{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OWZ6MIWJDWB3KJ3DP6F6P3KCJ5","short_pith_number":"pith:OWZ6MIWJ","canonical_record":{"source":{"id":"2607.01784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T06:56:29Z","cross_cats_sorted":[],"title_canon_sha256":"14b4cb6ea91f29d970889493467551cec3ffbff4bc72dc3c3bca93283f38c6b3","abstract_canon_sha256":"ca2c3624878a2ff4f3c849a354fa58a46d4e7595ab51a4e654e4582e812ab55c"},"schema_version":"1.0"},"canonical_sha256":"75b3e622c91d83b527637f8be7ed424f4bdf9d903bd38134aff2bf403762a8f7","source":{"kind":"arxiv","id":"2607.01784","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01784","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01784v1","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01784","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"pith_short_12","alias_value":"OWZ6MIWJDWB3","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"pith_short_16","alias_value":"OWZ6MIWJDWB3KJ3D","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"pith_short_8","alias_value":"OWZ6MIWJ","created_at":"2026-07-03T01:17:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OWZ6MIWJDWB3KJ3DP6F6P3KCJ5","target":"record","payload":{"canonical_record":{"source":{"id":"2607.01784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T06:56:29Z","cross_cats_sorted":[],"title_canon_sha256":"14b4cb6ea91f29d970889493467551cec3ffbff4bc72dc3c3bca93283f38c6b3","abstract_canon_sha256":"ca2c3624878a2ff4f3c849a354fa58a46d4e7595ab51a4e654e4582e812ab55c"},"schema_version":"1.0"},"canonical_sha256":"75b3e622c91d83b527637f8be7ed424f4bdf9d903bd38134aff2bf403762a8f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:29.696173Z","signature_b64":"+s6mO2glb8vpZ9eMBEvzcLyLNoySr56HrM0qVysm0/DbBLLLslw/qbPJ9obmLxp4JxJKMv5NdQ7fcCHg40YKCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"75b3e622c91d83b527637f8be7ed424f4bdf9d903bd38134aff2bf403762a8f7","last_reissued_at":"2026-07-03T01:17:29.695739Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:29.695739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.01784","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":"2026-07-03T01:17:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q5gQQsNiDBnfEwicD1Tus+1ee4MPIDuLLrM59cRPRvR6oVtp7IbdKCtM6knIkgJo325rv7SDODYiJgJVxmsyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T07:02:00.793601Z"},"content_sha256":"1d921a374eb09e837736b41af89989b1203d70f1aa62505df4e3db24d6520483","schema_version":"1.0","event_id":"sha256:1d921a374eb09e837736b41af89989b1203d70f1aa62505df4e3db24d6520483"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OWZ6MIWJDWB3KJ3DP6F6P3KCJ5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Qianlong Xiang, Weili Guan, Yaowei Wang","submitted_at":"2026-07-02T06:56:29Z","abstract_excerpt":"Visual-spatial understanding, defined as the ability to infer object relationships and scene layouts from visual inputs, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, pre-trained vision-language models (VLMs) remain constrained by spatial uncertainty stemming from inherently 2D observations and by the scarcity of data for 3D spatial understanding. To address these limitations, we proposed a novel framework, SpaceEra, in the NeurIPS 2025 Spotlight paper. Although it achieved significant performance gains, we further observed that its effectiven"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01784","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/2607.01784/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":"2026-07-03T01:17:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rUjF8iD7kwG/bkMXIT8FRzMpB4SzP2PXakR16sOpftoFU+/W3DMcyEO3xwnoOZR7MKjzh5zgGuJBbTO9Fa7/Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-04T07:02:00.793973Z"},"content_sha256":"5d3748a7f07c8c07c494d42d6ebb9fb303fc8865bc02744ce8c6bc80ea651fee","schema_version":"1.0","event_id":"sha256:5d3748a7f07c8c07c494d42d6ebb9fb303fc8865bc02744ce8c6bc80ea651fee"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/bundle.json","state_url":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/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