{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XPGZ2JNKJNNFIZRIIEZKDKXTW4","short_pith_number":"pith:XPGZ2JNK","canonical_record":{"source":{"id":"2405.17376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:32:37Z","cross_cats_sorted":[],"title_canon_sha256":"9194a2c511c5c9a2426f310012d6f63d825e92739983501565953f5a48e0b92c","abstract_canon_sha256":"a7e9b40fc850aac005b24803b866de06b7f571b20e96075ceb30506a9b0a03e8"},"schema_version":"1.0"},"canonical_sha256":"bbcd9d25aa4b5a5466284132a1aaf3b73f523b0e6f26e2d22a3b02c6cb56959f","source":{"kind":"arxiv","id":"2405.17376","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17376","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17376v1","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17376","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"XPGZ2JNKJNNF","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"XPGZ2JNKJNNFIZRI","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"XPGZ2JNK","created_at":"2026-07-05T08:23:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XPGZ2JNKJNNFIZRIIEZKDKXTW4","target":"record","payload":{"canonical_record":{"source":{"id":"2405.17376","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:32:37Z","cross_cats_sorted":[],"title_canon_sha256":"9194a2c511c5c9a2426f310012d6f63d825e92739983501565953f5a48e0b92c","abstract_canon_sha256":"a7e9b40fc850aac005b24803b866de06b7f571b20e96075ceb30506a9b0a03e8"},"schema_version":"1.0"},"canonical_sha256":"bbcd9d25aa4b5a5466284132a1aaf3b73f523b0e6f26e2d22a3b02c6cb56959f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:43.728552Z","signature_b64":"MfokrnVLO3wKFHgEfa2F9KTC77L0lJzhMXKCjdh0GhjwuehdnZInGKR/vlxegeqHAaqaMBPCaCsiEMDgORXbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbcd9d25aa4b5a5466284132a1aaf3b73f523b0e6f26e2d22a3b02c6cb56959f","last_reissued_at":"2026-07-05T08:23:43.728085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:43.728085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.17376","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":"2026-07-05T08:23:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aHzSOdlnNGOrPjnOjOQvbIr+SwqP6xPRl9GCzl/Duj1DaQCqYk9n8q40I60sdDrDkjAk0hFcNunoykkiVi0tBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:48:28.692276Z"},"content_sha256":"08957bd047fa8ed068402127129cb9aa215bb3b81ec591bb5a209980468a2423","schema_version":"1.0","event_id":"sha256:08957bd047fa8ed068402127129cb9aa215bb3b81ec591bb5a209980468a2423"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XPGZ2JNKJNNFIZRIIEZKDKXTW4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alessio Brutti, Daniele Falavigna, Mohamed Nabih Ali","submitted_at":"2024-05-27T17:32:37Z","abstract_excerpt":"Automatic speech recognition models require large amounts of speech recordings for training. However, the collection of such data often is cumbersome and leads to privacy concerns. Federated learning has been widely used as an effective decentralized technique that collaboratively learns a shared prediction model while keeping the data local on different clients. Unfortunately, client devices often feature limited computation and communication resources leading to practical difficulties for large models. In addition, the heterogeneity that characterizes edge devices makes it sub-optimal to gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17376","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/2405.17376/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":"2026-07-05T08:23:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qbHvI8OOI+9QxuOuyYkyzPuuY4/M2QXi7IpOoDsD+x0CvdPyRC/4vikmpHT5GBs+4iQFL0d4A5Ne7zA2EschCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:48:28.692834Z"},"content_sha256":"6e9ffa5b86de7452f630dc8233098d4e26f2c7d3d554d9ba8d17ed16f83c4c2d","schema_version":"1.0","event_id":"sha256:6e9ffa5b86de7452f630dc8233098d4e26f2c7d3d554d9ba8d17ed16f83c4c2d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XPGZ2JNKJNNFIZRIIEZKDKXTW4/bundle.json","state_url":"https://pith.science/pith/XPGZ2JNKJNNFIZRIIEZKDKXTW4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XPGZ2JNKJNNFIZRIIEZKDKXTW4/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