{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:YBT6OK6SXIAC5UGMXGVDBAKA7Y","short_pith_number":"pith:YBT6OK6S","canonical_record":{"source":{"id":"2505.17015","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b9c36f69fc3568e1ec2e506dadf323100b346f3277794db7029df94ddf8f2e8b","abstract_canon_sha256":"ba1ee1ab8f2626ea564e1f852c951a22b6ddf05c7d453b3114bd82165a4fcdee"},"schema_version":"1.0"},"canonical_sha256":"c067e72bd2ba002ed0ccb9aa308140fe09ff7e488b99f1a02985310125764cf9","source":{"kind":"arxiv","id":"2505.17015","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17015","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17015v2","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17015","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"YBT6OK6SXIAC","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"pith_short_16","alias_value":"YBT6OK6SXIAC5UGM","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"pith_short_8","alias_value":"YBT6OK6S","created_at":"2026-05-25T02:02:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:YBT6OK6SXIAC5UGMXGVDBAKA7Y","target":"record","payload":{"canonical_record":{"source":{"id":"2505.17015","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:39Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"b9c36f69fc3568e1ec2e506dadf323100b346f3277794db7029df94ddf8f2e8b","abstract_canon_sha256":"ba1ee1ab8f2626ea564e1f852c951a22b6ddf05c7d453b3114bd82165a4fcdee"},"schema_version":"1.0"},"canonical_sha256":"c067e72bd2ba002ed0ccb9aa308140fe09ff7e488b99f1a02985310125764cf9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-25T02:02:07.226225Z","signature_b64":"fH3ueKSN2Ll9IrKXktWk3zyBQKjhedVJ7ZcKAo+cjKRoTi7bXw6aJRod7JUczI+hzgg82KSDFL8TWgu4DdFACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c067e72bd2ba002ed0ccb9aa308140fe09ff7e488b99f1a02985310125764cf9","last_reissued_at":"2026-05-25T02:02:07.225357Z","signature_status":"signed_v1","first_computed_at":"2026-05-25T02:02:07.225357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.17015","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":"2026-05-25T02:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hPfG6NWcQ5nEj4ztvR77bBA3Unisk+FNb0Hl4hKpP+JOVRFacdoFyQ0mJ7F5QVwptkNshaQ3sQ158aGcNSp3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:53:07.027393Z"},"content_sha256":"2f3f981c07d8ea294c5bbf2e12e7af3929e0897899c23e32d27e74d481230c88","schema_version":"1.0","event_id":"sha256:2f3f981c07d8ea294c5bbf2e12e7af3929e0897899c23e32d27e74d481230c88"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:YBT6OK6SXIAC5UGMXGVDBAKA7Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Fu-Jen Chu, Hao Tang, Kevin J. Liang, Matt Feiszli, Runsen Xu, Weiyao Wang, Xiaodong Wang, Xingyu Chen","submitted_at":"2025-05-22T17:59:39Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning. In this paper, we propose a framework to equip MLLMs with multi-frame spatial understanding by integrating fundamental spatial skills, including depth perception, visual correspondence, and dynamic perception. We design a novel data pipeline and collect the MultiSPA dataset of more than 27 million samples spanning diverse 3D and 4D scenes to enable training. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17015","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/2505.17015/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":"2026-05-25T02:02:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PGxjH2DrOjR/k/J/19aRiEHSmNCbToqwRVYYpX87Gi7n+ZM4dymFTgE7OKTk9p62YQCVHLDOL+GA6MsGgKzyBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T19:53:07.028051Z"},"content_sha256":"4b019bdb0aedaac7be2a71a884b7b214d9cc0c7c4dcb70dc0e6d8537c3a049d7","schema_version":"1.0","event_id":"sha256:4b019bdb0aedaac7be2a71a884b7b214d9cc0c7c4dcb70dc0e6d8537c3a049d7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YBT6OK6SXIAC5UGMXGVDBAKA7Y/bundle.json","state_url":"https://pith.science/pith/YBT6OK6SXIAC5UGMXGVDBAKA7Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YBT6OK6SXIAC5UGMXGVDBAKA7Y/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":"2026-05-25T19:53:07Z","links":{"resolver":"https