{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:7E2NW6ZBNSOU2XL7N2GUWA47IE","short_pith_number":"pith:7E2NW6ZB","canonical_record":{"source":{"id":"2605.16251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-15T17:56:04Z","cross_cats_sorted":[],"title_canon_sha256":"e7f0115ee427a11cb6c3b9cff7e4512ab2cf16ec333f5f35dee343190f52e0b4","abstract_canon_sha256":"29a97fc6f62c517e207476a1cf628905f2f66003c80009facfd2f322398b2323"},"schema_version":"1.0"},"canonical_sha256":"f934db7b216c9d4d5d7f6e8d4b039f412fda21b7afa8469db495be054df8b88b","source":{"kind":"arxiv","id":"2605.16251","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16251","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16251v1","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16251","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"pith_short_12","alias_value":"7E2NW6ZBNSOU","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"pith_short_16","alias_value":"7E2NW6ZBNSOU2XL7","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"pith_short_8","alias_value":"7E2NW6ZB","created_at":"2026-05-20T00:02:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:7E2NW6ZBNSOU2XL7N2GUWA47IE","target":"record","payload":{"canonical_record":{"source":{"id":"2605.16251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-15T17:56:04Z","cross_cats_sorted":[],"title_canon_sha256":"e7f0115ee427a11cb6c3b9cff7e4512ab2cf16ec333f5f35dee343190f52e0b4","abstract_canon_sha256":"29a97fc6f62c517e207476a1cf628905f2f66003c80009facfd2f322398b2323"},"schema_version":"1.0"},"canonical_sha256":"f934db7b216c9d4d5d7f6e8d4b039f412fda21b7afa8469db495be054df8b88b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:00.158579Z","signature_b64":"5E0MA1a75dz6Niw8b/cf507o9VOkbqMyGvV4Lonl6IpGOXuf0ZSbmVr5LRDneyH0hMo1g2/H/hg22ED68mktDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f934db7b216c9d4d5d7f6e8d4b039f412fda21b7afa8469db495be054df8b88b","last_reissued_at":"2026-05-20T00:02:00.157755Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:00.157755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.16251","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":"2026-05-20T00:02:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+SsJ2ZCE01Q1OjvqfEPpyTKfxDkByGTm6XV3we0ibUkD+oteL43TyYyXGuG6qmez3fbDbt9wWjFrBEXR+b/3Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:24:11.291713Z"},"content_sha256":"124296f7cd5aa843ca2e77e5ef06320807ac1b5ec9e24b6f2a88087e82a6aa49","schema_version":"1.0","event_id":"sha256:124296f7cd5aa843ca2e77e5ef06320807ac1b5ec9e24b6f2a88087e82a6aa49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:7E2NW6ZBNSOU2XL7N2GUWA47IE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Real-time Speech Restoration using Data Prediction Mean Flows","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Data Prediction Mean Flows let generative speech restoration run in real time with 120 times less compute than prior methods.","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Sebastian Braun","submitted_at":"2026-05-15T17:56:04Z","abstract_excerpt":"Generative models are capable to address difficult problems with non-unique solutions like bandwidth extension and gap filling, removing highly non-linear artifacts from codecs, clipping and distortion, as opposed to removing linear additive components like noise and reverb. While large offline processing models have shown impressive results, these tasks have not been solved with real-time capable models with low latency and compute. We propose a few-step flow matching model using Data Prediction Mean Flows in combination with suitable novel low-latency architecture to make flow matching model"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Compared to state-of-the-art, our proposed mean flow model uses 120x less compute and introduces no algorithmic latency other than the STFT, while achieving similar audio quality.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the novel low-latency architecture combined with few-step Data Prediction Mean Flows can preserve audio quality comparable to large offline generative models under strict real-time constraints.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A Data Prediction Mean Flow model enables real-time speech restoration with 120x lower compute and no algorithmic latency beyond the STFT while matching state-of-the-art offline quality.