SELJIPDBA.json","view_paper":"https://pith.science/paper/6W546EFX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.10241&json=true","fetch_graph":"https://pith.science/api/pith-number/6W546EFX6KP7RNXN7SELJIPDBA/graph.json","fetch_events":"https://pith.science/api/pith-number/6W546EFX6KP7RNXN7SELJIPDBA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6W546EFX6KP7RNXN7SELJIPDBA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6W546EFX6KP7RNXN7SELJIPDBA/action/storage_attestation","attest_author":"https://pith.science/pith/6W546EFX6KP7RNXN7SELJIPDBA/action/author_attestation","sign_citation":"https://pith.science/pith/6W546EFX6KP7RNXN7SELJIPDBA/action/citation_signature","submit_replication":"https://pith.science/pith/6W546EFX6KP7RNXN7SELJIPDBA/action/replication_record"}},"created_at":"2026-07-05T08:08:27.363757+00:00","updated_at":"2026-07-05T08:08:27.363757+00:00"}