{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:K6I5CDOV3TDYCMYH7JFNJXKLVV","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":"032db2d81cf47393e91e227aee8f3f33e62cbd5c68f56f6a667305d23a13abfb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T07:40:36Z","title_canon_sha256":"c963f43f80c463eccbdccb72f4f061d579d48d019cb51bc82c52ac9c3ba09389"},"schema_version":"1.0","source":{"id":"2503.13983","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.13983","created_at":"2026-07-05T10:47:36Z"},{"alias_kind":"arxiv_version","alias_value":"2503.13983v3","created_at":"2026-07-05T10:47:36Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.13983","created_at":"2026-07-05T10:47:36Z"},{"alias_kind":"pith_short_12","alias_value":"K6I5CDOV3TDY","created_at":"2026-07-05T10:47:36Z"},{"alias_kind":"pith_short_16","alias_value":"K6I5CDOV3TDYCMYH","created_at":"2026-07-05T10:47:36Z"},{"alias_kind":"pith_short_8","alias_value":"K6I5CDOV","created_at":"2026-07-05T10:47:36Z"}],"graph_snapshots":[{"event_id":"sha256:83f50467779bc47e36a0cff72fbf5f66eee5855984c5bd452a9c4ba9d35322f5","target":"graph","created_at":"2026-07-05T10:47:36Z","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/2503.13983/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal large language models (MLLMs) have made remarkable progress in either temporal or spatial localization. However, they struggle to perform spatio-temporal video grounding. This limitation stems from two major challenges. Firstly, it is difficult to extract accurate spatio-temporal information of each frame in the video. Secondly, the substantial number of visual tokens makes it challenging to precisely map visual tokens of each frame to their corresponding spatial coordinates. To address these issues, we introduce SpaceVLLM, a MLLM endowed with spatio-temporal video grounding capabil","authors_text":"Hongtao Xie, Jiankang Wang, Jiannan Ge, Yang Li, Yongdong Zhang, Zhihang Liu, Zhihan Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T07:40:36Z","title":"SpaceVLLM: Endowing Multimodal Large Language Model with Spatio-Temporal Video Grounding Capability"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.13983","kind":"arxiv","version":3},"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":"sha256:372f1adf91d58c43a1ddc8e29a9432c604cdb57a9a3b239730ea68e4022e8fb7","target":"record","created_at":"2026-07-05T10:47:36Z","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":"032db2d81cf47393e91e227aee8f3f33e62cbd5c68f56f6a667305d23a13abfb","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-18T07:40:36Z","title_canon_sha256":"c963f43f80c463eccbdccb72f4f061d579d48d019cb51bc82c52ac9c3ba09389"},"schema_version":"1.0","source":{"id":"2503.13983","kind":"arxiv","version":3}},"canonical_sha256":"5791d10dd5dcc7813307fa4ad4dd4bad7680281115a8e99e81f1f0b535277dc6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5791d10dd5dcc7813307fa4ad4dd4bad7680281115a8e99e81f1f0b535277dc6","first_computed_at":"2026-07-05T10:47:36.805471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:47:36.805471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tpOLpoDjxmKru0mH8Iw10nnV7mEEZKhipl7+M/HP9lAjMBH/X6RP/eYltpV7VYSDZ12mpjMMXdyt7gG3+lwbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:47:36.805957Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.13983","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:372f1adf91d58c43a1ddc8e29a9432c604cdb57a9a3b239730ea68e4022e8fb7","sha256:83f50467779bc47e36a0cff72fbf5f66eee5855984c5bd452a9c4ba9d35322f5"],"state_sha256":"062e3561a80f78c194de4a4be798deffac7ebae93428523369611593e568e327"}