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Data Prediction Mean Flows let generative speech restoration run in real time with 120 times less compute than prior methods.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"5a483e8737b117e3a9ee2d4da49cccddb29c3d4d6e66653e2439d85e4d1dab6b"},"source":{"id":"2605.16251","kind":"arxiv","version":1},"verdict":{"id":"8974355d-f14d-465e-97be-470c6ebba1ff","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T18:18:42.516191Z","strongest_claim":"Compared to state-of-the-art, our proposed mean flow model uses 120x less compute and introduces no algorithmic latency other than the STFT, while achieving similar audio quality.","one_line_summary":"A Data Prediction Mean Flow model enables real-time speech restoration with 120x lower compute and no algorithmic latency beyond the STFT while matching state-of-the-art offline quality.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the novel low-latency architecture combined with few-step Data Prediction Mean Flows can preserve audio quality comparable to large offline generative models under strict real-time constraints.","pith_extraction_headline":"Data Prediction Mean Flows let generative speech restoration run in real time with 120 times less compute than prior methods."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.16251/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:18.705929Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:30:47.050759Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"shingle_duplication","ran_at":"2026-05-19T17:49:42.175523Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T17:49:41.787578Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:23.083121Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T17:31:24.179582Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.597051Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"cited_work_retraction","ran_at":"2026-05-19T16:51:56.367540Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"b766fbfd92dcae957e1092a8c986714496a304b4dccf0e032a04229c28af477a"},"references":{"count":28,"sample":[{"doi":"","year":null,"title":"Speech restoration aims to address and fix all of those non-linear and de- structive degradations by using generative modeling","work_id":"6e96a4fd-2a14-4d3f-ac15-d38798597692","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Real-time Speech Restoration using Data Prediction Mean Flows","work_id":"c9a688c4-3780-4428-b22c-3a6056c0f2b7","ref_index":2,"cited_arxiv_id":"2605.16251","is_internal_anchor":true},{"doi":"","year":null,"title":"DA TA AND IMPLEMENTA TION 3.1. Training data We generate degraded and target speech pairs with on-the-fly aug- mentation with a similar pipeline as in [7] using studio-quality clean speech from EARS [","work_id":"f136aebd-d295-4d40-aa6c-975635133bf6","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Test set and metrics We use the Signal Improvement Challenge 2024 (SIG2024) [21] test set, 500 real-world recordings with typical degradations from de- vices and V oiP processing","work_id":"64659c5a-4930-42c7-8543-62268926ecb5","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"CONCLUSIONS This work paved the way to drastically reduce computational cost and latency for general speech restoration flow-matching models. We demonstrate a 120x gain at increased quality by adoptin","work_id":"fbc7cad4-5a1a-4801-9759-fc09e3496e2c","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":28,"snapshot_sha256":"9cc33a4caa00ad43a49c86754cbf53e198036e9e32fa45c201b83e24dc3641d3","internal_anchors":3},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4ad477fd9711c5e7fcc3fd68327ef39e72e6b5f7c96c165814e0582db3e65b91"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"8974355d-f14d-465e-97be-470c6ebba1ff"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-20T00:02:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LQ9YzX+MW4QbWe5yQNbIk8/OIQc8/D7UTr/I8RpY2KcMvsvStQu8UQseUq2BB1Xd8nbdgnpf0FO7dJsB4yA3Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T22:24:11.292920Z"},"content_sha256":"e5c3b476b9a5992b67621d22dbcc776bf23600fa4bf6fe6e9ee0e7a45501af18","schema_version":"1.0","event_id":"sha256:e5c3b476b9a5992b67621d22dbcc776bf23600fa4bf6fe6e9ee0e7a45501af18"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7E2NW6ZBNSOU2XL7N2GUWA47IE/bundle.json","state_url":"https://pith.science/pith/7E2NW6ZBNSOU2XL7N2GUWA47IE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