{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YDRKKSY5MMYPDB6HIHYEONYG2I","short_pith_number":"pith:YDRKKSY5","canonical_record":{"source":{"id":"2412.11959","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T16:41:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4975ecb61a7cb1f90d7364726ea79f4dd54d7e6eb5c2c8b9afa237babdf28cf9","abstract_canon_sha256":"03bec2b00c8f7f5a0edb17f391c74e00b0219d6ef83b1adbe578814e21c897bd"},"schema_version":"1.0"},"canonical_sha256":"c0e2a54b1d6330f187c741f0473706d21d75c16e96244b6f4042c0661a355e85","source":{"kind":"arxiv","id":"2412.11959","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11959","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11959v2","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11959","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"YDRKKSY5MMYP","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"YDRKKSY5MMYPDB6H","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"YDRKKSY5","created_at":"2026-07-05T10:13:06Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YDRKKSY5MMYPDB6HIHYEONYG2I","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11959","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T16:41:51Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"4975ecb61a7cb1f90d7364726ea79f4dd54d7e6eb5c2c8b9afa237babdf28cf9","abstract_canon_sha256":"03bec2b00c8f7f5a0edb17f391c74e00b0219d6ef83b1adbe578814e21c897bd"},"schema_version":"1.0"},"canonical_sha256":"c0e2a54b1d6330f187c741f0473706d21d75c16e96244b6f4042c0661a355e85","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:06.605387Z","signature_b64":"HpEpI536j4hRzF0jk9bPlz+qezS3urkXJOJh7qWmJmQTP9jNvlrNkOeT3cC6L2ORE3aTi9RkePIQTVrKrxPNCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0e2a54b1d6330f187c741f0473706d21d75c16e96244b6f4042c0661a355e85","last_reissued_at":"2026-07-05T10:13:06.604839Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:06.604839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11959","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"No/eqcwaLE3tHUIAkDFpf8Ov7OX0okFpfQmaQRv9l99S7jpemrCkG0ljmyYAzTttzcERQ5rl25BDJaeh4hiQCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:42:24.774355Z"},"content_sha256":"09c89231ea98da69147a17b896912815f3039bb0dc72b29a595f8a33932589df","schema_version":"1.0","event_id":"sha256:09c89231ea98da69147a17b896912815f3039bb0dc72b29a595f8a33932589df"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YDRKKSY5MMYPDB6HIHYEONYG2I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gramian Multimodal Representation Learning and Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Danilo Comminiello, Eleonora Grassucci, Giordano Cicchetti, Luigi Sigillo","submitted_at":"2024-12-16T16:41:51Z","abstract_excerpt":"Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of modalities via contrastive learning, their solutions are unsuitable when scaling to multiple modalities. These models typically align each modality to a designated anchor without ensuring the alignment of all modalities with each other, leading to suboptimal performance in tasks requiring a joint understanding of multiple modalities. In this paper, we structurally r"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11959","kind":"arxiv","version":2},"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/2412.11959/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":"2026-07-05T10:13:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GZAsHlrqBkOjnw/HPKbpCua/ndmq/LsEwsWMzNviMTkKJQXvy0LiJorr/VKl9GUgetqwB8CvICj7/fBNXq5vDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T21:42:24.774744Z"},"content_sha256":"bcd214370d1265b72174a23204bc69c1c064845064edc263a8e84c7e8c387b9d","schema_version":"1.0","event_id":"sha256:bcd214370d1265b72174a23204bc69c1c064845064edc263a8e84c7e8c387b9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YDRKKSY5MMYPDB6HIHYEONYG2I/bundle.json","state_url":"https://pith.science/pith/YDRKKSY5MMYPDB6HIHYEONYG2I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YDRKKSY5MMYPDB6HIHYEONYG2I/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":"2026-08-03T21:42:24Z","links":{"resolver":"https://pith.science/pith/YDRKKSY5MMYPDB6HIHYEONYG2I","bundle":"https://pith.science/pith/YDRKKSY5MMYPDB6HIHYEONYG2I/bundle.json","state":"https://pith.science/pith/YDRKKSY5MMYPDB6HIHYEONYG2I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YDRKKSY5MMYPDB6HIHYEONYG2I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YDRKKSY5MMYPDB6HIHYEONYG2I","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":"03bec2b00c8f7f5a0edb17f391c74e00b0219d6ef83b1adbe578814e21c897bd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T16:41:51Z","title_canon_sha256":"4975ecb61a7cb1f90d7364726ea79f4dd54d7e6eb5c2c8b9afa237babdf28cf9"},"schema_version":"1.0","source":{"id":"2412.11959","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11959","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11959v2","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11959","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_12","alias_value":"YDRKKSY5MMYP","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_16","alias_value":"YDRKKSY5MMYPDB6H","created_at":"2026-07-05T10:13:06Z"},{"alias_kind":"pith_short_8","alias_value":"YDRKKSY5","created_at":"2026-07-05T10:13:06Z"}],"graph_snapshots":[{"event_id":"sha256:bcd214370d1265b72174a23204bc69c1c064845064edc263a8e84c7e8c387b9d","target":"graph","created_at":"2026-07-05T10:13:06Z","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/2412.11959/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Human perception integrates multiple modalities, such as vision, hearing, and language, into a unified understanding of the surrounding reality. While recent multimodal models have achieved significant progress by aligning pairs of modalities via contrastive learning, their solutions are unsuitable when scaling to multiple modalities. These models typically align each modality to a designated anchor without ensuring the alignment of all modalities with each other, leading to suboptimal performance in tasks requiring a joint understanding of multiple modalities. In this paper, we structurally r","authors_text":"Danilo Comminiello, Eleonora Grassucci, Giordano Cicchetti, Luigi Sigillo","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T16:41:51Z","title":"Gramian Multimodal Representation Learning and Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11959","kind":"arxiv","version":2},"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":"sha256:09c89231ea98da69147a17b896912815f3039bb0dc72b29a595f8a33932589df","target":"record","created_at":"2026-07-05T10:13:06Z","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":"03bec2b00c8f7f5a0edb17f391c74e00b0219d6ef83b1adbe578814e21c897bd","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-12-16T16:41:51Z","title_canon_sha256":"4975ecb61a7cb1f90d7364726ea79f4dd54d7e6eb5c2c8b9afa237babdf28cf9"},"schema_version":"1.0","source":{"id":"2412.11959","kind":"arxiv","version":2}},"canonical_sha256":"c0e2a54b1d6330f187c741f0473706d21d75c16e96244b6f4042c0661a355e85","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c0e2a54b1d6330f187c741f0473706d21d75c16e96244b6f4042c0661a355e85","first_computed_at":"2026-07-05T10:13:06.604839Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:06.604839Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"HpEpI536j4hRzF0jk9bPlz+qezS3urkXJOJh7qWmJmQTP9jNvlrNkOeT3cC6L2ORE3aTi9RkePIQTVrKrxPNCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:06.605387Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11959","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:09c89231ea98da69147a17b896912815f3039bb0dc72b29a595f8a33932589df","sha256:bcd214370d1265b72174a23204bc69c1c064845064edc263a8e84c7e8c387b9d"],"state_sha256":"525df3f72ba3fa5d1fa9794b9f5d3b7729dc33c88c52c6985d964d5604ae5c70"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+ADl6icchfs9h3owZZOLfCDQ+7IWq82LwG9F4smp4xPABuc7W12BltDJIshbZdACafH+U6GSJKQJ6LdDsddoBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T21:42:24.777456Z","bundle_sha256":"6a126219546eb212274d8734253303a027b988b0f1b4feb202b584c35a446874"}}