{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:2PBSSA5GNGBNJDMLDO6I5QK3EB","short_pith_number":"pith:2PBSSA5G","canonical_record":{"source":{"id":"2412.11272","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-15T18:27:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"90408a7ac99963034e1298049856bf259c70a13758032910cc0d786b810c012e","abstract_canon_sha256":"3707c7011d414b23441b44fae3d795560fbb0deb7a33484b4cd9139fc36a5f79"},"schema_version":"1.0"},"canonical_sha256":"d3c32903a66982d48d8b1bbc8ec15b2055b097454ac225ea47fe38212ed9aad0","source":{"kind":"arxiv","id":"2412.11272","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11272","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11272v2","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11272","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"2PBSSA5GNGBN","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"2PBSSA5GNGBNJDML","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"2PBSSA5G","created_at":"2026-07-05T10:52:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:2PBSSA5GNGBNJDMLDO6I5QK3EB","target":"record","payload":{"canonical_record":{"source":{"id":"2412.11272","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-15T18:27:37Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"90408a7ac99963034e1298049856bf259c70a13758032910cc0d786b810c012e","abstract_canon_sha256":"3707c7011d414b23441b44fae3d795560fbb0deb7a33484b4cd9139fc36a5f79"},"schema_version":"1.0"},"canonical_sha256":"d3c32903a66982d48d8b1bbc8ec15b2055b097454ac225ea47fe38212ed9aad0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:17.083680Z","signature_b64":"68ANqbpa4/KwEcYsy6/lUVgmlLza+SVNAvMesdFT/tq16EaRW7i6trbph/WqUgCO1BX6dJyyYMlDHt3vwR9DAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d3c32903a66982d48d8b1bbc8ec15b2055b097454ac225ea47fe38212ed9aad0","last_reissued_at":"2026-07-05T10:52:17.083182Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:17.083182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.11272","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":"2026-07-05T10:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z0TBcUhEfOOl77qDY4i0w/YuwdAq+9mTtAFnZ5Mf1zAZBMAC1sJ1PhLP0uq5+lVLaXVwTaK9X041hxqd4T6xDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:41:09.466334Z"},"content_sha256":"ee16db1bfba70f5fc669d57351f06deb4b6bba0f40aa8db1b9be7beb969c34d3","schema_version":"1.0","event_id":"sha256:ee16db1bfba70f5fc669d57351f06deb4b6bba0f40aa8db1b9be7beb969c34d3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:2PBSSA5GNGBNJDMLDO6I5QK3EB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"WhisperFlow: speech foundation models in real time","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Felix Xiaozhu Lin, Rongxiang Wang, Zhiming Xu","submitted_at":"2024-12-15T18:27:37Z","abstract_excerpt":"Speech foundation models, such as OpenAI's Whisper, become the state of the art in speech understanding due to their strong accuracy and generalizability. Yet, their applications are mostly limited to processing pre-recorded speech, whereas processing of streaming speech, in particular doing it efficiently, remains rudimentary. Behind this inefficiency are multiple fundamental reasons: (1) speech foundation models are trained to process long, fixed-length voice inputs (often 30 seconds); (2) encoding each voice input requires encoding as many as 1,500 tokens with tens of transformer layers; (3"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11272","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/2412.11272/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":"2026-07-05T10:52:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fEIugFzEuzIC08tfv3OeHysR/0u35io4uTSdL7fbKnX6FLFswBe4y+6kCa8dvDi4H5FlXqk/f29gi0LMETtqAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-14T06:41:09.466854Z"},"content_sha256":"2654c92b4f4749f95f885dedd0e4f393b577b0e903b1b24e64f26a085f6a0999","schema_version":"1.0","event_id":"sha256:2654c92b4f4749f95f885dedd0e4f393b577b0e903b1b24e64f26a085f6a0999"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2PBSSA5GNGBNJDMLDO6I5QK3EB/bundle.json","state_url":"https://pith.science/pith/2PBSSA5GNGBNJDMLDO6I5QK3EB