{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:V675CFJCUEICX7WANCZH4Q2IUG","short_pith_number":"pith:V675CFJC","canonical_record":{"source":{"id":"2404.01994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T14:40:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3784ba8c61c6aa512d95d0c26d01e52cea866d7bb7a687b5fb90b0915756d105","abstract_canon_sha256":"942ad7f3a6af8e083700d074a46d1415e9fc2f674b88bdb21db652138262a845"},"schema_version":"1.0"},"canonical_sha256":"afbfd11522a1102bfec068b27e4348a195f0a10f5172e14bdad8938b8fbdb655","source":{"kind":"arxiv","id":"2404.01994","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01994","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01994v1","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01994","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"V675CFJCUEIC","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"V675CFJCUEICX7WA","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"V675CFJC","created_at":"2026-07-05T08:03:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:V675CFJCUEICX7WANCZH4Q2IUG","target":"record","payload":{"canonical_record":{"source":{"id":"2404.01994","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T14:40:04Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"3784ba8c61c6aa512d95d0c26d01e52cea866d7bb7a687b5fb90b0915756d105","abstract_canon_sha256":"942ad7f3a6af8e083700d074a46d1415e9fc2f674b88bdb21db652138262a845"},"schema_version":"1.0"},"canonical_sha256":"afbfd11522a1102bfec068b27e4348a195f0a10f5172e14bdad8938b8fbdb655","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:03:34.584211Z","signature_b64":"IrXQE8N9Kq06sJf5QovrrZkKtl7IU7yQY7MymiAUnvmBKUCHM3vDxAfqa9O8eISn92fIfQgSxsRq7P3ErONaDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"afbfd11522a1102bfec068b27e4348a195f0a10f5172e14bdad8938b8fbdb655","last_reissued_at":"2026-07-05T08:03:34.583743Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:03:34.583743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.01994","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fv7sjA4JmDqZuqGKg7S/mRGU1rTbL7bWi8/LOYqpkLhsA2ZZd3R6GfMrRGnzOQlU+r298Gnbs782sSLAxgOfBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T06:31:39.312015Z"},"content_sha256":"3f97dc82cbf7008717e8385836b040c01485bc6361b77677639c9b80ea8169c5","schema_version":"1.0","event_id":"sha256:3f97dc82cbf7008717e8385836b040c01485bc6361b77677639c9b80ea8169c5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:V675CFJCUEICX7WANCZH4Q2IUG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Binhao Wu, Jiwen Zhang, Mengfei Du, Ruipu Luo, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","submitted_at":"2024-04-02T14:40:04Z","abstract_excerpt":"Vision-and-Language navigation (VLN) requires an agent to navigate in unseen environment by following natural language instruction. For task completion, the agent needs to align and integrate various navigation modalities, including instruction, observation and navigation history. Existing works primarily concentrate on cross-modal attention at the fusion stage to achieve this objective. Nevertheless, modality features generated by disparate uni-encoders reside in their own spaces, leading to a decline in the quality of cross-modal fusion and decision. To address this problem, we propose a Dua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01994","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/2404.01994/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:03:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eofw1uRr07qRqVbGurV6Y374H/uFWQ5GqOT+6ag1+r68W2SRQCxRGlsaYbRPDnDv1264hCFa7Ykw5VVBNoh6Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-13T06:31:39.312409Z"},"content_sha256":"91ce173e622d6bbfc92a6f8b5597199a0db4cd903f93b7e57ec8726bd12f7909","schema_version":"1.0","event_id":"sha256:91ce173e622d6bbfc92a6f8b5597199a0db4cd903f93b7e57ec8726bd12f7909"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/V675CFJCUEICX7WANCZH4Q2IUG/bundle.json","state_url":"https://pith.science/pith/V675CFJCUEICX7WANCZH4Q2IUG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/V675CFJCUEICX7WANCZH4Q2IUG/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