{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:HNPX7WVGRVO7UVZT4GYCBJSWD5","short_pith_number":"pith:HNPX7WVG","schema_version":"1.0","canonical_sha256":"3b5f7fdaa68d5dfa5733e1b020a6561f4aa2a9274c11cba7d6ac03c86f7c2005","source":{"kind":"arxiv","id":"2501.08282","version":2},"attestation_state":"computed","paper":{"title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Li, Jialin Gao, Jinyu Chen, Shaofei Huang, Si Liu, Tianrui Hui, Xiaoming Wei, Ziyu Wei","submitted_at":"2025-01-14T17:58:12Z","abstract_excerpt":"Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key issues: first, incorporating spatial-temporal localization introduces a vast number of coordinate combinations, complicating the alignment of linguistic and visual coordinate representations; second, encoding fine-grained temporal and spatial information during video feature compression is inherently difficult. To address these issues, we propose LLaVA-ST, a M"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.08282","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-01-14T17:58:12Z","cross_cats_sorted":[],"title_canon_sha256":"d864023f48172fcbcb7234a816144200eea03bbc4bf0603f647a1e52b0c85bac","abstract_canon_sha256":"52e6c6ea1fe9052ce2bf42582a78458f274d464c4e1abaa9ef1163d7194a4e9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:18.583883Z","signature_b64":"agvVIQUmDqSSTq+Q4E4YFVNMJOLGZiFdgbdK0g5KwHDEnTTPKhc9/oa+N8q7x/mUHJ4gU9EQnhTT25m76zVXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3b5f7fdaa68d5dfa5733e1b020a6561f4aa2a9274c11cba7d6ac03c86f7c2005","last_reissued_at":"2026-07-05T11:13:18.583337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:18.583337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongyu Li, Jialin Gao, Jinyu Chen, Shaofei Huang, Si Liu, Tianrui Hui, Xiaoming Wei, Ziyu Wei","submitted_at":"2025-01-14T17:58:12Z","abstract_excerpt":"Recent advancements in multimodal large language models (MLLMs) have shown promising results, yet existing approaches struggle to effectively handle both temporal and spatial localization simultaneously. This challenge stems from two key issues: first, incorporating spatial-temporal localization introduces a vast number of coordinate combinations, complicating the alignment of linguistic and visual coordinate representations; second, encoding fine-grained temporal and spatial information during video feature compression is inherently difficult. To address these issues, we propose LLaVA-ST, a M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.08282","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/2501.08282/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.08282","created_at":"2026-07-05T11:13:18.583409+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.08282v2","created_at":"2026-07-05T11:13:18.583409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.08282","created_at":"2026-07-05T11:13:18.583409+00:00"},{"alias_kind":"pith_short_12","alias_value":"HNPX7WVGRVO7","created_at":"2026-07-05T11:13:18.583409+00:00"},{"alias_kind":"pith_short_16","alias_value":"HNPX7WVGRVO7UVZT","created_at":"2026-07-05T11:13:18.583409+00:00"},{"alias_kind":"pith_short_8","alias_value":"HNPX7WVG","created_at":"2026-07-05T11:13:18.583409+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2505.20715","citing_title":"MUSEG: Reinforcing Video Temporal Understanding via Timestamp-Aware Multi-Segment Grounding","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12148","citing_title":"ViLL-E: Video LLM Embeddings for Retrieval","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HNPX7WVGRVO7UVZT4GYCBJSWD5","json":"https://pith.science/pith/HNPX7WVGRVO7UVZT4GYCBJSWD5.json","graph_json":"https://pith.science/api/pith-number/HNPX7WVGRVO7UVZT4GYCBJSWD5/graph.json","events_json":"https://pith.science/api/pith-number/HNPX7WVGRVO7UVZT4GYCBJSWD5/events.json","paper":"https://pith.science/paper/HNPX7WVG"},"agent_actions":{"view_html":"https://pith.science/pith/HNPX7WVGRVO7UVZT4GYCBJSWD5","download_json":"https://pith.science/pith/HNPX7WVGRVO7UVZT4GYCBJSWD5.json","view_paper":"https://pith.science/paper/HNPX7WVG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.08282&json=true","fetch_graph":"https://pith.science/api/pith-number/HNPX7WVGRVO7UVZT4GYCBJSWD5/graph.json","fetch_events":"https://pith.science/api/pith-number/HNPX7WVGRVO7UVZT4GYCBJSWD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HNPX7WVGRVO7UVZT4GYCBJSWD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HNPX7WVGRVO7UVZT4GYCBJSWD5/action/storage_attestation","attest_author":"https://pith.science/pith/HNPX7WVGRVO7UVZT4GYCBJSWD5/action/author_attestation","sign_citation":"https://pith.science/pith/HNPX7WVGRVO7UVZT4GYCBJSWD5/action/citation_signature","submit_replication":"https://pith.science/pith/HNPX7WVGRVO7UVZT4GYCBJSWD5/action/replication_record"}},"created_at":"2026-07-05T11:13:18.583409+00:00","updated_at":"2026-07-05T11:13:18.583409+00:00"}