://pith.science/pith/YBT6OK6SXIAC5UGMXGVDBAKA7Y","bundle":"https://pith.science/pith/YBT6OK6SXIAC5UGMXGVDBAKA7Y/bundle.json","state":"https://pith.science/pith/YBT6OK6SXIAC5UGMXGVDBAKA7Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YBT6OK6SXIAC5UGMXGVDBAKA7Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:YBT6OK6SXIAC5UGMXGVDBAKA7Y","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":"ba1ee1ab8f2626ea564e1f852c951a22b6ddf05c7d453b3114bd82165a4fcdee","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:39Z","title_canon_sha256":"b9c36f69fc3568e1ec2e506dadf323100b346f3277794db7029df94ddf8f2e8b"},"schema_version":"1.0","source":{"id":"2505.17015","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.17015","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"arxiv_version","alias_value":"2505.17015v2","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17015","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"pith_short_12","alias_value":"YBT6OK6SXIAC","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"pith_short_16","alias_value":"YBT6OK6SXIAC5UGM","created_at":"2026-05-25T02:02:07Z"},{"alias_kind":"pith_short_8","alias_value":"YBT6OK6S","created_at":"2026-05-25T02:02:07Z"}],"graph_snapshots":[{"event_id":"sha256:4b019bdb0aedaac7be2a71a884b7b214d9cc0c7c4dcb70dc0e6d8537c3a049d7","target":"graph","created_at":"2026-05-25T02:02:07Z","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/2505.17015/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multi-modal large language models (MLLMs) have rapidly advanced in visual tasks, yet their spatial understanding remains limited to single images, leaving them ill-suited for physical-world applications that require multi-frame reasoning. In this paper, we propose a framework to equip MLLMs with multi-frame spatial understanding by integrating fundamental spatial skills, including depth perception, visual correspondence, and dynamic perception. We design a novel data pipeline and collect the MultiSPA dataset of more than 27 million samples spanning diverse 3D and 4D scenes to enable training. ","authors_text":"Fu-Jen Chu, Hao Tang, Kevin J. Liang, Matt Feiszli, Runsen Xu, Weiyao Wang, Xiaodong Wang, Xingyu Chen","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:39Z","title":"Multi-SpatialMLLM: Multi-Frame Spatial Understanding with Multi-Modal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17015","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":"sha256:2f3f981c07d8ea294c5bbf2e12e7af3929e0897899c23e32d27e74d481230c88","target":"record","created_at":"2026-05-25T02:02:07Z","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":"ba1ee1ab8f2626ea564e1f852c951a22b6ddf05c7d453b3114bd82165a4fcdee","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-22T17:59:39Z","title_canon_sha256":"b9c36f69fc3568e1ec2e506dadf323100b346f3277794db7029df94ddf8f2e8b"},"schema_version":"1.0","source":{"id":"2505.17015","kind":"arxiv","version":2}},"canonical_sha256":"c067e72bd2ba002ed0ccb9aa308140fe09ff7e488b99f1a02985310125764cf9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c067e72bd2ba002ed0ccb9aa308140fe09ff7e488b99f1a02985310125764cf9","first_computed_at":"2026-05-25T02:02:07.225357Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-25T02:02:07.225357Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fH3ueKSN2Ll9IrKXktWk3zyBQKjhedVJ7ZcKAo+cjKRoTi7bXw6aJRod7JUczI+hzgg82KSDFL8TWgu4DdFACg==","signature_status":"signed_v1","signed_at":"2026-05-25T02:02:07.226225Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.17015","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f3f981c07d8ea294c5bbf2e12e7af3929e0897899c23e32d27e74d481230c88","sha256:4b019bdb0aedaac7be2a71a884b7b214d9cc0c7c4dcb70dc0e6d8537c3a049d7"],"state_sha256":"a0065b6e92f4f78e793056ef972a57e508911756cd009eff6bfa27f308803a9e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5bEWJGzcuGa8I0YLWDr3IRUZV7emk0zsxC3fMd5QA0zSFo6hIWDwP9JlMW0pygyAaNkr/w7GHRWVQsJx+JppBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T19:53:07.031809Z","bundle_sha256":"a9b38fd152a587cf5cdb0c3bc44d164a31543f366c89f54c2fdffe341d084e40"}}