{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2ME2GKP33XOXRIUZEBJMQOHUNS","short_pith_number":"pith:2ME2GKP3","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"},"canonical_sha256":"d309a329fbdddd78a2992052c838f46c94a28ff06af186f8818e5981943c14fe","source":{"kind":"arxiv","id":"2506.05336","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05336","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05336v2","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05336","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"pith_short_12","alias_value":"2ME2GKP33XOX","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"pith_short_16","alias_value":"2ME2GKP33XOXRIUZ","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"pith_short_8","alias_value":"2ME2GKP3","created_at":"2026-07-05T11:32:30Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2ME2GKP33XOXRIUZEBJMQOHUNS","target":"record","payload":{"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"},"canonical_sha256":"d309a329fbdddd78a2992052c838f46c94a28ff06af186f8818e5981943c14fe","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"},"source_kind":"arxiv","source_id":"2506.05336","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":"2026-07-05T11:32:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jj4Rhv5FbJCXNSqepYyt1c/7mVI69cIaokGgoatimVME2lOJEDmn5qIxCBw1aPwl1Um2x7sU8Z0D+URRyVvmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:35:17.135688Z"},"content_sha256":"40983e2672f287b44b92c3926562ed747d1938e6af8b5f5bf6dd3162079f6cea","schema_version":"1.0","event_id":"sha256:40983e2672f287b44b92c3926562ed747d1938e6af8b5f5bf6dd3162079f6cea"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2ME2GKP33XOXRIUZEBJMQOHUNS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:32:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ohTlbkqzPEk8W3XkM5MxblvMB/d2XAo2raCYqngPNHUOM4yo3bxtmGJODs1Q5AZcN2xAKhZR4LtMr+wzcdSWAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T04:35:17.136150Z"},"content_sha256":"8e49f901ddf00fa16a07b4a6bbfbb5acb0e6e011dce9c9cbe5b7f0ba45176f3d","schema_version":"1.0","event_id":"sha256:8e49f901ddf00fa16a07b4a6bbfbb5acb0e6e011dce9c9cbe5b7f0ba45176f3d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/bundle.json","state_url":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/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":"2026-07-07T04:35:17Z","links":{"resolver":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS","bundle":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/bundle.json","state":"https://pith.science/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2ME2GKP33XOXRIUZEBJMQOHUNS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2ME2GKP33XOXRIUZEBJMQOHUNS","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":"cb5c538d6ac07b06520323cc4ff011c6321fac54799be065d07d0541cf268092","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:29Z","title_canon_sha256":"9feafeffde9569819b14efed9ec84b52d234ddc861e4c2f24a3df5d3abf3a48e"},"schema_version":"1.0","source":{"id":"2506.05336","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05336","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05336v2","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05336","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"pith_short_12","alias_value":"2ME2GKP33XOX","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"pith_short_16","alias_value":"2ME2GKP33XOXRIUZ","created_at":"2026-07-05T11:32:30Z"},{"alias_kind":"pith_short_8","alias_value":"2ME2GKP3","created_at":"2026-07-05T11:32:30Z"}],"graph_snapshots":[{"event_id":"sha256:8e49f901ddf00fa16a07b4a6bbfbb5acb0e6e011dce9c9cbe5b7f0ba45176f3d","target":"graph","created_at":"2026-07-05T11:32:30Z","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/2506.05336/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Abdelrahman Shaker, Ahmed Heakl, Fahad Shahbaz Khan, Ghazi Shazan Ahmad, Hanan Gani, Salman Khan, Zhiqiang Shen","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:29Z","title":"VideoMolmo: Spatio-Temporal Grounding Meets Pointing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05336","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":"sha256:40983e2672f287b44b92c3926562ed747d1938e6af8b5f5bf6dd3162079f6cea","target":"record","created_at":"2026-07-05T11:32:30Z","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":"cb5c538d6ac07b06520323cc4ff011c6321fac54799be065d07d0541cf268092","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:29Z","title_canon_sha256":"9feafeffde9569819b14efed9ec84b52d234ddc861e4c2f24a3df5d3abf3a48e"},"schema_version":"1.0","source":{"id":"2506.05336","kind":"arxiv","version":2}},"canonical_sha256":"d309a329fbdddd78a2992052c838f46c94a28ff06af186f8818e5981943c14fe","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d309a329fbdddd78a2992052c838f46c94a28ff06af186f8818e5981943c14fe","first_computed_at":"2026-07-05T11:32:30.186448Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:30.186448Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ydtCLyBo9lA23/9IffglYC1GctSd8z6oJPIyCYFYWbnrTMv4eALe5VGI2cWEn9ZsFGoQShJurnlY1H2JHCpxCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:30.186932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05336","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:40983e2672f287b44b92c3926562ed747d1938e6af8b5f5bf6dd3162079f6cea","sha256:8e49f901ddf00fa16a07b4a6bbfbb5acb0e6e011dce9c9cbe5b7f0ba45176f3d"],"state_sha256":"c3986084a757ab5248444f9c7e0caf0c6e24ff964e36ef784eeedeb36b73b3d9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fNjhRVqBmH2u1j/o0ddaFjPT1LtImHkPoHY//j8Tnnk7223Eq3JyjF/ZDrAQLBjUuTww7F8Jza/Xdk3lEnHoAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T04:35:17.138080Z","bundle_sha256":"e6df687f90780bb3ee4c5f2672db9078845ccde67bfd18576e0b824bda951faf"}}