":"2026-07-04T07:02:00Z","links":{"resolver":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5","bundle":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/bundle.json","state":"https://pith.science/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OWZ6MIWJDWB3KJ3DP6F6P3KCJ5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OWZ6MIWJDWB3KJ3DP6F6P3KCJ5","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":"ca2c3624878a2ff4f3c849a354fa58a46d4e7595ab51a4e654e4582e812ab55c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T06:56:29Z","title_canon_sha256":"14b4cb6ea91f29d970889493467551cec3ffbff4bc72dc3c3bca93283f38c6b3"},"schema_version":"1.0","source":{"id":"2607.01784","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.01784","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"arxiv_version","alias_value":"2607.01784v1","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01784","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"pith_short_12","alias_value":"OWZ6MIWJDWB3","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"pith_short_16","alias_value":"OWZ6MIWJDWB3KJ3D","created_at":"2026-07-03T01:17:29Z"},{"alias_kind":"pith_short_8","alias_value":"OWZ6MIWJ","created_at":"2026-07-03T01:17:29Z"}],"graph_snapshots":[{"event_id":"sha256:5d3748a7f07c8c07c494d42d6ebb9fb303fc8865bc02744ce8c6bc80ea651fee","target":"graph","created_at":"2026-07-03T01:17:29Z","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/2607.01784/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual-spatial understanding, defined as the ability to infer object relationships and scene layouts from visual inputs, is fundamental to downstream tasks such as robotic navigation and embodied interaction. However, pre-trained vision-language models (VLMs) remain constrained by spatial uncertainty stemming from inherently 2D observations and by the scarcity of data for 3D spatial understanding. To address these limitations, we proposed a novel framework, SpaceEra, in the NeurIPS 2025 Spotlight paper. Although it achieved significant performance gains, we further observed that its effectiven","authors_text":"Haoyu Zhang, Liqiang Nie, Meng Liu, Qianlong Xiang, Weili Guan, Yaowei Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T06:56:29Z","title":"SpaceEra++: A Unified Framework Towards 3D Spatial Reasoning in Video"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01784","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":"sha256:1d921a374eb09e837736b41af89989b1203d70f1aa62505df4e3db24d6520483","target":"record","created_at":"2026-07-03T01:17:29Z","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":"ca2c3624878a2ff4f3c849a354fa58a46d4e7595ab51a4e654e4582e812ab55c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-07-02T06:56:29Z","title_canon_sha256":"14b4cb6ea91f29d970889493467551cec3ffbff4bc72dc3c3bca93283f38c6b3"},"schema_version":"1.0","source":{"id":"2607.01784","kind":"arxiv","version":1}},"canonical_sha256":"75b3e622c91d83b527637f8be7ed424f4bdf9d903bd38134aff2bf403762a8f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"75b3e622c91d83b527637f8be7ed424f4bdf9d903bd38134aff2bf403762a8f7","first_computed_at":"2026-07-03T01:17:29.695739Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-03T01:17:29.695739Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+s6mO2glb8vpZ9eMBEvzcLyLNoySr56HrM0qVysm0/DbBLLLslw/qbPJ9obmLxp4JxJKMv5NdQ7fcCHg40YKCw==","signature_status":"signed_v1","signed_at":"2026-07-03T01:17:29.696173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.01784","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d921a374eb09e837736b41af89989b1203d70f1aa62505df4e3db24d6520483","sha256:5d3748a7f07c8c07c494d42d6ebb9fb303fc8865bc02744ce8c6bc80ea651fee"],"state_sha256":"45384625b244b967ce021dbe47d2ff7ba4095c1ae56f011f8a87fbf5b913300e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VLjH7LEzF/fjfIzZ90kO885PiDhiZJttQu+9546lq4H680MC6yGSpJbPqFKB7xRIu2OiMAmv+aIys4hazFBeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-04T07:02:00.795926Z","bundle_sha256":"d02583165ccff6bcac4b666915504709583c6d4b6088e46f282cfd84d9d17251"}}