{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2ME2GKP33XOXRIUZEBJMQOHUNS","short_pith_number":"pith:2ME2GKP3","schema_version":"1.0","canonical_sha256":"d309a329fbdddd78a2992052c838f46c94a28ff06af186f8818e5981943c14fe","source":{"kind":"arxiv","id":"2506.05336","version":2},"attestation_state":"computed","paper":{"title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Ahmed Heakl, Fahad Shahbaz Khan, Ghazi Shazan Ahmad, Hanan Gani, Salman Khan, Zhiqiang Shen","submitted_at":"2025-06-05T17:59:29Z","abstract_excerpt":"Spatio-temporal localization is vital for precise interactions across diverse domains, from biological research to autonomous navigation and interactive interfaces. Current video-based approaches, while proficient in tracking, lack the sophisticated reasoning capabilities of large language models, limiting their contextual understanding and generalization. We introduce VideoMolmo, a large multimodal model tailored for fine-grained spatio-temporal pointing conditioned on textual descriptions. Building upon the Molmo architecture, VideoMolmo incorporates a temporal module utilizing an attention "},"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":"2506.05336","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:29Z","cross_cats_sorted":[],"title_canon_sha256":"9feafeffde9569819b14efed9ec84b52d234ddc861e4c2f24a3df5d3abf3a48e","abstract_canon_sha256":"cb5c538d6ac07b06520323cc4ff011c6321fac54799be065d07d0541cf268092"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:32:30.186932Z","signature_b64":"ydtCLyBo9lA23/9IffglYC1GctSd8z6oJPIyCYFYWbnrTMv4eALe5VGI2cWEn9ZsFGoQShJurnlY1H2JHCpxCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d309a329fbdddd78a2992052c838f46c94a28ff06af186f8818e5981943c14fe","last_reissued_at":"2026-07-05T11:32:30.186448Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:32:30.186448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Abdelrahman Shaker, Ahmed Heakl, Fahad Shahbaz Khan, Ghazi Shazan Ahmad, Hanan Gani, Salman Khan, Zhiqiang Shen","submitted_at":"2025-06-05T17:59:29Z","abstract_excerpt":"Spatio-temporal localization is vital for precise interactions across diverse domains, from biological research to autonomous navigation and interactive interfaces. Current video-based approaches, while proficient in tracking, lack the sophisticated reasoning capabilities of large language models, limiting their contextual understanding and generalization. We introduce VideoMolmo, a large multimodal model tailored for fine-grained spatio-temporal pointing conditioned on textual descriptions. Building upon the Molmo architecture, VideoMolmo incorporates a temporal module utilizing an attention "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05336","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/2506.05336/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":"2506.05336","created_at":"2026-07-05T11:32:30.186509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05336v2","created_at":"2026-07-05T11:32:30.186509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05336","created_at":"2026-07-05T11:32:30.186509+00:00"},{"alias_kind":"pith_short_12","alias_value":"2ME2GKP33XOX","created_at":"2026-07-05T11:32:30.186509+00:00"},{"alias_kind":"pith_short_16","alias_value":"2ME2GKP33XOXRIUZ","created_at":"2026-07-05T11:32:30.186509+00:00"},{"alias_kind":"pith_short_8","alias_value":"2ME2GKP3","created_at":"2026-07-05T11:32:30.186509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02269","citing_title":"AnyGroundBench: A Specialized-Domain Benchmark for Video Grounding in Vision-Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01391","citing_title":"VISTA: Video Interaction Spatio-Temporal Analysis Benchmark","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25979","citing_title":"LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2601.10611","citing_title":"Molmo2: Open Weights and Data for Vision-Language Models with Video Understanding and Grounding","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01391","citing_title":"VISTA: Video Interaction Spatio-Temporal Analysis Benchmark","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.08014","citing_title":"Bridging Time and Space: Decoupled Spatio-Temporal Alignment for Video Grounding","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS","json":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS.json","graph_json":"https://pith.science/api/pith-number/2ME2GKP33XOXRIUZEBJMQOHUNS/graph.json","events_json":"https://pith.science/api/pith-number/2ME2GKP33XOXRIUZEBJMQOHUNS/events.json","paper":"https://pith.science/paper/2ME2GKP3"},"agent_actions":{"view_html":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS","download_json":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS.json","view_paper":"https://pith.science/paper/2ME2GKP3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05336&json=true","fetch_graph":"https://pith.science/api/pith-number/2ME2GKP33XOXRIUZEBJMQOHUNS/graph.json","fetch_events":"https://pith.science/api/pith-number/2ME2GKP33XOXRIUZEBJMQOHUNS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/action/storage_attestation","attest_author":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/action/author_attestation","sign_citation":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/action/citation_signature","submit_replication":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/action/replication_record"}},"created_at":"2026-07-05T11:32:30.186509+00:00","updated_at":"2026-07-05T11:32:30.186509+00:00"}