{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SQOPUHA7C3PYJTSEKDRVRLCXZV","short_pith_number":"pith:SQOPUHA7","canonical_record":{"source":{"id":"2607.17599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:40:45Z","cross_cats_sorted":[],"title_canon_sha256":"5ef332a180404eea2a8f618345e670f7b3c238511e021b98c01c93bd0334f131","abstract_canon_sha256":"c47f118061ec6ba66e4e39aa78c3aabe1f9d392e3175f0646b06fe6baff34a0a"},"schema_version":"1.0"},"canonical_sha256":"941cfa1c1f16df84ce4450e358ac57cd6f0c3fb7a25dac09cbe4d48fffdd4c02","source":{"kind":"arxiv","id":"2607.17599","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17599","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17599v1","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17599","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"SQOPUHA7C3PY","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"SQOPUHA7C3PYJTSE","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"SQOPUHA7","created_at":"2026-07-21T01:21:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SQOPUHA7C3PYJTSEKDRVRLCXZV","target":"record","payload":{"canonical_record":{"source":{"id":"2607.17599","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:40:45Z","cross_cats_sorted":[],"title_canon_sha256":"5ef332a180404eea2a8f618345e670f7b3c238511e021b98c01c93bd0334f131","abstract_canon_sha256":"c47f118061ec6ba66e4e39aa78c3aabe1f9d392e3175f0646b06fe6baff34a0a"},"schema_version":"1.0"},"canonical_sha256":"941cfa1c1f16df84ce4450e358ac57cd6f0c3fb7a25dac09cbe4d48fffdd4c02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T01:21:54.461622Z","signature_b64":"TW2NYkbctcL/nsnQlEv3KRR0fZSGh+McqqwR0tWuK4bh54oVwPVhBPSj8jYMXM4h9NLUkFf0RbmGjEGsja/IBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"941cfa1c1f16df84ce4450e358ac57cd6f0c3fb7a25dac09cbe4d48fffdd4c02","last_reissued_at":"2026-07-21T01:21:54.460750Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T01:21:54.460750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.17599","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":"2026-07-21T01:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZlnJTpNigTd4qiw+ymWHHfLMN5skPSvAKUN+prOemGidNkRm4Wl/3X3jHIdsXVdlWJnJ9EAVL9CrB/A3KMYZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T19:09:24.937240Z"},"content_sha256":"a60a74fa921f62c179151562da7340537c38f60c90629a84a6780d7a1c6ce581","schema_version":"1.0","event_id":"sha256:a60a74fa921f62c179151562da7340537c38f60c90629a84a6780d7a1c6ce581"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SQOPUHA7C3PYJTSEKDRVRLCXZV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hao Tang, Jian Yang, Ting Huang, Wenyuan Huang, Zhenyu Zhang","submitted_at":"2026-07-20T06:40:45Z","abstract_excerpt":"Video spatial reasoning is essential for navigation-oriented perception and long-video question answering, where models must infer spatial relations across long horizons under changing viewpoints. However, existing multimodal large language models (MLLMs) remain largely semantic-centric, and often fail to reliably aggregate consistent spatial evidence from redundant video observations, leading to inefficient or unstable reasoning. To address these issues, we propose ConsiSpace, a geometry-consistency-aware framework for geometry-sensitive video spatial reasoning that turns spatial consistency "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17599","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/2607.17599/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":"2026-07-21T01:21:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Zv2Vcrv3sKb/UvrTBfmRnsvGhrpp8WwR24Ie5l/VVY6qn5M1DoFCsix0lIq++cXt+VvTL3hLtWbX6wWq+az8AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-02T19:09:24.937791Z"},"content_sha256":"6061723fdc1f9fdc4d00bea8b9ed0e965894c164414e1a96780c9c062ec3785b","schema_version":"1.0","event_id":"sha256:6061723fdc1f9fdc4d00bea8b9ed0e965894c164414e1a96780c9c062ec3785b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/bundle.json","state_url":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/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