{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:VJGKNGU5Z4473VEFZYMVCIARB7","short_pith_number":"pith:VJGKNGU5","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"},"canonical_sha256":"aa4ca69a9dcf39fdd485ce195120110fd12ed9fd7f89fbf57c7afc0a806a3132","source":{"kind":"arxiv","id":"2509.02807","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02807","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02807v1","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02807","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"VJGKNGU5Z447","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"VJGKNGU5Z4473VEF","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"VJGKNGU5","created_at":"2026-07-05T12:03:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:VJGKNGU5Z4473VEFZYMVCIARB7","target":"record","payload":{"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"},"canonical_sha256":"aa4ca69a9dcf39fdd485ce195120110fd12ed9fd7f89fbf57c7afc0a806a3132","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"},"source_kind":"arxiv","source_id":"2509.02807","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xUgqW+YNa3AN2JkDi6rNT9Y08GVAEZJv9o6NAl2/BuDZ2fXbvLAfBzVkiEukfejsw5sc+Kot1FAm/KvD4LaLBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:58:47.740038Z"},"content_sha256":"c9b78df4a395c2216d10426ede2a4e5677886010408c76b61c7505d1c8189d18","schema_version":"1.0","event_id":"sha256:c9b78df4a395c2216d10426ede2a4e5677886010408c76b61c7505d1c8189d18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:VJGKNGU5Z4473VEFZYMVCIARB7","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T12:03:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/yIytu/RR7GKy4/nr32UNFhTuWeiTjDhrnBgIZuqyV0LZoLAX/06V8u+QPqKS+dC/Xs20NcIB5sGa45L90HcDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T12:58:47.740891Z"},"content_sha256":"8b2eccdfdb752da11293867ba628c1783654ffea75de961ce134ea12face8016","schema_version":"1.0","event_id":"sha256:8b2eccdfdb752da11293867ba628c1783654ffea75de961ce134ea12face8016"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7/bundle.json","state_url":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VJGKNGU5Z4473VEFZYMVCIARB7/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":"2026-08-08T12:58:47Z","links":{"resolver":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7","bundle":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7/bundle.json","state":"https://pith.science/pith/VJGKNGU5Z4473VEFZYMVCIARB7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VJGKNGU5Z4473VEFZYMVCIARB7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:VJGKNGU5Z4473VEFZYMVCIARB7","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":"b3bc6c5b27d803529178ae54f8c0c1e15c3a96baf0a77725b47aea62abeb663e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T20:21:11Z","title_canon_sha256":"ea765fc3c03c59f9cf5672bb0ab975e992a2bc3f75e9182d98fb49e9c882089f"},"schema_version":"1.0","source":{"id":"2509.02807","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.02807","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"arxiv_version","alias_value":"2509.02807v1","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.02807","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"pith_short_12","alias_value":"VJGKNGU5Z447","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"pith_short_16","alias_value":"VJGKNGU5Z4473VEF","created_at":"2026-07-05T12:03:58Z"},{"alias_kind":"pith_short_8","alias_value":"VJGKNGU5","created_at":"2026-07-05T12:03:58Z"}],"graph_snapshots":[{"event_id":"sha256:8b2eccdfdb752da11293867ba628c1783654ffea75de961ce134ea12face8016","target":"graph","created_at":"2026-07-05T12:03:58Z","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/2509.02807/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Mennatullah Siam","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T20:21:11Z","title":"PixFoundation 2.0: Do Video Multi-Modal LLMs Use Motion in Visual Grounding?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.02807","kind":"arxiv","version":1},"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:c9b78df4a395c2216d10426ede2a4e5677886010408c76b61c7505d1c8189d18","target":"record","created_at":"2026-07-05T12:03:58Z","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":"b3bc6c5b27d803529178ae54f8c0c1e15c3a96baf0a77725b47aea62abeb663e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-02T20:21:11Z","title_canon_sha256":"ea765fc3c03c59f9cf5672bb0ab975e992a2bc3f75e9182d98fb49e9c882089f"},"schema_version":"1.0","source":{"id":"2509.02807","kind":"arxiv","version":1}},"canonical_sha256":"aa4ca69a9dcf39fdd485ce195120110fd12ed9fd7f89fbf57c7afc0a806a3132","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aa4ca69a9dcf39fdd485ce195120110fd12ed9fd7f89fbf57c7afc0a806a3132","first_computed_at":"2026-07-05T12:03:58.038502Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:03:58.038502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e4mDo2qKBabHWovOgyYa/RlUts3I8x6HJlPMvqRzKtqHA6jb8sL/eCPttfJaKTD6y/pppH4DEY/4957H1RMqBA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:03:58.039054Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.02807","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c9b78df4a395c2216d10426ede2a4e5677886010408c76b61c7505d1c8189d18","sha256:8b2eccdfdb752da11293867ba628c1783654ffea75de961ce134ea12face8016"],"state_sha256":"501bffacdf894d45b8d4634f3e7fa427135ea21ee31665a0c84018160448fe2a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2EXL6exfsW+jkV94pvceSZdFJsmfCVOx65zvQb1CKbdtK2xCxM5qOuDkXMMcpSQr+jTqe6TWpvmvlwlrQXCrBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T12:58:47.747522Z","bundle_sha256":"bba621c2c85a3a3afc2eb18ee41f342d3c96db108c4a01f4355e656021f472c1"}}