{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2TJKE4PFCATGWJRBZS7SOQOSLB","short_pith_number":"pith:2TJKE4PF","canonical_record":{"source":{"id":"2404.10838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T18:22:49Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"b4ccd575db39a18a717c281b6c49ea807b6d545befa1bc874a3ca5f8391e648e","abstract_canon_sha256":"083f8358ffcaf6332413e16b5204f70a555d1cf6084b5d7ec17cf3fc2dfd6bdd"},"schema_version":"1.0"},"canonical_sha256":"d4d2a271e510266b2621ccbf2741d2584db7ba12dd078e46ccabb86f85427e22","source":{"kind":"arxiv","id":"2404.10838","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10838","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10838v1","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10838","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"2TJKE4PFCATG","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"2TJKE4PFCATGWJRB","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"2TJKE4PF","created_at":"2026-07-05T08:08:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2TJKE4PFCATGWJRBZS7SOQOSLB","target":"record","payload":{"canonical_record":{"source":{"id":"2404.10838","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T18:22:49Z","cross_cats_sorted":["cs.CL","cs.MM"],"title_canon_sha256":"b4ccd575db39a18a717c281b6c49ea807b6d545befa1bc874a3ca5f8391e648e","abstract_canon_sha256":"083f8358ffcaf6332413e16b5204f70a555d1cf6084b5d7ec17cf3fc2dfd6bdd"},"schema_version":"1.0"},"canonical_sha256":"d4d2a271e510266b2621ccbf2741d2584db7ba12dd078e46ccabb86f85427e22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:08:59.631551Z","signature_b64":"/t6RvDhNxPsE4oXhcEO3p2IUBF8bTLdygksNhPtOmBcDOOrn6LnWp0fCWgY77/BCiOOxrySsPy0YeJ6Jg6cfAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d4d2a271e510266b2621ccbf2741d2584db7ba12dd078e46ccabb86f85427e22","last_reissued_at":"2026-07-05T08:08:59.631120Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:08:59.631120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2404.10838","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":"2026-07-05T08:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s46pD8px0bJqPKhPFGuYpKhLp4wjzKVHjWns3JimkTdjLYiOmH2IUGIaGCEH+pz1zIPrsIz+ACoJPX5ZqrKXCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T11:01:54.124695Z"},"content_sha256":"ae9f65e74ca26c46484af80e0e358d30a931c217fbc0e71e7fdec19478f8065c","schema_version":"1.0","event_id":"sha256:ae9f65e74ca26c46484af80e0e358d30a931c217fbc0e71e7fdec19478f8065c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2TJKE4PFCATGWJRBZS7SOQOSLB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.MM"],"primary_cat":"cs.CV","authors_text":"Meiyu Liang, Wei Huang, Yawen Li, Zhengyang Liang, Zhe Xue","submitted_at":"2024-04-16T18:22:49Z","abstract_excerpt":"In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required for their training present significant hurdles for deployment in environments with limited computational resources. To address this challenge, we propose a novel dynamic self-adaptive multiscale distillation from pre-trained multimodal large model for efficient cross-modal representation learning for the first time. Unlike existing distillation methods, our "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10838","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/2404.10838/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":"2026-07-05T08:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2IehmxOGmF0GN744v/3WAjclSjVkVzH5RxAfvzOsWqHoVo+zjS1Wdh6vzQP8dYlbY0m+r2dVJTQ7nhkyuOkICg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T11:01:54.125069Z"},"content_sha256":"241640a4863aa8a02e4f062e11f8f7669a748dabcdf81f2f210cbd30d5b7ac5f","schema_version":"1.0","event_id":"sha256:241640a4863aa8a02e4f062e11f8f7669a748dabcdf81f2f210cbd30d5b7ac5f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2TJKE4PFCATGWJRBZS7SOQOSLB/bundle.json","state_url":"https://pith.science/pith/2TJKE4PFCATGWJRBZS7SOQOSLB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2TJKE4PFCATGWJRBZS7SOQOSLB/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":"2026-07-