7E2NW6ZBNSOU2XL7N2GUWA47IE/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":"2026-05-25T22:24:11Z","links":{"resolver":"https://pith.science/pith/7E2NW6ZBNSOU2XL7N2GUWA47IE","bundle":"https://pith.science/pith/7E2NW6ZBNSOU2XL7N2GUWA47IE/bundle.json","state":"https://pith.science/pith/7E2NW6ZBNSOU2XL7N2GUWA47IE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7E2NW6ZBNSOU2XL7N2GUWA47IE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:7E2NW6ZBNSOU2XL7N2GUWA47IE","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":"29a97fc6f62c517e207476a1cf628905f2f66003c80009facfd2f322398b2323","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-15T17:56:04Z","title_canon_sha256":"e7f0115ee427a11cb6c3b9cff7e4512ab2cf16ec333f5f35dee343190f52e0b4"},"schema_version":"1.0","source":{"id":"2605.16251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.16251","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"arxiv_version","alias_value":"2605.16251v1","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16251","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"pith_short_12","alias_value":"7E2NW6ZBNSOU","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"pith_short_16","alias_value":"7E2NW6ZBNSOU2XL7","created_at":"2026-05-20T00:02:00Z"},{"alias_kind":"pith_short_8","alias_value":"7E2NW6ZB","created_at":"2026-05-20T00:02:00Z"}],"graph_snapshots":[{"event_id":"sha256:e5c3b476b9a5992b67621d22dbcc776bf23600fa4bf6fe6e9ee0e7a45501af18","target":"graph","created_at":"2026-05-20T00:02:00Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Compared to state-of-the-art, our proposed mean flow model uses 120x less compute and introduces no algorithmic latency other than the STFT, while achieving similar audio quality."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the novel low-latency architecture combined with few-step Data Prediction Mean Flows can preserve audio quality comparable to large offline generative models under strict real-time constraints."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A Data Prediction Mean Flow model enables real-time speech restoration with 120x lower compute and no algorithmic latency beyond the STFT while matching state-of-the-art offline quality."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Data Prediction Mean Flows let generative speech restoration run in real time with 120 times less compute than prior methods."}],"snapshot_sha256":"5a483e8737b117e3a9ee2d4da49cccddb29c3d4d6e66653e2439d85e4d1dab6b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4ad477fd9711c5e7fcc3fd68327ef39e72e6b5f7c96c165814e0582db3e65b91"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-19T18:31:18.705929Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T18:30:47.050759Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"shingle_duplication","ran_at":"2026-05-19T17:49:42.175523Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"citation_quote_validity","ran_at":"2026-05-19T17:49:41.787578Z","status":"skipped","version":"0.1.0"},{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-19T17:33:23.083121Z","status":"skipped","version":"1.0.0"},{"findings_count":0,"name":"external_links","ran_at":"2026-05-19T17:31:24.179582Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"claim_evidence","ran_at":"2026-05-19T17:01:55.597051Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"cited_work_retraction","ran_at":"2026-05-19T16:51:56.367540Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.16251/integrity.json","findings":[],"snapshot_sha256":"b766fbfd92dcae957e1092a8c986714496a304b4dccf0e032a04229c28af477a","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative models are capable to address difficult problems with non-unique solutions like bandwidth extension and gap filling, removing highly non-linear artifacts from codecs, clipping and distortion, as opposed to removing linear additive components like noise and reverb. While large offline processing models have shown impressive results, these tasks have not been solved with real-time capable models with low latency and compute. We propose a few-step flow matching model using Data Prediction Mean Flows in combination with suitable novel low-latency architecture to make flow matching model","authors_text":"Sebastian Braun","cross_cats":[],"headline":"Data Prediction Mean Flows let generative speech restoration run in real time with 120 times less compute than prior methods.