{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:EV3B2VJDFSY7Y7HUSVQCEZKPDP","short_pith_number":"pith:EV3B2VJD","canonical_record":{"source":{"id":"2107.07201","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-15T09:11:02Z","cross_cats_sorted":[],"title_canon_sha256":"ff90c6082874afec94138af9d0b0c69c7daf974f89627919743a5ce4e8a5e8a9","abstract_canon_sha256":"d11df8917668dad757556cec7f09341771fcbf0af093a93686b18ce46a3444db"},"schema_version":"1.0"},"canonical_sha256":"25761d55232cb1fc7cf4956022654f1bcfbfe325f88f08c9cb8d0acf7af25451","source":{"kind":"arxiv","id":"2107.07201","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.07201","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"2107.07201v3","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07201","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"EV3B2VJDFSY7","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"pith_short_16","alias_value":"EV3B2VJDFSY7Y7HU","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"pith_short_8","alias_value":"EV3B2VJD","created_at":"2026-07-05T03:00:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:EV3B2VJDFSY7Y7HUSVQCEZKPDP","target":"record","payload":{"canonical_record":{"source":{"id":"2107.07201","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-15T09:11:02Z","cross_cats_sorted":[],"title_canon_sha256":"ff90c6082874afec94138af9d0b0c69c7daf974f89627919743a5ce4e8a5e8a9","abstract_canon_sha256":"d11df8917668dad757556cec7f09341771fcbf0af093a93686b18ce46a3444db"},"schema_version":"1.0"},"canonical_sha256":"25761d55232cb1fc7cf4956022654f1bcfbfe325f88f08c9cb8d0acf7af25451","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:00:18.805397Z","signature_b64":"aEJ1jHdbrRCaU42CNyNms4A1PWxWCMiKXuKMywLNCnTyZTDkdRgm/gf6X88A63wvKDx6s/jMaCgUuEGuaZv+CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"25761d55232cb1fc7cf4956022654f1bcfbfe325f88f08c9cb8d0acf7af25451","last_reissued_at":"2026-07-05T03:00:18.804898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:00:18.804898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.07201","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:00:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"itL4hW5pZysHwyEJHTTJagm/v2ert9uy9sn3Vn4gCPrHhKJ8I54tk9Pn0z0n4SehqRqHFBO/HeAMtMJ9sETWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:28:36.397699Z"},"content_sha256":"057fcca34c07629eaa22180da575a8a785dee6bebfa3cd2c57a9ffd2f7116a6f","schema_version":"1.0","event_id":"sha256:057fcca34c07629eaa22180da575a8a785dee6bebfa3cd2c57a9ffd2f7116a6f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:EV3B2VJDFSY7Y7HUSVQCEZKPDP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neighbor-view Enhanced Model for Vision and Language Navigation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong An, Liang Wang, Qi Wu, Tieniu Tan, Yan Huang, Yuankai Qi","submitted_at":"2021-07-15T09:11:02Z","abstract_excerpt":"Vision and Language Navigation (VLN) requires an agent to navigate to a target location by following natural language instructions. Most of existing works represent a navigation candidate by the feature of the corresponding single view where the candidate lies in. However, an instruction may mention landmarks out of the single view as references, which might lead to failures of textual-visual matching of existing methods. In this work, we propose a multi-module Neighbor-View Enhanced Model (NvEM) to adaptively incorporate visual contexts from neighbor views for better textual-visual matching. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07201","kind":"arxiv","version":3},"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/2107.07201/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":"2026-07-05T03:00:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YBRP0/mI3RdXI3OJxNJPcLbsM9RmZFgt7LfdpM5G8a0R61nbQ7+nlys6EwLBaQ/AmKmcasyEHSm5BjU/t0zNAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T14:28:36.398029Z"},"content_sha256":"d3493d8b75a5a31226823ffb8cd9307eb044ee2d1675d924c508ac90a0ef237a","schema_version":"1.0","event_id":"sha256:d3493d8b75a5a31226823ffb8cd9307eb044ee2d1675d924c508ac90a0ef237a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EV3B2VJDFSY7Y7HUSVQCEZKPDP/bundle.json","state_url":"https://pith.