16T11:01:54Z","links":{"resolver":"https://pith.science/pith/2TJKE4PFCATGWJRBZS7SOQOSLB","bundle":"https://pith.science/pith/2TJKE4PFCATGWJRBZS7SOQOSLB/bundle.json","state":"https://pith.science/pith/2TJKE4PFCATGWJRBZS7SOQOSLB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2TJKE4PFCATGWJRBZS7SOQOSLB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2TJKE4PFCATGWJRBZS7SOQOSLB","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":"083f8358ffcaf6332413e16b5204f70a555d1cf6084b5d7ec17cf3fc2dfd6bdd","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T18:22:49Z","title_canon_sha256":"b4ccd575db39a18a717c281b6c49ea807b6d545befa1bc874a3ca5f8391e648e"},"schema_version":"1.0","source":{"id":"2404.10838","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.10838","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2404.10838v1","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.10838","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"2TJKE4PFCATG","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"2TJKE4PFCATGWJRB","created_at":"2026-07-05T08:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"2TJKE4PF","created_at":"2026-07-05T08:08:59Z"}],"graph_snapshots":[{"event_id":"sha256:241640a4863aa8a02e4f062e11f8f7669a748dabcdf81f2f210cbd30d5b7ac5f","target":"graph","created_at":"2026-07-05T08:08:59Z","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/2404.10838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, pre-trained multimodal large models have attracted widespread attention due to their outstanding performance in various multimodal applications. Nonetheless, the extensive computational resources and vast datasets required for their training present significant hurdles for deployment in environments with limited computational resources. To address this challenge, we propose a novel dynamic self-adaptive multiscale distillation from pre-trained multimodal large model for efficient cross-modal representation learning for the first time. Unlike existing distillation methods, our ","authors_text":"Meiyu Liang, Wei Huang, Yawen Li, Zhengyang Liang, Zhe Xue","cross_cats":["cs.CL","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T18:22:49Z","title":"Dynamic Self-adaptive Multiscale Distillation from Pre-trained Multimodal Large Model for Efficient Cross-modal Representation Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.10838","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:ae9f65e74ca26c46484af80e0e358d30a931c217fbc0e71e7fdec19478f8065c","target":"record","created_at":"2026-07-05T08:08:59Z","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":"083f8358ffcaf6332413e16b5204f70a555d1cf6084b5d7ec17cf3fc2dfd6bdd","cross_cats_sorted":["cs.CL","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-04-16T18:22:49Z","title_canon_sha256":"b4ccd575db39a18a717c281b6c49ea807b6d545befa1bc874a3ca5f8391e648e"},"schema_version":"1.0","source":{"id":"2404.10838","kind":"arxiv","version":1}},"canonical_sha256":"d4d2a271e510266b2621ccbf2741d2584db7ba12dd078e46ccabb86f85427e22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d4d2a271e510266b2621ccbf2741d2584db7ba12dd078e46ccabb86f85427e22","first_computed_at":"2026-07-05T08:08:59.631120Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:08:59.631120Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/t6RvDhNxPsE4oXhcEO3p2IUBF8bTLdygksNhPtOmBcDOOrn6LnWp0fCWgY77/BCiOOxrySsPy0YeJ6Jg6cfAg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:08:59.631551Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.10838","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae9f65e74ca26c46484af80e0e358d30a931c217fbc0e71e7fdec19478f8065c","sha256:241640a4863aa8a02e4f062e11f8f7669a748dabcdf81f2f210cbd30d5b7ac5f"],"state_sha256":"7d099e2245d92e3bc9eb4ba93ab51f5f611aa9c78f7424ce0f54cf56c8010994"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HU1FEy2WGvOySYzPuhg3AvrH6tnwYtHTL9WF6OmNzrZ0WCH3Z2PAauQWBykVA4jPfigNPiCQ6SOlT2Y2uraqCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T11:01:54.127305Z","bundle_sha256":"c3dcc6f9e3ab1c42768150286a6756db7fcf4591e80b181ac6b3df03ea167a49"}}