{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:UJT3HDXM2QJBW3TKETNPZWJ7YS","short_pith_number":"pith:UJT3HDXM","canonical_record":{"source":{"id":"2004.14973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-30T17:22:40Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"a3df957b0d4b2b48f1b0cc9adb7d02a09a682ef100c5c139b9ccd0ee97d180e4","abstract_canon_sha256":"240de43c8afd8c9f4767011da875285712730023440caabc85760d6b1707dfce"},"schema_version":"1.0"},"canonical_sha256":"a267b38eecd4121b6e6a24dafcd93fc49024e73fe00aa7170b535ef78a7532db","source":{"kind":"arxiv","id":"2004.14973","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14973","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14973v2","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14973","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"UJT3HDXM2QJB","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_16","alias_value":"UJT3HDXM2QJBW3TK","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_8","alias_value":"UJT3HDXM","created_at":"2026-07-05T00:59:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:UJT3HDXM2QJBW3TKETNPZWJ7YS","target":"record","payload":{"canonical_record":{"source":{"id":"2004.14973","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-30T17:22:40Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"a3df957b0d4b2b48f1b0cc9adb7d02a09a682ef100c5c139b9ccd0ee97d180e4","abstract_canon_sha256":"240de43c8afd8c9f4767011da875285712730023440caabc85760d6b1707dfce"},"schema_version":"1.0"},"canonical_sha256":"a267b38eecd4121b6e6a24dafcd93fc49024e73fe00aa7170b535ef78a7532db","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:59:37.166068Z","signature_b64":"iyUdhLhNV1irGvrs2quaoRdJn5Y01rkKfNJnOL6LewTkNyX8B8aAdlZoT9QvZwMZXuQSDlSjkcIG/eRHOcXtBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a267b38eecd4121b6e6a24dafcd93fc49024e73fe00aa7170b535ef78a7532db","last_reissued_at":"2026-07-05T00:59:37.165645Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:59:37.165645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.14973","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z8QmJMC7NrZ0TuCZEeOfR36W/TC+FcCPkEyxCZCuhal6zyfqReIx9iIPA01gj2NE6B3IqwdjdHBbRqvZpjtVBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:18:45.749679Z"},"content_sha256":"28881ab3e408fc644b5ef81f1a076327ebbbc557945a7ed3faa0c4278f8bf1ac","schema_version":"1.0","event_id":"sha256:28881ab3e408fc644b5ef81f1a076327ebbbc557945a7ed3faa0c4278f8bf1ac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:UJT3HDXM2QJBW3TKETNPZWJ7YS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Arjun Majumdar, Ayush Shrivastava, Devi Parikh, Dhruv Batra, Peter Anderson, Stefan Lee","submitted_at":"2020-04-30T17:22:40Z","abstract_excerpt":"Following a navigation instruction such as 'Walk down the stairs and stop at the brown sofa' requires embodied AI agents to ground scene elements referenced via language (e.g. 'stairs') to visual content in the environment (pixels corresponding to 'stairs').\n  We ask the following question -- can we leverage abundant 'disembodied' web-scraped vision-and-language corpora (e.g. Conceptual Captions) to learn visual groundings (what do 'stairs' look like?) that improve performance on a relatively data-starved embodied perception task (Vision-and-Language Navigation)? Specifically, we develop VLN-B"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14973","kind":"arxiv","version":2},"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/2004.14973/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":"2026-07-05T00:59:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rqHKhpf4U+9oufdQHOb7iycCHbP+OtnYCsxvT3YNj+c4MQUZPhR77w5ZHkhpbHrVsMj6/Vo/UCMZ//wYdoIKCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T06:18:45.750048Z"},"content_sha256":"18c06f039a3cbc4fb9840c723d5aada30d7351417d776f83c41d1d39893b2b1b","schema_version":"1.0","event_id":"sha256:18c06f039a3cbc4fb9840c723d5aada30d7351417d776f83c41d1d39893b2b1b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UJT3HDXM2QJBW3TKETNPZWJ7YS/bundle.json","state_url":"https://pith.science/pith/UJT3HDXM2QJBW3TKETNPZWJ7YS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UJT3HDXM2QJBW3TKETNPZWJ7YS/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