{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3435VKJPK5SLLXVR7D5YCBKJHS","short_pith_number":"pith:3435VKJP","canonical_record":{"source":{"id":"2403.11373","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T23:44:20Z","cross_cats_sorted":[],"title_canon_sha256":"af7d9ffbdd8baee3224fa3cd21849766e9aca87ca7df6ffce5465ec4e252a95d","abstract_canon_sha256":"3f827d81122994cbeb91b7490519906976f0ca5b4799746e7478892cffd967c6"},"schema_version":"1.0"},"canonical_sha256":"df37daa92f5764b5deb1f8fb8105493cb2ff13e5dd959f384584cf015c68c9f2","source":{"kind":"arxiv","id":"2403.11373","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11373","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11373v1","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11373","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"3435VKJPK5SL","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"pith_short_16","alias_value":"3435VKJPK5SLLXVR","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"pith_short_8","alias_value":"3435VKJP","created_at":"2026-07-05T07:57:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3435VKJPK5SLLXVR7D5YCBKJHS","target":"record","payload":{"canonical_record":{"source":{"id":"2403.11373","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T23:44:20Z","cross_cats_sorted":[],"title_canon_sha256":"af7d9ffbdd8baee3224fa3cd21849766e9aca87ca7df6ffce5465ec4e252a95d","abstract_canon_sha256":"3f827d81122994cbeb91b7490519906976f0ca5b4799746e7478892cffd967c6"},"schema_version":"1.0"},"canonical_sha256":"df37daa92f5764b5deb1f8fb8105493cb2ff13e5dd959f384584cf015c68c9f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:57:15.336698Z","signature_b64":"H2T0eHIm+lbAr5xan2LOPO2yIO9qsheponnQ0Y9UjokBFP4kt7KQWt3W0WG6d8nP76bRTymrSUwtCArqaXrACw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df37daa92f5764b5deb1f8fb8105493cb2ff13e5dd959f384584cf015c68c9f2","last_reissued_at":"2026-07-05T07:57:15.336191Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:57:15.336191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.11373","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":"2026-07-05T07:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dKWE44bhmThKAMA21QE3dMBwhukL3im567cXMVeEhAgm4OARd1TIHT+l5YHv/SZvPny2vbvsT7oJVE3T2nLyCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:07:54.057555Z"},"content_sha256":"f5ad709383d54cf7b41ba58be05c153c34cecd2942f7d8dffce1cca3f47dc733","schema_version":"1.0","event_id":"sha256:f5ad709383d54cf7b41ba58be05c153c34cecd2942f7d8dffce1cca3f47dc733"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3435VKJPK5SLLXVR7D5YCBKJHS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Huijuan Xu, Shu Zhao, Tan Yu, Xiaohan Zou","submitted_at":"2024-03-17T23:44:20Z","abstract_excerpt":"Pre-trained large multi-modal models (LMMs) exploit fine-tuning to adapt diverse user applications. Nevertheless, fine-tuning may face challenges due to deactivated sensors (e.g., cameras turned off for privacy or technical issues), yielding modality-incomplete data and leading to inconsistency in training data and the data for inference. Additionally, continuous training leads to catastrophic forgetting, diluting the knowledge in pre-trained LMMs. To overcome these challenges, we introduce a novel task, Continual Missing Modality Learning (CMML), to investigate how models can generalize when "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11373","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/2403.11373/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":"2026-07-05T07:57:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8D8MLqqudmDiwZj3bjIw626QAd4RLNcIkVlAWGQ4j05gYLhUuT45PG94gL7NOT4sir4PmB5PuzZTMfqiVwoHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:07:54.057917Z"},"content_sha256":"02937d6a5e36120c864ad0702184c26fdba44891fb1bef16cf32780559afe322","schema_version":"1.0","event_id":"sha256:02937d6a5e36120c864ad0702184c26fdba44891fb1bef16cf32780559afe322"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3435VKJPK5SLLXVR7D5YCBKJHS/bundle.json","state_url":"https://pith.science/pith/3435VKJPK5SLLXVR7D5YCBKJHS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