":"2026-08-02T19:09:24Z","links":{"resolver":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV","bundle":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/bundle.json","state":"https://pith.science/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SQOPUHA7C3PYJTSEKDRVRLCXZV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SQOPUHA7C3PYJTSEKDRVRLCXZV","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":"c47f118061ec6ba66e4e39aa78c3aabe1f9d392e3175f0646b06fe6baff34a0a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:40:45Z","title_canon_sha256":"5ef332a180404eea2a8f618345e670f7b3c238511e021b98c01c93bd0334f131"},"schema_version":"1.0","source":{"id":"2607.17599","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.17599","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"arxiv_version","alias_value":"2607.17599v1","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.17599","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_12","alias_value":"SQOPUHA7C3PY","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_16","alias_value":"SQOPUHA7C3PYJTSE","created_at":"2026-07-21T01:21:54Z"},{"alias_kind":"pith_short_8","alias_value":"SQOPUHA7","created_at":"2026-07-21T01:21:54Z"}],"graph_snapshots":[{"event_id":"sha256:6061723fdc1f9fdc4d00bea8b9ed0e965894c164414e1a96780c9c062ec3785b","target":"graph","created_at":"2026-07-21T01:21:54Z","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/2607.17599/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video spatial reasoning is essential for navigation-oriented perception and long-video question answering, where models must infer spatial relations across long horizons under changing viewpoints. However, existing multimodal large language models (MLLMs) remain largely semantic-centric, and often fail to reliably aggregate consistent spatial evidence from redundant video observations, leading to inefficient or unstable reasoning. To address these issues, we propose ConsiSpace, a geometry-consistency-aware framework for geometry-sensitive video spatial reasoning that turns spatial consistency ","authors_text":"Hao Tang, Jian Yang, Ting Huang, Wenyuan Huang, Zhenyu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:40:45Z","title":"ConsiSpace: Learning Geometric Consistency Matters for Video Spatial Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.17599","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:a60a74fa921f62c179151562da7340537c38f60c90629a84a6780d7a1c6ce581","target":"record","created_at":"2026-07-21T01:21:54Z","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":"c47f118061ec6ba66e4e39aa78c3aabe1f9d392e3175f0646b06fe6baff34a0a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-07-20T06:40:45Z","title_canon_sha256":"5ef332a180404eea2a8f618345e670f7b3c238511e021b98c01c93bd0334f131"},"schema_version":"1.0","source":{"id":"2607.17599","kind":"arxiv","version":1}},"canonical_sha256":"941cfa1c1f16df84ce4450e358ac57cd6f0c3fb7a25dac09cbe4d48fffdd4c02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"941cfa1c1f16df84ce4450e358ac57cd6f0c3fb7a25dac09cbe4d48fffdd4c02","first_computed_at":"2026-07-21T01:21:54.460750Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T01:21:54.460750Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TW2NYkbctcL/nsnQlEv3KRR0fZSGh+McqqwR0tWuK4bh54oVwPVhBPSj8jYMXM4h9NLUkFf0RbmGjEGsja/IBQ==","signature_status":"signed_v1","signed_at":"2026-07-21T01:21:54.461622Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.17599","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a60a74fa921f62c179151562da7340537c38f60c90629a84a6780d7a1c6ce581","sha256:6061723fdc1f9fdc4d00bea8b9ed0e965894c164414e1a96780c9c062ec3785b"],"state_sha256":"5c621b59d773b279ea30ca375189092e04c4c5eff2d8eaf1b2ec9307ce62db7e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fd3o375pjgokMr0f99Ph8YmC8Fdy1S7rT2q7BDnuamllJyjHODYs2PQjKThwjUdUogrVUdSfVE8jn8ECOxY4Dg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-02T19:09:24.941540Z","bundle_sha256":"876846e04ac9f9fd6d00a6432fc0fe30dc427173eee966ab9c49f512d9e37d14"}}