{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:O3O4L3VXQIZCPPFBM2XQOHSY23","short_pith_number":"pith:O3O4L3VX","canonical_record":{"source":{"id":"2201.10788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-26T07:43:47Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"78eb006a39e7a57c68cc389e503c67dea76127c3f503af51459080a7512d78aa","abstract_canon_sha256":"18c128ca7793d30b73c57506213f26a63aaa20ef5d4ab1b41ac05f1c3898800a"},"schema_version":"1.0"},"canonical_sha256":"76ddc5eeb7823227bca166af071e58d6f81faf8146d57c5ea66cf615a762897b","source":{"kind":"arxiv","id":"2201.10788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10788","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10788v1","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10788","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"O3O4L3VXQIZC","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"pith_short_16","alias_value":"O3O4L3VXQIZCPPFB","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"pith_short_8","alias_value":"O3O4L3VX","created_at":"2026-07-05T03:51:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:O3O4L3VXQIZCPPFBM2XQOHSY23","target":"record","payload":{"canonical_record":{"source":{"id":"2201.10788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-26T07:43:47Z","cross_cats_sorted":["cs.RO"],"title_canon_sha256":"78eb006a39e7a57c68cc389e503c67dea76127c3f503af51459080a7512d78aa","abstract_canon_sha256":"18c128ca7793d30b73c57506213f26a63aaa20ef5d4ab1b41ac05f1c3898800a"},"schema_version":"1.0"},"canonical_sha256":"76ddc5eeb7823227bca166af071e58d6f81faf8146d57c5ea66cf615a762897b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:51:49.672545Z","signature_b64":"zmnWeYCNvv/UUHnK9QzRiNgc5RH01tVebhH70oWh2bVmf4/vBBs9HjD05fE7LUbJZzFQuHkGlzLLOhodUgQRAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"76ddc5eeb7823227bca166af071e58d6f81faf8146d57c5ea66cf615a762897b","last_reissued_at":"2026-07-05T03:51:49.672146Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:51:49.672146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.10788","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":"2026-07-05T03:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RUH4/L9MdSz71SsMnr4jo3jWSRj62oEuAdhtSnww3Pr5ugLR0/jiWosENyV31NE4JJayDtyE5ByvBkOE5UPrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:51:28.811004Z"},"content_sha256":"3d9e9da3c12d65557a5f138f185e1b6cb530b2134ba2f4a4dae9d56f20505428","schema_version":"1.0","event_id":"sha256:3d9e9da3c12d65557a5f138f185e1b6cb530b2134ba2f4a4dae9d56f20505428"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:O3O4L3VXQIZCPPFBM2XQOHSY23","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Self-supervised 3D Semantic Representation Learning for Vision-and-Language Navigation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.RO"],"primary_cat":"cs.CV","authors_text":"Di Guo, Fuchun Sun, Huaping Liu, Mengmeng Ge, Sinan Tan","submitted_at":"2022-01-26T07:43:47Z","abstract_excerpt":"In the Vision-and-Language Navigation task, the embodied agent follows linguistic instructions and navigates to a specific goal. It is important in many practical scenarios and has attracted extensive attention from both computer vision and robotics communities. However, most existing works only use RGB images but neglect the 3D semantic information of the scene. To this end, we develop a novel self-supervised training framework to encode the voxel-level 3D semantic reconstruction into a 3D semantic representation. Specifically, a region query task is designed as the pretext task, which predic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10788","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/2201.10788/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":"2026-07-05T03:51:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T48Rzkz+PZy59h3lbOF14YGvH3ftm3HKYwpJBkoIDSmatLaEwQ/cpYf0FoUU7lglq5FhPN94fBccW9z+2Z31CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T17:51:28.811513Z"},"content_sha256":"39bb9a1c7f651ffee9dc05316ca78ac809021cfce462efd89b7b29ea073aee03","schema_version":"1.0","event_id":"sha256:39bb9a1c7f651ffee9dc05316ca78ac809021cfce462efd89b7b29ea073aee03"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O3O4L3VXQIZCPPFBM2XQOHSY23/bundle.json","state_url":"https://pith.science/pith/O3O4L3VXQIZCPPFBM2XQOHSY23/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O3O4L3VXQIZCPPFBM2XQOHSY23/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":"2026-08-19T17:51:28Z","links":{"resolver":"https://pith.science/pith/O3O4L3VXQIZCPPFBM2XQOHSY23","bundle":"https://pith.science/pith/O3O4L3VXQIZCPPFBM2XQOHSY23/bundle.json","state":"https://pith.science/pith/O3O4L3VXQIZCPPFBM2XQOHSY23/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O3O4L3VXQIZCPPFBM2XQOHSY23/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:O3O4L3VXQIZCPPFBM2XQOHSY23","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":"18c128ca7793d30b73c57506213f26a63aaa20ef5d4ab1b41ac05f1c3898800a","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-26T07:43:47Z","title_canon_sha256":"78eb006a39e7a57c68cc389e503c67dea76127c3f503af51459080a7512d78aa"},"schema_version":"1.0","source":{"id":"2201.10788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.10788","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"arxiv_version","alias_value":"2201.10788v1","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.10788","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"pith_short_12","alias_value":"O3O4L3VXQIZC","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"pith_short_16","alias_value":"O3O4L3VXQIZCPPFB","created_at":"2026-07-05T03:51:49Z"},{"alias_kind":"pith_short_8","alias_value":"O3O4L3VX","created_at":"2026-07-05T03:51:49Z"}],"graph_snapshots":[{"event_id":"sha256:39bb9a1c7f651ffee9dc05316ca78ac809021cfce462efd89b7b29ea073aee03","target":"graph","created_at":"2026-07-05T03:51:49Z","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/2201.10788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In the Vision-and-Language Navigation task, the embodied agent follows linguistic instructions and navigates to a specific goal. It is important in many practical scenarios and has attracted extensive attention from both computer vision and robotics communities. However, most existing works only use RGB images but neglect the 3D semantic information of the scene. To this end, we develop a novel self-supervised training framework to encode the voxel-level 3D semantic reconstruction into a 3D semantic representation. Specifically, a region query task is designed as the pretext task, which predic","authors_text":"Di Guo, Fuchun Sun, Huaping Liu, Mengmeng Ge, Sinan Tan","cross_cats":["cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-26T07:43:47Z","title":"Self-supervised 3D Semantic Representation Learning for Vision-and-Language Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.10788","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":"sha256:3d9e9da3c12d65557a5f138f185e1b6cb530b2134ba2f4a4dae9d56f20505428","target":"record","created_at":"2026-07-05T03:51:49Z","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":"18c128ca7793d30b73c57506213f26a63aaa20ef5d4ab1b41ac05f1c3898800a","cross_cats_sorted":["cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-01-26T07:43:47Z","title_canon_sha256":"78eb006a39e7a57c68cc389e503c67dea76127c3f503af51459080a7512d78aa"},"schema_version":"1.0","source":{"id":"2201.10788","kind":"arxiv","version":1}},"canonical_sha256":"76ddc5eeb7823227bca166af071e58d6f81faf8146d57c5ea66cf615a762897b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"76ddc5eeb7823227bca166af071e58d6f81faf8146d57c5ea66cf615a762897b","first_computed_at":"2026-07-05T03:51:49.672146Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:51:49.672146Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zmnWeYCNvv/UUHnK9QzRiNgc5RH01tVebhH70oWh2bVmf4/vBBs9HjD05fE7LUbJZzFQuHkGlzLLOhodUgQRAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:51:49.672545Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.10788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3d9e9da3c12d65557a5f138f185e1b6cb530b2134ba2f4a4dae9d56f20505428","sha256:39bb9a1c7f651ffee9dc05316ca78ac809021cfce462efd89b7b29ea073aee03"],"state_sha256":"6b3e1060b25a508a3bb3747455efd9a88413a4d23c3d4311051c01b6990518a2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"moBj3oml3pB4K6ZREYNo7N450pLm0yIBXz0+wcUK8DUgmvuwDXe5vaNjydClaZOD4McKxSzaY+XaXLRpz1OwCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T17:51:28.815678Z","bundle_sha256":"cab9f5c315ef107425e53ccf2f3188a964460b6e35360b13ecaac6da28c7580c"}}