-13T06:31:39Z","links":{"resolver":"https://pith.science/pith/V675CFJCUEICX7WANCZH4Q2IUG","bundle":"https://pith.science/pith/V675CFJCUEICX7WANCZH4Q2IUG/bundle.json","state":"https://pith.science/pith/V675CFJCUEICX7WANCZH4Q2IUG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/V675CFJCUEICX7WANCZH4Q2IUG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:V675CFJCUEICX7WANCZH4Q2IUG","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":"942ad7f3a6af8e083700d074a46d1415e9fc2f674b88bdb21db652138262a845","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T14:40:04Z","title_canon_sha256":"3784ba8c61c6aa512d95d0c26d01e52cea866d7bb7a687b5fb90b0915756d105"},"schema_version":"1.0","source":{"id":"2404.01994","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.01994","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"arxiv_version","alias_value":"2404.01994v1","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.01994","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"pith_short_12","alias_value":"V675CFJCUEIC","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"pith_short_16","alias_value":"V675CFJCUEICX7WA","created_at":"2026-07-05T08:03:34Z"},{"alias_kind":"pith_short_8","alias_value":"V675CFJC","created_at":"2026-07-05T08:03:34Z"}],"graph_snapshots":[{"event_id":"sha256:91ce173e622d6bbfc92a6f8b5597199a0db4cd903f93b7e57ec8726bd12f7909","target":"graph","created_at":"2026-07-05T08:03:34Z","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/2404.01994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-Language navigation (VLN) requires an agent to navigate in unseen environment by following natural language instruction. For task completion, the agent needs to align and integrate various navigation modalities, including instruction, observation and navigation history. Existing works primarily concentrate on cross-modal attention at the fusion stage to achieve this objective. Nevertheless, modality features generated by disparate uni-encoders reside in their own spaces, leading to a decline in the quality of cross-modal fusion and decision. To address this problem, we propose a Dua","authors_text":"Binhao Wu, Jiwen Zhang, Mengfei Du, Ruipu Luo, Xuanjing Huang, Zejun Li, Zhihao Fan, Zhongyu Wei","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T14:40:04Z","title":"DELAN: Dual-Level Alignment for Vision-and-Language Navigation by Cross-Modal Contrastive Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.01994","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":"sha256:3f97dc82cbf7008717e8385836b040c01485bc6361b77677639c9b80ea8169c5","target":"record","created_at":"2026-07-05T08:03:34Z","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":"942ad7f3a6af8e083700d074a46d1415e9fc2f674b88bdb21db652138262a845","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-02T14:40:04Z","title_canon_sha256":"3784ba8c61c6aa512d95d0c26d01e52cea866d7bb7a687b5fb90b0915756d105"},"schema_version":"1.0","source":{"id":"2404.01994","kind":"arxiv","version":1}},"canonical_sha256":"afbfd11522a1102bfec068b27e4348a195f0a10f5172e14bdad8938b8fbdb655","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"afbfd11522a1102bfec068b27e4348a195f0a10f5172e14bdad8938b8fbdb655","first_computed_at":"2026-07-05T08:03:34.583743Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:03:34.583743Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IrXQE8N9Kq06sJf5QovrrZkKtl7IU7yQY7MymiAUnvmBKUCHM3vDxAfqa9O8eISn92fIfQgSxsRq7P3ErONaDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:03:34.584211Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.01994","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f97dc82cbf7008717e8385836b040c01485bc6361b77677639c9b80ea8169c5","sha256:91ce173e622d6bbfc92a6f8b5597199a0db4cd903f93b7e57ec8726bd12f7909"],"state_sha256":"2edcd8c75667d62030261ac73db4863c9b177bb4366039c1cf40b2d418aecdcb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BYkKvT5G/R60HUeXSvZdw/xQLa5nkAZL7XDeK9DM09+g96TYJZsmLT0sSCGMLkDFD0UjXxvIcONOxZhwq1wtBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-13T06:31:39.314802Z","bundle_sha256":"854c05fc33c73a8652f8aadca04008d3e6917fcecf332114d28151d413d8e22f"}}