{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YVMTA52OJKYEDHKG7LS47RAE34","short_pith_number":"pith:YVMTA52O","canonical_record":{"source":{"id":"2406.14183","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T10:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"9e16d2db9f48c2ca6b19a26e82e0c3fcc8cad955b79ccc7886415de52b9b6109","abstract_canon_sha256":"4e75b958501e37a5953384b1340f2570a273d85e45bf779878a3e1fbd9bfe64f"},"schema_version":"1.0"},"canonical_sha256":"c55930774e4ab0419d46fae5cfc404df296bb999a4e1a5f26a0f695c9c664588","source":{"kind":"arxiv","id":"2406.14183","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14183","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14183v4","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14183","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"pith_short_12","alias_value":"YVMTA52OJKYE","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"pith_short_16","alias_value":"YVMTA52OJKYEDHKG","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"pith_short_8","alias_value":"YVMTA52O","created_at":"2026-07-05T11:36:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YVMTA52OJKYEDHKG7LS47RAE34","target":"record","payload":{"canonical_record":{"source":{"id":"2406.14183","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T10:43:28Z","cross_cats_sorted":[],"title_canon_sha256":"9e16d2db9f48c2ca6b19a26e82e0c3fcc8cad955b79ccc7886415de52b9b6109","abstract_canon_sha256":"4e75b958501e37a5953384b1340f2570a273d85e45bf779878a3e1fbd9bfe64f"},"schema_version":"1.0"},"canonical_sha256":"c55930774e4ab0419d46fae5cfc404df296bb999a4e1a5f26a0f695c9c664588","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:20.784280Z","signature_b64":"M+BfGSlTS/H+gcrbN+iG9Lmn//y5gbHb+c04YTgJK3TuOKAdpXEv1LR/zwqx1rAVfD3WCOCNc5CegXuYReooAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c55930774e4ab0419d46fae5cfc404df296bb999a4e1a5f26a0f695c9c664588","last_reissued_at":"2026-07-05T11:36:20.783719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:20.783719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.14183","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:36:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z917goS/UHzwvor3BjCq4pohqoDltf4P8g87pa6v1BOXfKadNqZ8xKcevE59TKTTo/FWuhbuaBd3UKhpVtr2Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:47:55.868849Z"},"content_sha256":"df09ddb0aefc430971b9eac944fda0615d9a8c2a38703933ed0dcfeee2d1854d","schema_version":"1.0","event_id":"sha256:df09ddb0aefc430971b9eac944fda0615d9a8c2a38703933ed0dcfeee2d1854d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YVMTA52OJKYEDHKG7LS47RAE34","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Latent Functional Maps: a spectral framework for representation alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Emanuele Rodol\\`a, Francesco Locatello, Marco Fumero, Marco Pegoraro, Valentino Maiorca","submitted_at":"2024-06-20T10:43:28Z","abstract_excerpt":"Neural models learn data representations that lie on low-dimensional manifolds, yet modeling the relation between these representational spaces is an ongoing challenge. By integrating spectral geometry principles into neural modeling, we show that this problem can be better addressed in the functional domain, mitigating complexity, while enhancing interpretability and performances on downstream tasks. To this end, we introduce a multi-purpose framework to the representation learning community, which allows to: (i) compare different spaces in an interpretable way and measure their intrinsic sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14183","kind":"arxiv","version":4},"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/2406.14183/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":"2026-07-05T11:36:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZJH2nVZS18OLxd3j2lVT0tkH03PqEAzCFdbP6RdbGdX/XtveCpr4CPOumupQvdyzr3x/Pls5bEFrcZ5qovs5Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:47:55.869354Z"},"content_sha256":"2cff7b8b0de8417ebf3357d9705ce6e181a2eb82dc51cba29f76a7cf3099e730","schema_version":"1.0","event_id":"sha256:2cff7b8b0de8417ebf3357d9705ce6e181a2eb82dc51cba29f76a7cf3099e730"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YVMTA52OJKYEDHKG7LS47RAE34/bundle.json","state_url":"https://pith.science/pith/YVMTA52OJKYEDHKG