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-15T17:56:04Z","title":"Real-time Speech Restoration using Data Prediction Mean Flows"},"references":{"count":28,"internal_anchors":3,"resolved_work":28,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Speech restoration aims to address and fix all of those non-linear and de- structive degradations by using generative modeling","work_id":"6e96a4fd-2a14-4d3f-ac15-d38798597692","year":null},{"cited_arxiv_id":"2605.16251","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Real-time Speech Restoration using Data Prediction Mean Flows","work_id":"c9a688c4-3780-4428-b22c-3a6056c0f2b7","year":2026},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"DA TA AND IMPLEMENTA TION 3.1. Training data We generate degraded and target speech pairs with on-the-fly aug- mentation with a similar pipeline as in [7] using studio-quality clean speech from EARS [","work_id":"f136aebd-d295-4d40-aa6c-975635133bf6","year":null},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Test set and metrics We use the Signal Improvement Challenge 2024 (SIG2024) [21] test set, 500 real-world recordings with typical degradations from de- vices and V oiP processing","work_id":"64659c5a-4930-42c7-8543-62268926ecb5","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"CONCLUSIONS This work paved the way to drastically reduce computational cost and latency for general speech restoration flow-matching models. We demonstrate a 120x gain at increased quality by adoptin","work_id":"fbc7cad4-5a1a-4801-9759-fc09e3496e2c","year":null}],"snapshot_sha256":"9cc33a4caa00ad43a49c86754cbf53e198036e9e32fa45c201b83e24dc3641d3"},"source":{"id":"2605.16251","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-19T18:18:42.516191Z","id":"8974355d-f14d-465e-97be-470c6ebba1ff","model_set":{"reader":"grok-4.3"},"one_line_summary":"A Data Prediction Mean Flow model enables real-time speech restoration with 120x lower compute and no algorithmic latency beyond the STFT while matching state-of-the-art offline quality.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Data Prediction Mean Flows let generative speech restoration run in real time with 120 times less compute than prior methods.","strongest_claim":"Compared to state-of-the-art, our proposed mean flow model uses 120x less compute and introduces no algorithmic latency other than the STFT, while achieving similar audio quality.","weakest_assumption":"That the novel low-latency architecture combined with few-step Data Prediction Mean Flows can preserve audio quality comparable to large offline generative models under strict real-time constraints."}},"verdict_id":"8974355d-f14d-465e-97be-470c6ebba1ff"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:124296f7cd5aa843ca2e77e5ef06320807ac1b5ec9e24b6f2a88087e82a6aa49","target":"record","created_at":"2026-05-20T00:02:00Z","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":"29a97fc6f62c517e207476a1cf628905f2f66003c80009facfd2f322398b2323","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-05-15T17:56:04Z","title_canon_sha256":"e7f0115ee427a11cb6c3b9cff7e4512ab2cf16ec333f5f35dee343190f52e0b4"},"schema_version":"1.0","source":{"id":"2605.16251","kind":"arxiv","version":1}},"canonical_sha256":"f934db7b216c9d4d5d7f6e8d4b039f412fda21b7afa8469db495be054df8b88b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f934db7b216c9d4d5d7f6e8d4b039f412fda21b7afa8469db495be054df8b88b","first_computed_at":"2026-05-20T00:02:00.157755Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-20T00:02:00.157755Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5E0MA1a75dz6Niw8b/cf507o9VOkbqMyGvV4Lonl6IpGOXuf0ZSbmVr5LRDneyH0hMo1g2/H/hg22ED68mktDg==","signature_status":"signed_v1","signed_at":"2026-05-20T00:02:00.158579Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.16251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:124296f7cd5aa843ca2e77e5ef06320807ac1b5ec9e24b6f2a88087e82a6aa49","sha256:e5c3b476b9a5992b67621d22dbcc776bf23600fa4bf6fe6e9ee0e7a45501af18"],"state_sha256":"71518cc0985bc1d8333b020c99b1d7b5cc8e1c63e492186798b65b1a0dbff57e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PfMp4lcYN0BI0VN/1RPshtsxAV1q6SId5NxC4UpeyzlqaZHMDtKUMfiXubefxTDbqgsjgFS0lGmpg1O8Pv/TCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T22:24:11.297687Z","bundle_sha256":"9bcb185b5b67452e43c198c6dcef58975e228c464cafbd6daee0cd0f4fb1afaf"}}