":"2026-07-07T06:18:45Z","links":{"resolver":"https://pith.science/pith/UJT3HDXM2QJBW3TKETNPZWJ7YS","bundle":"https://pith.science/pith/UJT3HDXM2QJBW3TKETNPZWJ7YS/bundle.json","state":"https://pith.science/pith/UJT3HDXM2QJBW3TKETNPZWJ7YS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UJT3HDXM2QJBW3TKETNPZWJ7YS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:UJT3HDXM2QJBW3TKETNPZWJ7YS","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":"240de43c8afd8c9f4767011da875285712730023440caabc85760d6b1707dfce","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-30T17:22:40Z","title_canon_sha256":"a3df957b0d4b2b48f1b0cc9adb7d02a09a682ef100c5c139b9ccd0ee97d180e4"},"schema_version":"1.0","source":{"id":"2004.14973","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.14973","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"arxiv_version","alias_value":"2004.14973v2","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.14973","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_12","alias_value":"UJT3HDXM2QJB","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_16","alias_value":"UJT3HDXM2QJBW3TK","created_at":"2026-07-05T00:59:37Z"},{"alias_kind":"pith_short_8","alias_value":"UJT3HDXM","created_at":"2026-07-05T00:59:37Z"}],"graph_snapshots":[{"event_id":"sha256:18c06f039a3cbc4fb9840c723d5aada30d7351417d776f83c41d1d39893b2b1b","target":"graph","created_at":"2026-07-05T00:59:37Z","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/2004.14973/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Following a navigation instruction such as 'Walk down the stairs and stop at the brown sofa' requires embodied AI agents to ground scene elements referenced via language (e.g. 'stairs') to visual content in the environment (pixels corresponding to 'stairs').\n  We ask the following question -- can we leverage abundant 'disembodied' web-scraped vision-and-language corpora (e.g. Conceptual Captions) to learn visual groundings (what do 'stairs' look like?) that improve performance on a relatively data-starved embodied perception task (Vision-and-Language Navigation)? Specifically, we develop VLN-B","authors_text":"Arjun Majumdar, Ayush Shrivastava, Devi Parikh, Dhruv Batra, Peter Anderson, Stefan Lee","cross_cats":["cs.AI","cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-30T17:22:40Z","title":"Improving Vision-and-Language Navigation with Image-Text Pairs from the Web"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.14973","kind":"arxiv","version":2},"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":"sha256:28881ab3e408fc644b5ef81f1a076327ebbbc557945a7ed3faa0c4278f8bf1ac","target":"record","created_at":"2026-07-05T00:59:37Z","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":"240de43c8afd8c9f4767011da875285712730023440caabc85760d6b1707dfce","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-04-30T17:22:40Z","title_canon_sha256":"a3df957b0d4b2b48f1b0cc9adb7d02a09a682ef100c5c139b9ccd0ee97d180e4"},"schema_version":"1.0","source":{"id":"2004.14973","kind":"arxiv","version":2}},"canonical_sha256":"a267b38eecd4121b6e6a24dafcd93fc49024e73fe00aa7170b535ef78a7532db","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a267b38eecd4121b6e6a24dafcd93fc49024e73fe00aa7170b535ef78a7532db","first_computed_at":"2026-07-05T00:59:37.165645Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:59:37.165645Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iyUdhLhNV1irGvrs2quaoRdJn5Y01rkKfNJnOL6LewTkNyX8B8aAdlZoT9QvZwMZXuQSDlSjkcIG/eRHOcXtBg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:59:37.166068Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.14973","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28881ab3e408fc644b5ef81f1a076327ebbbc557945a7ed3faa0c4278f8bf1ac","sha256:18c06f039a3cbc4fb9840c723d5aada30d7351417d776f83c41d1d39893b2b1b"],"state_sha256":"8c9037e12643681785bf32264111bc0c79b3c294bf52a2df247a27d49a0bcfe8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p5AMu8QJdozJQbiKZiLpZ9nB2xBjPw1g0i2wAh69LLBEwF9gz5aPWCa4UAcVQBJuThJu/kRt4kgEvBB9SRiWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T06:18:45.751967Z","bundle_sha256":"4315a888fec2466700da09b3bf8ea8871b4878b1028c2388efd4269807d9b91f"}}