{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GSRFRWADLYGKYSYS422S4SLZV6","short_pith_number":"pith:GSRFRWAD","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"},"canonical_sha256":"34a258d8035e0cac4b12e6b52e4979afa857fd60af0b16d9c421796aa5ee02ad","source":{"kind":"arxiv","id":"2408.00754","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00754","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00754v2","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00754","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"GSRFRWADLYGK","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"GSRFRWADLYGKYSYS","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"GSRFRWAD","created_at":"2026-07-05T09:38:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GSRFRWADLYGKYSYS422S4SLZV6","target":"record","payload":{"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"},"canonical_sha256":"34a258d8035e0cac4b12e6b52e4979afa857fd60af0b16d9c421796aa5ee02ad","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"},"source_kind":"arxiv","source_id":"2408.00754","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":"2026-07-05T09:38:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SoZ2/angIbJj2Znq38ndz5Xdn/ZGSoHFRgnzBL3UetAxjFa18QaaWphDJplkEZuHUqfbS9ZlY8sb3sDtQG0VBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:23:54.128232Z"},"content_sha256":"998a0f77ab26f14d4ed20d8223931b125e162da246b262af43668df2d115b0ba","schema_version":"1.0","event_id":"sha256:998a0f77ab26f14d4ed20d8223931b125e162da246b262af43668df2d115b0ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GSRFRWADLYGKYSYS422S4SLZV6","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:38:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uiN8ZfeSjVR9r6ZvEUruWSKrAaEupAkA2O3IAaK7SaKrIvl0oWSNCAOjhnCClUIWQn5C4LPaCMuntqvZOhEYAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T21:23:54.129345Z"},"content_sha256":"8f72f6d06b0f2391bd485afec832f726f220988348e727b943876cab18cd151a","schema_version":"1.0","event_id":"sha256:8f72f6d06b0f2391bd485afec832f726f220988348e727b943876cab18cd151a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6/bundle.json","state_url":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GSRFRWADLYGKYSYS422S4SLZV6/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":"2026-08-10T21:23:54Z","links":{"resolver":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6","bundle":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6/bundle.json","state":"https://pith.science/pith/GSRFRWADLYGKYSYS422S4SLZV6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GSRFRWADLYGKYSYS422S4SLZV6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GSRFRWADLYGKYSYS422S4SLZV6","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":"597ca82b47265665f9369798df30f95965abf02674e203118156c2084a2739a6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:57:12Z","title_canon_sha256":"08fca8805015ffc9520fdb6a84e21b3fc2544f56a38380ecd76fe457f3828a85"},"schema_version":"1.0","source":{"id":"2408.00754","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.00754","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"arxiv_version","alias_value":"2408.00754v2","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.00754","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"pith_short_12","alias_value":"GSRFRWADLYGK","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"pith_short_16","alias_value":"GSRFRWADLYGKYSYS","created_at":"2026-07-05T09:38:28Z"},{"alias_kind":"pith_short_8","alias_value":"GSRFRWAD","created_at":"2026-07-05T09:38:28Z"}],"graph_snapshots":[{"event_id":"sha256:8f72f6d06b0f2391bd485afec832f726f220988348e727b943876cab18cd151a","target":"graph","created_at":"2026-07-05T09:38:28Z","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/2408.00754/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Benlin Liu, Luming Tang, Ranjay Krishna, Wei-Chiu Ma, Yansong Tang, Yiqin Wang, Yongming Rao, Yuhao Dong, Zixian Ma","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:57:12Z","title":"Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.00754","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":"sha256:998a0f77ab26f14d4ed20d8223931b125e162da246b262af43668df2d115b0ba","target":"record","created_at":"2026-07-05T09:38:28Z","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":"597ca82b47265665f9369798df30f95965abf02674e203118156c2084a2739a6","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-01T17:57:12Z","title_canon_sha256":"08fca8805015ffc9520fdb6a84e21b3fc2544f56a38380ecd76fe457f3828a85"},"schema_version":"1.0","source":{"id":"2408.00754","kind":"arxiv","version":2}},"canonical_sha256":"34a258d8035e0cac4b12e6b52e4979afa857fd60af0b16d9c421796aa5ee02ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"34a258d8035e0cac4b12e6b52e4979afa857fd60af0b16d9c421796aa5ee02ad","first_computed_at":"2026-07-05T09:38:28.389887Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:28.389887Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9FX2EHfQbPKyxIvu5BXQcgFlPe8PvWO6PdEFVxp5gQfbFg6GuLrFwSqZv7FhQ8pc9rBoYMPYK7s7EQJCaxLyAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:28.390361Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.00754","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:998a0f77ab26f14d4ed20d8223931b125e162da246b262af43668df2d115b0ba","sha256:8f72f6d06b0f2391bd485afec832f726f220988348e727b943876cab18cd151a"],"state_sha256":"14d179c275d583391fa127fabb74b1baf71dfa444ee92a32ae7f0f64b9ea2883"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RzKh+4FswTSbf5rEYY3KHY2/IaO7NrFyBYJPsr6jG9q3pkid/5UY8LE1EmNDuBYedwZIFY1QRUpHbIMMKYpJAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T21:23:54.133340Z","bundle_sha256":"8f752baa1f385ce71b8b6a7a2642526c010587a02347f7caa594528462e90b10"}}