{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VJGKNGU5Z4473VEFZYMVCIARB7","short_pith_number":"pith:VJGKNGU5","schema_version":"1.0","canonical_sha256":"aa4ca69a9dcf39fdd485ce195120110fd12ed9fd7f89fbf57c7afc0a806a3132","source":{"kind":"arxiv","id":"2509.02807","version":1},"attestation_state":"computed","paper":{"title":"PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mennatullah Siam","submitted_at":"2025-09-02T20:21:11Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have shown impressive generalization across tasks using images and text modalities. While their extension to video has enabled tasks such as video question answering and video captioning, their pixel-level visual grounding abilities are less studied. In this work, we raise the pertinent question of whether motion is used in pixel-level visual grounding and whether video MLLMs can segment objects based on natural language expressions describing their motion patterns. We identify the shortcomings in the current benchmarks, where we show that a single fra"},"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":"2509.02807","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T20:21:11Z","cross_cats_sorted":[],"title_canon_sha256":"ea765fc3c03c59f9cf5672bb0ab975e992a2bc3f75e9182d98fb49e9c882089f","abstract_canon_sha256":"b3bc6c5b27d803529178ae54f8c0c1e15c3a96baf0a77725b47aea62abeb663e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:58.039054Z","signature_b64":"e4mDo2qKBabHWovOgyYa/RlUts3I8x6HJlPMvqRzKtqHA6jb8sL/eCPttfJaKTD6y/pppH4DEY/4957H1RMqBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aa4ca69a9dcf39fdd485ce195120110fd12ed9fd7f89fbf57c7afc0a806a3132","last_reissued_at":"2026-07-05T12:03:58.038502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:58.038502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Mennatullah Siam","submitted_at":"2025-09-02T20:21:11Z","abstract_excerpt":"Multi-modal large language models (MLLMs) have shown impressive generalization across tasks using images and text modalities. While their extension to video has enabled tasks such as video question answering and video captioning, their pixel-level visual grounding abilities are less studied. In this work, we raise the pertinent question of whether motion is used in pixel-level visual grounding and whether video MLLMs can segment objects based on natural language expressions describing their motion patterns. We identify the shortcomings in the current benchmarks, where we show that a single fra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02807","kind":"arxiv","version":1},"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/2509.02807/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":"2509.02807","created_at":"2026-07-05T12:03:58.038560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.02807v1","created_at":"2026-07-05T12:03:58.038560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02807","created_at":"2026-07-05T12:03:58.038560+00:00"},{"alias_kind":"pith_short_12","alias_value":"VJGKNGU5Z447","created_at":"2026-07-05T12:03:58.038560+00:00"},{"alias_kind":"pith_short_16","alias_value":"VJGKNGU5Z4473VEF","created_at":"2026-07-05T12:03:58.038560+00:00"},{"alias_kind":"pith_short_8","alias_value":"VJGKNGU5","created_at":"2026-07-05T12:03:58.038560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7","json":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7.json","graph_json":"https://pith.science/api/pith-number/VJGKNGU5Z4473VEFZYMVCIARB7/graph.json","events_json":"https://pith.science/api/pith-number/VJGKNGU5Z4473VEFZYMVCIARB7/events.json","paper":"https://pith.science/paper/VJGKNGU5"},"agent_actions":{"view_html":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7","download_json":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7.json","view_paper":"https://pith.science/paper/VJGKNGU5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.02807&json=true","fetch_graph":"https://pith.science/api/pith-number/VJGKNGU5Z4473VEFZYMVCIARB7/graph.json","fetch_events":"https://pith.science/api/pith-number/VJGKNGU5Z4473VEFZYMVCIARB7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7/action/storage_attestation","attest_author":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7/action/author_attestation","sign_citation":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7/action/citation_signature","submit_replication":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7/action/replication_record"}},"created_at":"2026-07-05T12:03:58.038560+00:00","updated_at":"2026-07-05T12:03:58.038560+00:00"}