{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2LF3X5UWQ6ZCDYCCCNXPLSQFBE","short_pith_number":"pith:2LF3X5UW","canonical_record":{"source":{"id":"2412.08591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:10:21Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"65aff648abc3c7342a0c7ee0a664120b9cbe26029d5e36dcbbe2ffa07a495c2c","abstract_canon_sha256":"0471557ead9348367da84f355ad1e08997fde0cb561278942c92af2b0f45e950"},"schema_version":"1.0"},"canonical_sha256":"d2cbbbf69687b221e042136ef5ca050916fb54d827b8ac5d92c38a54e8c153ac","source":{"kind":"arxiv","id":"2412.08591","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08591","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08591v2","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08591","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"2LF3X5UWQ6ZC","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"2LF3X5UWQ6ZCDYCC","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"2LF3X5UW","created_at":"2026-07-05T10:34:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2LF3X5UWQ6ZCDYCCCNXPLSQFBE","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08591","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:10:21Z","cross_cats_sorted":["cs.AI","cs.RO"],"title_canon_sha256":"65aff648abc3c7342a0c7ee0a664120b9cbe26029d5e36dcbbe2ffa07a495c2c","abstract_canon_sha256":"0471557ead9348367da84f355ad1e08997fde0cb561278942c92af2b0f45e950"},"schema_version":"1.0"},"canonical_sha256":"d2cbbbf69687b221e042136ef5ca050916fb54d827b8ac5d92c38a54e8c153ac","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:34:13.341594Z","signature_b64":"mwiU8cVkktvja8cAeMCwFUh1Pqf7k+fYf/uOCaI2I4rh31nAYrBGpdYKcXO9Y/g+dZA0FTz4DlM5M7pjN0IVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2cbbbf69687b221e042136ef5ca050916fb54d827b8ac5d92c38a54e8c153ac","last_reissued_at":"2026-07-05T10:34:13.341063Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:34:13.341063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08591","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":"2026-07-05T10:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n68zLnpaFfWI4yN/YjpQSuvZSrGwd9GxSn2Awi/cxCVspwE0ebkibj5+AcpDV7a+sFgeXaw/vwNXCKV/oA8HCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:34:59.030537Z"},"content_sha256":"da14401592929f019ee8ea98f32d0c33007861c066789e188240d4e127cae217","schema_version":"1.0","event_id":"sha256:da14401592929f019ee8ea98f32d0c33007861c066789e188240d4e127cae217"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2LF3X5UWQ6ZCDYCCCNXPLSQFBE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.RO"],"primary_cat":"cs.CV","authors_text":"Ekaterina Radionova, Ivan Laptev, Jingyi Zhang, Kamila Zhumakhanova, Liang Ma, Mingfei Han, Xiaodan Liang, Xiaojun Chang","submitted_at":"2024-12-11T18:10:21Z","abstract_excerpt":"Vision-and-Language Navigation (VLN) suffers from the limited diversity and scale of training data, primarily constrained by the manual curation of existing simulators. To address this, we introduce RoomTour3D, a video-instruction dataset derived from web-based room tour videos that capture real-world indoor spaces and human walking demonstrations. Unlike existing VLN datasets, RoomTour3D leverages the scale and diversity of online videos to generate open-ended human walking trajectories and open-world navigable instructions. To compensate for the lack of navigation data in online videos, we p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08591","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/2412.08591/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":"2026-07-05T10:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TES5ERymnmDMXTC7g+XM/pHniHLBslfjOYvkSA6yfMnqcAw9nykAJ8kXAp+bKEbvv1vHm0DyFPZlmsRAB+X7Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T10:34:59.031029Z"},"content_sha256":"c62862888cefc191220759172f789717ef46380d3f66ade75d4d3668ddb2977a","schema_version":"1.0","event_id":"sha256:c62862888cefc191220759172f789717ef46380d3f66ade75d4d3668ddb2977a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/bundle.json","state_url":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/