{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:KOO3IIRNP4AUFGCFY3SNRVHTM7","short_pith_number":"pith:KOO3IIRN","canonical_record":{"source":{"id":"2402.05889","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T18:27:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1f3a168dad0223111db76348415aa80fc8f07e08ea8b816858734d93cf4a3975","abstract_canon_sha256":"c0a4a082b1f6b53b60c628b3bbcb287f698be05b6d4c76accde7bd81797e5b94"},"schema_version":"1.0"},"canonical_sha256":"539db4222d7f01429845c6e4d8d4f367d838b5b86d45ea3cf0fa36cf052cfd7b","source":{"kind":"arxiv","id":"2402.05889","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05889","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05889v4","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05889","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"pith_short_12","alias_value":"KOO3IIRNP4AU","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"pith_short_16","alias_value":"KOO3IIRNP4AUFGCF","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"pith_short_8","alias_value":"KOO3IIRN","created_at":"2026-07-05T10:35:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:KOO3IIRNP4AUFGCFY3SNRVHTM7","target":"record","payload":{"canonical_record":{"source":{"id":"2402.05889","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T18:27:22Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"1f3a168dad0223111db76348415aa80fc8f07e08ea8b816858734d93cf4a3975","abstract_canon_sha256":"c0a4a082b1f6b53b60c628b3bbcb287f698be05b6d4c76accde7bd81797e5b94"},"schema_version":"1.0"},"canonical_sha256":"539db4222d7f01429845c6e4d8d4f367d838b5b86d45ea3cf0fa36cf052cfd7b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:35:31.374300Z","signature_b64":"J2TxvggraN1VHLvNLSVsLNSBmxErhIlbfR1f5msei8qeSjOllBH5O1ywqerOyeIuO4ndiNfIVlLWWv4vmd+bBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"539db4222d7f01429845c6e4d8d4f367d838b5b86d45ea3cf0fa36cf052cfd7b","last_reissued_at":"2026-07-05T10:35:31.373816Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:35:31.373816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.05889","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:35:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PH3BVY05ePpguKs9KJ3gNQNn409fHREkEgQPVn9DTs5HL20AoOKqlrgdWq/jxBc4DF4KCxMbo5m+D/pOSegRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:27:04.679076Z"},"content_sha256":"8b4a109c70c48a92f5c96feac3af08b47306d1f816540dfc926562f9a2abd8dc","schema_version":"1.0","event_id":"sha256:8b4a109c70c48a92f5c96feac3af08b47306d1f816540dfc926562f9a2abd8dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:KOO3IIRNP4AUFGCFY3SNRVHTM7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CV","authors_text":"Jaehong Yoon, Mohit Bansal, Shoubin Yu","submitted_at":"2024-02-08T18:27:22Z","abstract_excerpt":"Despite impressive advancements in recent multimodal reasoning approaches, they are still limited in flexibility and efficiency, as these models typically process only a few fixed modality inputs and require updates to numerous parameters. This paper tackles these critical challenges and proposes CREMA, a generalizable, highly efficient, and modular modality-fusion framework that can incorporate any new modality to enhance video reasoning. We first augment multiple informative modalities (such as optical flow, 3D point cloud, audio, thermal heatmap, and touch map) from given videos without ext"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05889","kind":"arxiv","version":4},"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/2402.05889/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":"2026-07-05T10:35:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JVndNg+GEunCnnna2qUXSBdynGlE5QaNCOL6igNNYzRboSzpy0LEExMMbaz7OUeal7azKKjNV25h/Alihx7zAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:27:04.680215Z"},"content_sha256":"571d4a58b77238c583aeacdcf9b24253f8b60d8fcb06f94d74e13c2edd6093ba","schema_version":"1.0","event_id":"sha256:571d4a58b77238c583aeacdcf9b24253f8b60d8fcb06f94d74e13c2edd6093ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KOO3IIRNP4AUFGCFY3SNRVHTM7/bundle.json","state_url":"https://pith.science/pith/KOO3IIRNP4AUFGCFY3SNRVHTM7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