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2PBSSA5GNGBNJDMLDO6I5QK3EB/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":"2026-08-14T06:41:09Z","links":{"resolver":"https://pith.science/pith/2PBSSA5GNGBNJDMLDO6I5QK3EB","bundle":"https://pith.science/pith/2PBSSA5GNGBNJDMLDO6I5QK3EB/bundle.json","state":"https://pith.science/pith/2PBSSA5GNGBNJDMLDO6I5QK3EB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2PBSSA5GNGBNJDMLDO6I5QK3EB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:2PBSSA5GNGBNJDMLDO6I5QK3EB","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":"3707c7011d414b23441b44fae3d795560fbb0deb7a33484b4cd9139fc36a5f79","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-15T18:27:37Z","title_canon_sha256":"90408a7ac99963034e1298049856bf259c70a13758032910cc0d786b810c012e"},"schema_version":"1.0","source":{"id":"2412.11272","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.11272","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"arxiv_version","alias_value":"2412.11272v2","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.11272","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_12","alias_value":"2PBSSA5GNGBN","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_16","alias_value":"2PBSSA5GNGBNJDML","created_at":"2026-07-05T10:52:17Z"},{"alias_kind":"pith_short_8","alias_value":"2PBSSA5G","created_at":"2026-07-05T10:52:17Z"}],"graph_snapshots":[{"event_id":"sha256:2654c92b4f4749f95f885dedd0e4f393b577b0e903b1b24e64f26a085f6a0999","target":"graph","created_at":"2026-07-05T10:52:17Z","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/2412.11272/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Speech foundation models, such as OpenAI's Whisper, become the state of the art in speech understanding due to their strong accuracy and generalizability. Yet, their applications are mostly limited to processing pre-recorded speech, whereas processing of streaming speech, in particular doing it efficiently, remains rudimentary. Behind this inefficiency are multiple fundamental reasons: (1) speech foundation models are trained to process long, fixed-length voice inputs (often 30 seconds); (2) encoding each voice input requires encoding as many as 1,500 tokens with tens of transformer layers; (3","authors_text":"Felix Xiaozhu Lin, Rongxiang Wang, Zhiming Xu","cross_cats":["eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-15T18:27:37Z","title":"WhisperFlow: speech foundation models in real time"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.11272","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:ee16db1bfba70f5fc669d57351f06deb4b6bba0f40aa8db1b9be7beb969c34d3","target":"record","created_at":"2026-07-05T10:52:17Z","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":"3707c7011d414b23441b44fae3d795560fbb0deb7a33484b4cd9139fc36a5f79","cross_cats_sorted":["eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-15T18:27:37Z","title_canon_sha256":"90408a7ac99963034e1298049856bf259c70a13758032910cc0d786b810c012e"},"schema_version":"1.0","source":{"id":"2412.11272","kind":"arxiv","version":2}},"canonical_sha256":"d3c32903a66982d48d8b1bbc8ec15b2055b097454ac225ea47fe38212ed9aad0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d3c32903a66982d48d8b1bbc8ec15b2055b097454ac225ea47fe38212ed9aad0","first_computed_at":"2026-07-05T10:52:17.083182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:17.083182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"68ANqbpa4/KwEcYsy6/lUVgmlLza+SVNAvMesdFT/tq16EaRW7i6trbph/WqUgCO1BX6dJyyYMlDHt3vwR9DAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:17.083680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.11272","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ee16db1bfba70f5fc669d57351f06deb4b6bba0f40aa8db1b9be7beb969c34d3","sha256:2654c92b4f4749f95f885dedd0e4f393b577b0e903b1b24e64f26a085f6a0999"],"state_sha256":"977fae8f30f61be1815bd72662d786d12ae408632899bc9ee42d6da7896987b3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R4UbMYtGadW43SSmaE/00Q559ykxazEDcrvchoNJUQEzFj7aU9O8m0H1XxhN7+z15qL8MkkCr7mBTFbGFuEWCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-14T06:41:09.472157Z","bundle_sha256":"41d323494eb4456edf2aa6e044998ce53239be5f8e4d7c2eb7aa3c26036ff4db"}}