3435VKJPK5SLLXVR7D5YCBKJHS/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":"2026-08-18T11:07:54Z","links":{"resolver":"https://pith.science/pith/3435VKJPK5SLLXVR7D5YCBKJHS","bundle":"https://pith.science/pith/3435VKJPK5SLLXVR7D5YCBKJHS/bundle.json","state":"https://pith.science/pith/3435VKJPK5SLLXVR7D5YCBKJHS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3435VKJPK5SLLXVR7D5YCBKJHS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3435VKJPK5SLLXVR7D5YCBKJHS","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":"3f827d81122994cbeb91b7490519906976f0ca5b4799746e7478892cffd967c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T23:44:20Z","title_canon_sha256":"af7d9ffbdd8baee3224fa3cd21849766e9aca87ca7df6ffce5465ec4e252a95d"},"schema_version":"1.0","source":{"id":"2403.11373","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.11373","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.11373v1","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.11373","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"pith_short_12","alias_value":"3435VKJPK5SL","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"pith_short_16","alias_value":"3435VKJPK5SLLXVR","created_at":"2026-07-05T07:57:15Z"},{"alias_kind":"pith_short_8","alias_value":"3435VKJP","created_at":"2026-07-05T07:57:15Z"}],"graph_snapshots":[{"event_id":"sha256:02937d6a5e36120c864ad0702184c26fdba44891fb1bef16cf32780559afe322","target":"graph","created_at":"2026-07-05T07:57:15Z","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/2403.11373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained large multi-modal models (LMMs) exploit fine-tuning to adapt diverse user applications. Nevertheless, fine-tuning may face challenges due to deactivated sensors (e.g., cameras turned off for privacy or technical issues), yielding modality-incomplete data and leading to inconsistency in training data and the data for inference. Additionally, continuous training leads to catastrophic forgetting, diluting the knowledge in pre-trained LMMs. To overcome these challenges, we introduce a novel task, Continual Missing Modality Learning (CMML), to investigate how models can generalize when ","authors_text":"Huijuan Xu, Shu Zhao, Tan Yu, Xiaohan Zou","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T23:44:20Z","title":"Reconstruct before Query: Continual Missing Modality Learning with Decomposed Prompt Collaboration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.11373","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:f5ad709383d54cf7b41ba58be05c153c34cecd2942f7d8dffce1cca3f47dc733","target":"record","created_at":"2026-07-05T07:57:15Z","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":"3f827d81122994cbeb91b7490519906976f0ca5b4799746e7478892cffd967c6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-03-17T23:44:20Z","title_canon_sha256":"af7d9ffbdd8baee3224fa3cd21849766e9aca87ca7df6ffce5465ec4e252a95d"},"schema_version":"1.0","source":{"id":"2403.11373","kind":"arxiv","version":1}},"canonical_sha256":"df37daa92f5764b5deb1f8fb8105493cb2ff13e5dd959f384584cf015c68c9f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df37daa92f5764b5deb1f8fb8105493cb2ff13e5dd959f384584cf015c68c9f2","first_computed_at":"2026-07-05T07:57:15.336191Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:57:15.336191Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H2T0eHIm+lbAr5xan2LOPO2yIO9qsheponnQ0Y9UjokBFP4kt7KQWt3W0WG6d8nP76bRTymrSUwtCArqaXrACw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:57:15.336698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.11373","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5ad709383d54cf7b41ba58be05c153c34cecd2942f7d8dffce1cca3f47dc733","sha256:02937d6a5e36120c864ad0702184c26fdba44891fb1bef16cf32780559afe322"],"state_sha256":"77911242175960874bc180223985ce9062f0c2b617d6dd19dc55b66d94609650"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"F6JMxBr2pNIA1NmvO+DFAeJcANYbsiknPcxPK3PUkgGy8DISLXHWI0FVI9IqCwpYhPItWc0Ai2HbHBR2GeL+Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:07:54.061283Z","bundle_sha256":"1a82bdb105a6b752cb9092c5366beccfa28f17c489ba0f1675b222f9531c2bc1"}}