7LS47RAE34/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YVMTA52OJKYEDHKG7LS47RAE34/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":"2026-08-06T14:47:55Z","links":{"resolver":"https://pith.science/pith/YVMTA52OJKYEDHKG7LS47RAE34","bundle":"https://pith.science/pith/YVMTA52OJKYEDHKG7LS47RAE34/bundle.json","state":"https://pith.science/pith/YVMTA52OJKYEDHKG7LS47RAE34/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YVMTA52OJKYEDHKG7LS47RAE34/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YVMTA52OJKYEDHKG7LS47RAE34","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":"4e75b958501e37a5953384b1340f2570a273d85e45bf779878a3e1fbd9bfe64f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T10:43:28Z","title_canon_sha256":"9e16d2db9f48c2ca6b19a26e82e0c3fcc8cad955b79ccc7886415de52b9b6109"},"schema_version":"1.0","source":{"id":"2406.14183","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.14183","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"arxiv_version","alias_value":"2406.14183v4","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.14183","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"pith_short_12","alias_value":"YVMTA52OJKYE","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"pith_short_16","alias_value":"YVMTA52OJKYEDHKG","created_at":"2026-07-05T11:36:20Z"},{"alias_kind":"pith_short_8","alias_value":"YVMTA52O","created_at":"2026-07-05T11:36:20Z"}],"graph_snapshots":[{"event_id":"sha256:2cff7b8b0de8417ebf3357d9705ce6e181a2eb82dc51cba29f76a7cf3099e730","target":"graph","created_at":"2026-07-05T11:36:20Z","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/2406.14183/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Neural models learn data representations that lie on low-dimensional manifolds, yet modeling the relation between these representational spaces is an ongoing challenge. By integrating spectral geometry principles into neural modeling, we show that this problem can be better addressed in the functional domain, mitigating complexity, while enhancing interpretability and performances on downstream tasks. To this end, we introduce a multi-purpose framework to the representation learning community, which allows to: (i) compare different spaces in an interpretable way and measure their intrinsic sim","authors_text":"Emanuele Rodol\\`a, Francesco Locatello, Marco Fumero, Marco Pegoraro, Valentino Maiorca","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T10:43:28Z","title":"Latent Functional Maps: a spectral framework for representation alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.14183","kind":"arxiv","version":4},"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:df09ddb0aefc430971b9eac944fda0615d9a8c2a38703933ed0dcfeee2d1854d","target":"record","created_at":"2026-07-05T11:36:20Z","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":"4e75b958501e37a5953384b1340f2570a273d85e45bf779878a3e1fbd9bfe64f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-20T10:43:28Z","title_canon_sha256":"9e16d2db9f48c2ca6b19a26e82e0c3fcc8cad955b79ccc7886415de52b9b6109"},"schema_version":"1.0","source":{"id":"2406.14183","kind":"arxiv","version":4}},"canonical_sha256":"c55930774e4ab0419d46fae5cfc404df296bb999a4e1a5f26a0f695c9c664588","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c55930774e4ab0419d46fae5cfc404df296bb999a4e1a5f26a0f695c9c664588","first_computed_at":"2026-07-05T11:36:20.783719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:36:20.783719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M+BfGSlTS/H+gcrbN+iG9Lmn//y5gbHb+c04YTgJK3TuOKAdpXEv1LR/zwqx1rAVfD3WCOCNc5CegXuYReooAA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:36:20.784280Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.14183","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:df09ddb0aefc430971b9eac944fda0615d9a8c2a38703933ed0dcfeee2d1854d","sha256:2cff7b8b0de8417ebf3357d9705ce6e181a2eb82dc51cba29f76a7cf3099e730"],"state_sha256":"5500f06716dcafe301a59ebd509253d1dabcc1c8ab60d6c12e8b27e653fc4507"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8YvLwFXaEO5ntnwNWmLJJUprMg3I5xuRFOzjXq3WixKmikCf5YMIv3C1VNiWl8KYSS3nmqhOvrZC6qWVkLPwCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:47:55.872835Z","bundle_sha256":"24f908b1d5f2d8d5b9d7a55d93bf3d29e1be68236674738a06efa634fad3b102"}}