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":"2026-08-05T10:34:59Z","links":{"resolver":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE","bundle":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/bundle.json","state":"https://pith.science/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2LF3X5UWQ6ZCDYCCCNXPLSQFBE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2LF3X5UWQ6ZCDYCCCNXPLSQFBE","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":"0471557ead9348367da84f355ad1e08997fde0cb561278942c92af2b0f45e950","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:10:21Z","title_canon_sha256":"65aff648abc3c7342a0c7ee0a664120b9cbe26029d5e36dcbbe2ffa07a495c2c"},"schema_version":"1.0","source":{"id":"2412.08591","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08591","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08591v2","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08591","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"2LF3X5UWQ6ZC","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"2LF3X5UWQ6ZCDYCC","created_at":"2026-07-05T10:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"2LF3X5UW","created_at":"2026-07-05T10:34:13Z"}],"graph_snapshots":[{"event_id":"sha256:c62862888cefc191220759172f789717ef46380d3f66ade75d4d3668ddb2977a","target":"graph","created_at":"2026-07-05T10:34:13Z","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/2412.08591/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Vision-and-Language Navigation (VLN) suffers from the limited diversity and scale of training data, primarily constrained by the manual curation of existing simulators. To address this, we introduce RoomTour3D, a video-instruction dataset derived from web-based room tour videos that capture real-world indoor spaces and human walking demonstrations. Unlike existing VLN datasets, RoomTour3D leverages the scale and diversity of online videos to generate open-ended human walking trajectories and open-world navigable instructions. To compensate for the lack of navigation data in online videos, we p","authors_text":"Ekaterina Radionova, Ivan Laptev, Jingyi Zhang, Kamila Zhumakhanova, Liang Ma, Mingfei Han, Xiaodan Liang, Xiaojun Chang","cross_cats":["cs.AI","cs.RO"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:10:21Z","title":"RoomTour3D: Geometry-Aware Video-Instruction Tuning for Embodied Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08591","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:da14401592929f019ee8ea98f32d0c33007861c066789e188240d4e127cae217","target":"record","created_at":"2026-07-05T10:34:13Z","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":"0471557ead9348367da84f355ad1e08997fde0cb561278942c92af2b0f45e950","cross_cats_sorted":["cs.AI","cs.RO"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-11T18:10:21Z","title_canon_sha256":"65aff648abc3c7342a0c7ee0a664120b9cbe26029d5e36dcbbe2ffa07a495c2c"},"schema_version":"1.0","source":{"id":"2412.08591","kind":"arxiv","version":2}},"canonical_sha256":"d2cbbbf69687b221e042136ef5ca050916fb54d827b8ac5d92c38a54e8c153ac","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2cbbbf69687b221e042136ef5ca050916fb54d827b8ac5d92c38a54e8c153ac","first_computed_at":"2026-07-05T10:34:13.341063Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:34:13.341063Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mwiU8cVkktvja8cAeMCwFUh1Pqf7k+fYf/uOCaI2I4rh31nAYrBGpdYKcXO9Y/g+dZA0FTz4DlM5M7pjN0IVAw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:34:13.341594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08591","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:da14401592929f019ee8ea98f32d0c33007861c066789e188240d4e127cae217","sha256:c62862888cefc191220759172f789717ef46380d3f66ade75d4d3668ddb2977a"],"state_sha256":"e40fa7fb257eef475ba3ab5532e8ea28866bdb3d1043139d2d2536eb708b835e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tm0BLUxjnQr6gUIg5Bj8GOw2rGSyAKd1mAyoNc1HZiWBDjkckxpsIh+f1gyjhlHOna6JOVh6HUnsAmzFTBgZCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T10:34:59.034654Z","bundle_sha256":"58e95651154d2cefafec14b06beb2b30e62152fce7c251d4855adea545cdb8e3"}}