":"2026-08-11T05:48:28Z","links":{"resolver":"https://pith.science/pith/XPGZ2JNKJNNFIZRIIEZKDKXTW4","bundle":"https://pith.science/pith/XPGZ2JNKJNNFIZRIIEZKDKXTW4/bundle.json","state":"https://pith.science/pith/XPGZ2JNKJNNFIZRIIEZKDKXTW4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XPGZ2JNKJNNFIZRIIEZKDKXTW4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XPGZ2JNKJNNFIZRIIEZKDKXTW4","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":"a7e9b40fc850aac005b24803b866de06b7f571b20e96075ceb30506a9b0a03e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:32:37Z","title_canon_sha256":"9194a2c511c5c9a2426f310012d6f63d825e92739983501565953f5a48e0b92c"},"schema_version":"1.0","source":{"id":"2405.17376","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.17376","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"arxiv_version","alias_value":"2405.17376v1","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17376","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"pith_short_12","alias_value":"XPGZ2JNKJNNF","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"pith_short_16","alias_value":"XPGZ2JNKJNNFIZRI","created_at":"2026-07-05T08:23:43Z"},{"alias_kind":"pith_short_8","alias_value":"XPGZ2JNK","created_at":"2026-07-05T08:23:43Z"}],"graph_snapshots":[{"event_id":"sha256:6e9ffa5b86de7452f630dc8233098d4e26f2c7d3d554d9ba8d17ed16f83c4c2d","target":"graph","created_at":"2026-07-05T08:23:43Z","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/2405.17376/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Automatic speech recognition models require large amounts of speech recordings for training. However, the collection of such data often is cumbersome and leads to privacy concerns. Federated learning has been widely used as an effective decentralized technique that collaboratively learns a shared prediction model while keeping the data local on different clients. Unfortunately, client devices often feature limited computation and communication resources leading to practical difficulties for large models. In addition, the heterogeneity that characterizes edge devices makes it sub-optimal to gen","authors_text":"Alessio Brutti, Daniele Falavigna, Mohamed Nabih Ali","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:32:37Z","title":"Federating Dynamic Models using Early-Exit Architectures for Automatic Speech Recognition on Heterogeneous Clients"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17376","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":"sha256:08957bd047fa8ed068402127129cb9aa215bb3b81ec591bb5a209980468a2423","target":"record","created_at":"2026-07-05T08:23:43Z","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":"a7e9b40fc850aac005b24803b866de06b7f571b20e96075ceb30506a9b0a03e8","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-27T17:32:37Z","title_canon_sha256":"9194a2c511c5c9a2426f310012d6f63d825e92739983501565953f5a48e0b92c"},"schema_version":"1.0","source":{"id":"2405.17376","kind":"arxiv","version":1}},"canonical_sha256":"bbcd9d25aa4b5a5466284132a1aaf3b73f523b0e6f26e2d22a3b02c6cb56959f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbcd9d25aa4b5a5466284132a1aaf3b73f523b0e6f26e2d22a3b02c6cb56959f","first_computed_at":"2026-07-05T08:23:43.728085Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:43.728085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MfokrnVLO3wKFHgEfa2F9KTC77L0lJzhMXKCjdh0GhjwuehdnZInGKR/vlxegeqHAaqaMBPCaCsiEMDgORXbDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:43.728552Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.17376","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08957bd047fa8ed068402127129cb9aa215bb3b81ec591bb5a209980468a2423","sha256:6e9ffa5b86de7452f630dc8233098d4e26f2c7d3d554d9ba8d17ed16f83c4c2d"],"state_sha256":"5b9eb908eae4ecd2441791c306c5c5a892fb32483f1164330f1684fcf0a42557"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"irP4pMRftCWUUulN82WPykBZRSb9+R7Nm5BjhsDbrQPje58NmFtfje5Ndrua0P/8CenzKQw+KFkNz2DJUGPSBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:48:28.697681Z","bundle_sha256":"e704736dd7eb245072335089380eedb66b71d6070e84fcd7bc0f62b5e0904f6c"}}