KOO3IIRNP4AUFGCFY3SNRVHTM7/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":"2026-08-07T23:27:04Z","links":{"resolver":"https://pith.science/pith/KOO3IIRNP4AUFGCFY3SNRVHTM7","bundle":"https://pith.science/pith/KOO3IIRNP4AUFGCFY3SNRVHTM7/bundle.json","state":"https://pith.science/pith/KOO3IIRNP4AUFGCFY3SNRVHTM7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KOO3IIRNP4AUFGCFY3SNRVHTM7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:KOO3IIRNP4AUFGCFY3SNRVHTM7","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":"c0a4a082b1f6b53b60c628b3bbcb287f698be05b6d4c76accde7bd81797e5b94","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T18:27:22Z","title_canon_sha256":"1f3a168dad0223111db76348415aa80fc8f07e08ea8b816858734d93cf4a3975"},"schema_version":"1.0","source":{"id":"2402.05889","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.05889","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"arxiv_version","alias_value":"2402.05889v4","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.05889","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"pith_short_12","alias_value":"KOO3IIRNP4AU","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"pith_short_16","alias_value":"KOO3IIRNP4AUFGCF","created_at":"2026-07-05T10:35:31Z"},{"alias_kind":"pith_short_8","alias_value":"KOO3IIRN","created_at":"2026-07-05T10:35:31Z"}],"graph_snapshots":[{"event_id":"sha256:571d4a58b77238c583aeacdcf9b24253f8b60d8fcb06f94d74e13c2edd6093ba","target":"graph","created_at":"2026-07-05T10:35:31Z","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/2402.05889/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite impressive advancements in recent multimodal reasoning approaches, they are still limited in flexibility and efficiency, as these models typically process only a few fixed modality inputs and require updates to numerous parameters. This paper tackles these critical challenges and proposes CREMA, a generalizable, highly efficient, and modular modality-fusion framework that can incorporate any new modality to enhance video reasoning. We first augment multiple informative modalities (such as optical flow, 3D point cloud, audio, thermal heatmap, and touch map) from given videos without ext","authors_text":"Jaehong Yoon, Mohit Bansal, Shoubin Yu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T18:27:22Z","title":"CREMA: Generalizable and Efficient Video-Language Reasoning via Multimodal Modular Fusion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.05889","kind":"arxiv","version":4},"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":"sha256:8b4a109c70c48a92f5c96feac3af08b47306d1f816540dfc926562f9a2abd8dc","target":"record","created_at":"2026-07-05T10:35:31Z","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":"c0a4a082b1f6b53b60c628b3bbcb287f698be05b6d4c76accde7bd81797e5b94","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-02-08T18:27:22Z","title_canon_sha256":"1f3a168dad0223111db76348415aa80fc8f07e08ea8b816858734d93cf4a3975"},"schema_version":"1.0","source":{"id":"2402.05889","kind":"arxiv","version":4}},"canonical_sha256":"539db4222d7f01429845c6e4d8d4f367d838b5b86d45ea3cf0fa36cf052cfd7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"539db4222d7f01429845c6e4d8d4f367d838b5b86d45ea3cf0fa36cf052cfd7b","first_computed_at":"2026-07-05T10:35:31.373816Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:35:31.373816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J2TxvggraN1VHLvNLSVsLNSBmxErhIlbfR1f5msei8qeSjOllBH5O1ywqerOyeIuO4ndiNfIVlLWWv4vmd+bBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:35:31.374300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.05889","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b4a109c70c48a92f5c96feac3af08b47306d1f816540dfc926562f9a2abd8dc","sha256:571d4a58b77238c583aeacdcf9b24253f8b60d8fcb06f94d74e13c2edd6093ba"],"state_sha256":"c844c2393f3c9f7058ba1422a46581452aeed55cb903a6bf3f47b26c94200a6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4TqksYZfiN9QV+t3YHCFpm6O2vZQB7aMD/Xou8z0oECtJeyuNARqd4i14+Gvh2pJR2c0/PZjAWFRzU+mqY8OAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:27:04.690798Z","bundle_sha256":"4c62e3df1c7fffacf8684bb2bfed419b9d326c1bc063f8ea16f28c172782a5b7"}}