{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WMQGN6VNBIYBOGV4F7QIVFJZNA","short_pith_number":"pith:WMQGN6VN","canonical_record":{"source":{"id":"2408.05097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T14:39:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"572f372858bc9883d3ba54e38b67062a0d188778e6ccd1afdec3455dfcbd53f2","abstract_canon_sha256":"4f123ed5359cd345a09740862a0fa47a0beb32f40cb452c2929a2426fd874d6c"},"schema_version":"1.0"},"canonical_sha256":"b32066faad0a30171abc2fe08a953968180947a4d449d7cf581f33bb3a38b556","source":{"kind":"arxiv","id":"2408.05097","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05097","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05097v1","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05097","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_12","alias_value":"WMQGN6VNBIYB","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_16","alias_value":"WMQGN6VNBIYBOGV4","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_8","alias_value":"WMQGN6VN","created_at":"2026-07-05T08:53:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WMQGN6VNBIYBOGV4F7QIVFJZNA","target":"record","payload":{"canonical_record":{"source":{"id":"2408.05097","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T14:39:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"572f372858bc9883d3ba54e38b67062a0d188778e6ccd1afdec3455dfcbd53f2","abstract_canon_sha256":"4f123ed5359cd345a09740862a0fa47a0beb32f40cb452c2929a2426fd874d6c"},"schema_version":"1.0"},"canonical_sha256":"b32066faad0a30171abc2fe08a953968180947a4d449d7cf581f33bb3a38b556","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:53:56.715624Z","signature_b64":"2hxn4lC+UFqBCIeamVWTkIy3uVXMAh4hgobVUdsPfRsP44Dnf/yCoJ1ZBocQrfZKtjfB2TAUqEZlVkaZmDF2CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b32066faad0a30171abc2fe08a953968180947a4d449d7cf581f33bb3a38b556","last_reissued_at":"2026-07-05T08:53:56.715250Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:53:56.715250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2408.05097","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":"2026-07-05T08:53:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dVE3iKt4342YOlF0whsqT/A3PuLmKgCnuQoWp82Z4faqZWyQQoocFpdSK8LrTD/rBiG7UN4AdrVYbDXMKxGBCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:26:40.623223Z"},"content_sha256":"bda79c5c7c3f8c450fac5e988a48a27856f6c9e83d9dc11cbb5afab7571d264a","schema_version":"1.0","event_id":"sha256:bda79c5c7c3f8c450fac5e988a48a27856f6c9e83d9dc11cbb5afab7571d264a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WMQGN6VNBIYBOGV4F7QIVFJZNA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Hyperbolic Learning with Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Fabio Galasso, Konstantinos Kallidromitis, Luca Franco, Paolo Mandica, Suzanne Petryk","submitted_at":"2024-08-09T14:39:15Z","abstract_excerpt":"Hyperbolic embeddings have demonstrated their effectiveness in capturing measures of uncertainty and hierarchical relationships across various deep-learning tasks, including image segmentation and active learning. However, their application in modern vision-language models (VLMs) has been limited. A notable exception is MERU, which leverages the hierarchical properties of hyperbolic space in the CLIP ViT-large model, consisting of hundreds of millions parameters. In our work, we address the challenges of scaling multi-modal hyperbolic models by orders of magnitude in terms of parameters (billi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05097","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/2408.05097/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":"2026-07-05T08:53:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0DJsOK7FC96QIHLtKEYr/yljnda7xihP6rVwIwJrCpKAPc+G6RLg3Rddq/FD8ouYmOFpgwBGIsuwmHKFj7KtAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:26:40.623611Z"},"content_sha256":"d129802306ee95cb7a4c6b45df8960a15e5b2bcc3b9a1e5d49236ddc810c1716","schema_version":"1.0","event_id":"sha256:d129802306ee95cb7a4c6b45df8960a15e5b2bcc3b9a1e5d49236ddc810c1716"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WMQGN6VNBIYBOGV4F7QIVFJZNA/bundle.json","state_url":"https://pith.science/pith/WMQGN6VNBIYBOGV4F7QIVFJZNA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WMQGN6VNBIYBOGV4F7QIVFJZNA/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":"2026-07-07T12:26:40Z","links":{"resolver":"https://pith.science/pith/WMQGN6VNBIYBOGV4F7QIVFJZNA","bundle":"https://pith.science/pith/WMQGN6VNBIYBOGV4F7QIVFJZNA/bundle.json","state":"https://pith.science/pith/WMQGN6VNBIYBOGV4F7QIVFJZNA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WMQGN6VNBIYBOGV4F7QIVFJZNA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WMQGN6VNBIYBOGV4F7QIVFJZNA","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":"4f123ed5359cd345a09740862a0fa47a0beb32f40cb452c2929a2426fd874d6c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T14:39:15Z","title_canon_sha256":"572f372858bc9883d3ba54e38b67062a0d188778e6ccd1afdec3455dfcbd53f2"},"schema_version":"1.0","source":{"id":"2408.05097","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.05097","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"arxiv_version","alias_value":"2408.05097v1","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.05097","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_12","alias_value":"WMQGN6VNBIYB","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_16","alias_value":"WMQGN6VNBIYBOGV4","created_at":"2026-07-05T08:53:56Z"},{"alias_kind":"pith_short_8","alias_value":"WMQGN6VN","created_at":"2026-07-05T08:53:56Z"}],"graph_snapshots":[{"event_id":"sha256:d129802306ee95cb7a4c6b45df8960a15e5b2bcc3b9a1e5d49236ddc810c1716","target":"graph","created_at":"2026-07-05T08:53:56Z","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/2408.05097/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Hyperbolic embeddings have demonstrated their effectiveness in capturing measures of uncertainty and hierarchical relationships across various deep-learning tasks, including image segmentation and active learning. However, their application in modern vision-language models (VLMs) has been limited. A notable exception is MERU, which leverages the hierarchical properties of hyperbolic space in the CLIP ViT-large model, consisting of hundreds of millions parameters. In our work, we address the challenges of scaling multi-modal hyperbolic models by orders of magnitude in terms of parameters (billi","authors_text":"Fabio Galasso, Konstantinos Kallidromitis, Luca Franco, Paolo Mandica, Suzanne Petryk","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T14:39:15Z","title":"Hyperbolic Learning with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.05097","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:bda79c5c7c3f8c450fac5e988a48a27856f6c9e83d9dc11cbb5afab7571d264a","target":"record","created_at":"2026-07-05T08:53:56Z","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":"4f123ed5359cd345a09740862a0fa47a0beb32f40cb452c2929a2426fd874d6c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-08-09T14:39:15Z","title_canon_sha256":"572f372858bc9883d3ba54e38b67062a0d188778e6ccd1afdec3455dfcbd53f2"},"schema_version":"1.0","source":{"id":"2408.05097","kind":"arxiv","version":1}},"canonical_sha256":"b32066faad0a30171abc2fe08a953968180947a4d449d7cf581f33bb3a38b556","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b32066faad0a30171abc2fe08a953968180947a4d449d7cf581f33bb3a38b556","first_computed_at":"2026-07-05T08:53:56.715250Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:53:56.715250Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2hxn4lC+UFqBCIeamVWTkIy3uVXMAh4hgobVUdsPfRsP44Dnf/yCoJ1ZBocQrfZKtjfB2TAUqEZlVkaZmDF2CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:53:56.715624Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.05097","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bda79c5c7c3f8c450fac5e988a48a27856f6c9e83d9dc11cbb5afab7571d264a","sha256:d129802306ee95cb7a4c6b45df8960a15e5b2bcc3b9a1e5d49236ddc810c1716"],"state_sha256":"5f49e3011847f936ed72dfe3a35a0f8f4bc31c908ba80646a91dc10d4c6224f6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yQAHNXMkiZFvSmnCw4RcKApL5Iuz9toTA69GOYgCfLhmS9fCc/LBwACzk8mqeAhQE9BgD2xvw3OFpLETTAJ4Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:26:40.625545Z","bundle_sha256":"b800dc78d3e1bfc39a6a5865e9fea170688ffeb54a3fbf05dc386f6b75217093"}}