{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GSRFRWADLYGKYSYS422S4SLZV6","short_pith_number":"pith:GSRFRWAD","schema_version":"1.0","canonical_sha256":"34a258d8035e0cac4b12e6b52e4979afa857fd60af0b16d9c421796aa5ee02ad","source":{"kind":"arxiv","id":"2408.00754","version":2},"attestation_state":"computed","paper":{"title":"Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Benlin Liu, Luming Tang, Ranjay Krishna, Wei-Chiu Ma, Yansong Tang, Yiqin Wang, Yongming Rao, Yuhao Dong, Zixian Ma","submitted_at":"2024-08-01T17:57:12Z","abstract_excerpt":"Multimodal language models (MLLMs) are increasingly being applied in real-world environments, necessitating their ability to interpret 3D spaces and comprehend temporal dynamics. Current methods often rely on specialized architectural designs or task-specific fine-tuning to achieve this. We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input, without modifying the architecture or requiring task-specific fine-tuning. Our method uses a lightweight tracking model to identify primary object correspondences between fr"},"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":"2408.00754","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:57:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"08fca8805015ffc9520fdb6a84e21b3fc2544f56a38380ecd76fe457f3828a85","abstract_canon_sha256":"597ca82b47265665f9369798df30f95965abf02674e203118156c2084a2739a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:28.390361Z","signature_b64":"9FX2EHfQbPKyxIvu5BXQcgFlPe8PvWO6PdEFVxp5gQfbFg6GuLrFwSqZv7FhQ8pc9rBoYMPYK7s7EQJCaxLyAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34a258d8035e0cac4b12e6b52e4979afa857fd60af0b16d9c421796aa5ee02ad","last_reissued_at":"2026-07-05T09:38:28.389887Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:28.389887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Benlin Liu, Luming Tang, Ranjay Krishna, Wei-Chiu Ma, Yansong Tang, Yiqin Wang, Yongming Rao, Yuhao Dong, Zixian Ma","submitted_at":"2024-08-01T17:57:12Z","abstract_excerpt":"Multimodal language models (MLLMs) are increasingly being applied in real-world environments, necessitating their ability to interpret 3D spaces and comprehend temporal dynamics. Current methods often rely on specialized architectural designs or task-specific fine-tuning to achieve this. We introduce Coarse Correspondences, a simple lightweight method that enhances MLLMs' spatial-temporal reasoning with 2D images as input, without modifying the architecture or requiring task-specific fine-tuning. Our method uses a lightweight tracking model to identify primary object correspondences between fr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00754","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/2408.00754/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":"2408.00754","created_at":"2026-07-05T09:38:28.389942+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.00754v2","created_at":"2026-07-05T09:38:28.389942+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00754","created_at":"2026-07-05T09:38:28.389942+00:00"},{"alias_kind":"pith_short_12","alias_value":"GSRFRWADLYGK","created_at":"2026-07-05T09:38:28.389942+00:00"},{"alias_kind":"pith_short_16","alias_value":"GSRFRWADLYGKYSYS","created_at":"2026-07-05T09:38:28.389942+00:00"},{"alias_kind":"pith_short_8","alias_value":"GSRFRWAD","created_at":"2026-07-05T09:38:28.389942+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2412.14171","citing_title":"Thinking in Space: How Multimodal Large Language Models See, Remember, and Recall Spaces","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2507.05920","citing_title":"High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6","json":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6.json","graph_json":"https://pith.science/api/pith-number/GSRFRWADLYGKYSYS422S4SLZV6/graph.json","events_json":"https://pith.science/api/pith-number/GSRFRWADLYGKYSYS422S4SLZV6/events.json","paper":"https://pith.science/paper/GSRFRWAD"},"agent_actions":{"view_html":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6","download_json":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6.json","view_paper":"https://pith.science/paper/GSRFRWAD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.00754&json=true","fetch_graph":"https://pith.science/api/pith-number/GSRFRWADLYGKYSYS422S4SLZV6/graph.json","fetch_events":"https://pith.science/api/pith-number/GSRFRWADLYGKYSYS422S4SLZV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6/action/storage_attestation","attest_author":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6/action/author_attestation","sign_citation":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6/action/citation_signature","submit_replication":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6/action/replication_record"}},"created_at":"2026-07-05T09:38:28.389942+00:00","updated_at":"2026-07-05T09:38:28.389942+00:00"}