science/pith/EV3B2VJDFSY7Y7HUSVQCEZKPDP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EV3B2VJDFSY7Y7HUSVQCEZKPDP/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":"2026-08-19T14:28:36Z","links":{"resolver":"https://pith.science/pith/EV3B2VJDFSY7Y7HUSVQCEZKPDP","bundle":"https://pith.science/pith/EV3B2VJDFSY7Y7HUSVQCEZKPDP/bundle.json","state":"https://pith.science/pith/EV3B2VJDFSY7Y7HUSVQCEZKPDP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EV3B2VJDFSY7Y7HUSVQCEZKPDP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:EV3B2VJDFSY7Y7HUSVQCEZKPDP","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":"d11df8917668dad757556cec7f09341771fcbf0af093a93686b18ce46a3444db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-15T09:11:02Z","title_canon_sha256":"ff90c6082874afec94138af9d0b0c69c7daf974f89627919743a5ce4e8a5e8a9"},"schema_version":"1.0","source":{"id":"2107.07201","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.07201","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"arxiv_version","alias_value":"2107.07201v3","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07201","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"pith_short_12","alias_value":"EV3B2VJDFSY7","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"pith_short_16","alias_value":"EV3B2VJDFSY7Y7HU","created_at":"2026-07-05T03:00:18Z"},{"alias_kind":"pith_short_8","alias_value":"EV3B2VJD","created_at":"2026-07-05T03:00:18Z"}],"graph_snapshots":[{"event_id":"sha256:d3493d8b75a5a31226823ffb8cd9307eb044ee2d1675d924c508ac90a0ef237a","target":"graph","created_at":"2026-07-05T03:00:18Z","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/2107.07201/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 to a target location by following natural language instructions. Most of existing works represent a navigation candidate by the feature of the corresponding single view where the candidate lies in. However, an instruction may mention landmarks out of the single view as references, which might lead to failures of textual-visual matching of existing methods. In this work, we propose a multi-module Neighbor-View Enhanced Model (NvEM) to adaptively incorporate visual contexts from neighbor views for better textual-visual matching. ","authors_text":"Dong An, Liang Wang, Qi Wu, Tieniu Tan, Yan Huang, Yuankai Qi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-15T09:11:02Z","title":"Neighbor-view Enhanced Model for Vision and Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07201","kind":"arxiv","version":3},"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":"sha256:057fcca34c07629eaa22180da575a8a785dee6bebfa3cd2c57a9ffd2f7116a6f","target":"record","created_at":"2026-07-05T03:00:18Z","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":"d11df8917668dad757556cec7f09341771fcbf0af093a93686b18ce46a3444db","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2021-07-15T09:11:02Z","title_canon_sha256":"ff90c6082874afec94138af9d0b0c69c7daf974f89627919743a5ce4e8a5e8a9"},"schema_version":"1.0","source":{"id":"2107.07201","kind":"arxiv","version":3}},"canonical_sha256":"25761d55232cb1fc7cf4956022654f1bcfbfe325f88f08c9cb8d0acf7af25451","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"25761d55232cb1fc7cf4956022654f1bcfbfe325f88f08c9cb8d0acf7af25451","first_computed_at":"2026-07-05T03:00:18.804898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:00:18.804898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aEJ1jHdbrRCaU42CNyNms4A1PWxWCMiKXuKMywLNCnTyZTDkdRgm/gf6X88A63wvKDx6s/jMaCgUuEGuaZv+CA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:00:18.805397Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.07201","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:057fcca34c07629eaa22180da575a8a785dee6bebfa3cd2c57a9ffd2f7116a6f","sha256:d3493d8b75a5a31226823ffb8cd9307eb044ee2d1675d924c508ac90a0ef237a"],"state_sha256":"0be4df90ff0e81d6907d6859455f948e09ec0fb6d2f7edc8b5da2fe7b0c0799b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CSXbPCe+cxHka+961HdBXAxyd/1SICfJGcZ8cl+NqBn0zPnYtxt0pr8sJDpQXkRccz6bYsqQqZBi3lozk8XjBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T14:28:36.401974Z","bundle_sha256":"2c643c9289260bb5d43fc3c0e32d259c9ea10405606916f290054042cdb055d7"}}