{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XWAGSUJ3FKYFTAQRX7UOS2AMTA","short_pith_number":"pith:XWAGSUJ3","canonical_record":{"source":{"id":"2410.06395","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T21:57:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90d35af6e1946624fc503add7d5fcf58cf450bda50076fb7beae7c00d458d45c","abstract_canon_sha256":"64bad2b782dfd13db5647e5c8f06fd1ee64b1e602dac4068bf47687ece20fc0d"},"schema_version":"1.0"},"canonical_sha256":"bd8069513b2ab0598211bfe8e9680c9817bb62f522f4244154fab89e4b7856af","source":{"kind":"arxiv","id":"2410.06395","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06395","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06395v1","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06395","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"XWAGSUJ3FKYF","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"XWAGSUJ3FKYFTAQR","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"XWAGSUJ3","created_at":"2026-07-05T09:18:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XWAGSUJ3FKYFTAQRX7UOS2AMTA","target":"record","payload":{"canonical_record":{"source":{"id":"2410.06395","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T21:57:46Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"90d35af6e1946624fc503add7d5fcf58cf450bda50076fb7beae7c00d458d45c","abstract_canon_sha256":"64bad2b782dfd13db5647e5c8f06fd1ee64b1e602dac4068bf47687ece20fc0d"},"schema_version":"1.0"},"canonical_sha256":"bd8069513b2ab0598211bfe8e9680c9817bb62f522f4244154fab89e4b7856af","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:00.958698Z","signature_b64":"snP4beFd6796uF5lgtmIaK6AR2H+w5Q9CoX1/8C2l1qiIDA2tlNHP98uuE529OaDAkrMQrwwAgTmFLriVoQWDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd8069513b2ab0598211bfe8e9680c9817bb62f522f4244154fab89e4b7856af","last_reissued_at":"2026-07-05T09:18:00.958249Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:00.958249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.06395","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":"2026-07-05T09:18:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1dasvSyX2J/Wx0ffq9fM3E/ApXsGqf7tdmaJ4l+UxhF+3vxzTimg9E3atBOPhbRrvQBTfE9fFYwsOvOS06p+Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:50:20.508512Z"},"content_sha256":"4751cd79216fa8e2b8015876737dbee806b6aa05d4cbd32f11251b9a5e77d90f","schema_version":"1.0","event_id":"sha256:4751cd79216fa8e2b8015876737dbee806b6aa05d4cbd32f11251b9a5e77d90f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XWAGSUJ3FKYFTAQRX7UOS2AMTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Multimodal Representation Learning using Adaptive Graph Construction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Weichen Huang","submitted_at":"2024-10-08T21:57:46Z","abstract_excerpt":"Multimodal contrastive learning train neural networks by levergaing data from heterogeneous sources such as images and text. Yet, many current multimodal learning architectures cannot generalize to an arbitrary number of modalities and need to be hand-constructed. We propose AutoBIND, a novel contrastive learning framework that can learn representations from an arbitrary number of modalites through graph optimization. We evaluate AutoBIND on Alzhiemer's disease detection because it has real-world medical applicability and it contains a broad range of data modalities. We show that AutoBIND outp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06395","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/2410.06395/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":"2026-07-05T09:18:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"l1h+zNEoWbKc7pNm1yF6Eb7s6dT3KDVRl1cOv5KayD1HB5itKTh6LXy14RkWtzQbRi3Wu9OSREs/OcIkAv2vAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T17:50:20.508789Z"},"content_sha256":"322fd060f699ac40730ed87cd07390a974d671bf64c07039a50632bc60970e4d","schema_version":"1.0","event_id":"sha256:322fd060f699ac40730ed87cd07390a974d671bf64c07039a50632bc60970e4d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XWAGSUJ3FKYFTAQRX7UOS2AMTA/bundle.json","state_url":"https://pith.science/pith/XWAGSUJ3FKYFTAQRX7UOS2AMTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XWAGSUJ3FKYFTAQRX7UOS2AMTA/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":"2026-07-31T17:50:20Z","links":{"resolver":"https://pith.science/pith/XWAGSUJ3FKYFTAQRX7UOS2AMTA","bundle":"https://pith.science/pith/XWAGSUJ3FKYFTAQRX7UOS2AMTA/bundle.json","state":"https://pith.science/pith/XWAGSUJ3FKYFTAQRX7UOS2AMTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XWAGSUJ3FKYFTAQRX7UOS2AMTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XWAGSUJ3FKYFTAQRX7UOS2AMTA","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":"64bad2b782dfd13db5647e5c8f06fd1ee64b1e602dac4068bf47687ece20fc0d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T21:57:46Z","title_canon_sha256":"90d35af6e1946624fc503add7d5fcf58cf450bda50076fb7beae7c00d458d45c"},"schema_version":"1.0","source":{"id":"2410.06395","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.06395","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"arxiv_version","alias_value":"2410.06395v1","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.06395","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"pith_short_12","alias_value":"XWAGSUJ3FKYF","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"pith_short_16","alias_value":"XWAGSUJ3FKYFTAQR","created_at":"2026-07-05T09:18:00Z"},{"alias_kind":"pith_short_8","alias_value":"XWAGSUJ3","created_at":"2026-07-05T09:18:00Z"}],"graph_snapshots":[{"event_id":"sha256:322fd060f699ac40730ed87cd07390a974d671bf64c07039a50632bc60970e4d","target":"graph","created_at":"2026-07-05T09:18:00Z","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/2410.06395/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal contrastive learning train neural networks by levergaing data from heterogeneous sources such as images and text. Yet, many current multimodal learning architectures cannot generalize to an arbitrary number of modalities and need to be hand-constructed. We propose AutoBIND, a novel contrastive learning framework that can learn representations from an arbitrary number of modalites through graph optimization. We evaluate AutoBIND on Alzhiemer's disease detection because it has real-world medical applicability and it contains a broad range of data modalities. We show that AutoBIND outp","authors_text":"Weichen Huang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T21:57:46Z","title":"Multimodal Representation Learning using Adaptive Graph Construction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.06395","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":"sha256:4751cd79216fa8e2b8015876737dbee806b6aa05d4cbd32f11251b9a5e77d90f","target":"record","created_at":"2026-07-05T09:18:00Z","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":"64bad2b782dfd13db5647e5c8f06fd1ee64b1e602dac4068bf47687ece20fc0d","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-08T21:57:46Z","title_canon_sha256":"90d35af6e1946624fc503add7d5fcf58cf450bda50076fb7beae7c00d458d45c"},"schema_version":"1.0","source":{"id":"2410.06395","kind":"arxiv","version":1}},"canonical_sha256":"bd8069513b2ab0598211bfe8e9680c9817bb62f522f4244154fab89e4b7856af","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd8069513b2ab0598211bfe8e9680c9817bb62f522f4244154fab89e4b7856af","first_computed_at":"2026-07-05T09:18:00.958249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:18:00.958249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"snP4beFd6796uF5lgtmIaK6AR2H+w5Q9CoX1/8C2l1qiIDA2tlNHP98uuE529OaDAkrMQrwwAgTmFLriVoQWDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:18:00.958698Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.06395","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4751cd79216fa8e2b8015876737dbee806b6aa05d4cbd32f11251b9a5e77d90f","sha256:322fd060f699ac40730ed87cd07390a974d671bf64c07039a50632bc60970e4d"],"state_sha256":"6ecf736fa8b136e81f8be4635bad0fadbac64c26f46a7327f3588f40601be172"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WDQ7I/SYktCDDmzKV315M49qygatCYMjM2hWI75K+J1Tywde9eI+GMBOPSoS4lFWklSwAdfHUNGHPK/IVC5iDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T17:50:20.511503Z","bundle_sha256":"555fd5cafebc1764bacdc613443e0995fd4407d6abad884a6a91ff39a5ab00b8"}}