{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:S5LSQZXDCTFBHFC277KAYUSUVT","short_pith_number":"pith:S5LSQZXD","canonical_record":{"source":{"id":"2406.18373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T14:17:36Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"1ca49a60acca5a8f27a7082593fc1bd9a7bf3286481aa712e24d07082ef3c0af","abstract_canon_sha256":"f0638df8bd41a044e929815e86d0d963a3d7665c45f01f9bbb321b3ce67a11d9"},"schema_version":"1.0"},"canonical_sha256":"97572866e314ca13945affd40c5254acede749e4427ceed2d06438699d2ddd08","source":{"kind":"arxiv","id":"2406.18373","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18373","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18373v1","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18373","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"pith_short_12","alias_value":"S5LSQZXDCTFB","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"pith_short_16","alias_value":"S5LSQZXDCTFBHFC2","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"pith_short_8","alias_value":"S5LSQZXD","created_at":"2026-07-05T08:37:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:S5LSQZXDCTFBHFC277KAYUSUVT","target":"record","payload":{"canonical_record":{"source":{"id":"2406.18373","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T14:17:36Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"1ca49a60acca5a8f27a7082593fc1bd9a7bf3286481aa712e24d07082ef3c0af","abstract_canon_sha256":"f0638df8bd41a044e929815e86d0d963a3d7665c45f01f9bbb321b3ce67a11d9"},"schema_version":"1.0"},"canonical_sha256":"97572866e314ca13945affd40c5254acede749e4427ceed2d06438699d2ddd08","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:37:08.460943Z","signature_b64":"RxQaFdoHWAdJ6SI10u2hr/us7s87qQmqkP0d+T6t9U+si+pcVOVAByUirCpli1CBzCQdLWlKmyBnf7t9fkK0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97572866e314ca13945affd40c5254acede749e4427ceed2d06438699d2ddd08","last_reissued_at":"2026-07-05T08:37:08.460467Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:37:08.460467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.18373","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":"2026-07-05T08:37:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PUEt39O4LO7pJAex9hzZN692pUdyRvv4FzP7rRcs55GNt/ziad2yNKrXWIrrymr5E+Ldcc24MgMN7+lRvIEHBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:43:59.234273Z"},"content_sha256":"eb54dbf539c239a13322ae489be9d5be0bd1412437fb826ab48f7ecb03ea5120","schema_version":"1.0","event_id":"sha256:eb54dbf539c239a13322ae489be9d5be0bd1412437fb826ab48f7ecb03ea5120"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:S5LSQZXDCTFBHFC277KAYUSUVT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Data Pruning for Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Adriana Fernandez-Lopez, Boqian Wu, Decebal Constantin Mocanu, Lu Yin, Maja Pantic, Mykola Pechenizkiy, Pingchuan Ma, Qiao Xiao, Shiwei Liu, Stavros Petridis","submitted_at":"2024-06-26T14:17:36Z","abstract_excerpt":"The recent success of Automatic Speech Recognition (ASR) is largely attributed to the ever-growing amount of training data. However, this trend has made model training prohibitively costly and imposed computational demands. While data pruning has been proposed to mitigate this issue by identifying a small subset of relevant data, its application in ASR has been barely explored, and existing works often entail significant overhead to achieve meaningful results. To fill this gap, this paper presents the first investigation of dynamic data pruning for ASR, finding that we can reach the full-data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18373","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/2406.18373/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":"2026-07-05T08:37:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jTSpcZWrOoOIL3hSuklZaY6luprAl4+lVMCOCF43v6V6TsW9tpVF1191LJ94t3lsusjcdqyocEq7n1VocH1YCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T14:43:59.235419Z"},"content_sha256":"7b8f1407031a9b0cec3ccef02a60d1db2766ee9a2e47d466ba364bb51be10c54","schema_version":"1.0","event_id":"sha256:7b8f1407031a9b0cec3ccef02a60d1db2766ee9a2e47d466ba364bb51be10c54"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S5LSQZXDCTFBHFC277KAYUSUVT/bundle.json","state_url":"https://pith.science/pith/S5LSQZXDCTFBHFC277KAYUSUVT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S5LSQZXDCTFBHFC277KAYUSUVT/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":"2026-08-04T14:43:59Z","links":{"resolver":"https://pith.science/pith/S5LSQZXDCTFBHFC277KAYUSUVT","bundle":"https://pith.science/pith/S5LSQZXDCTFBHFC277KAYUSUVT/bundle.json","state":"https://pith.science/pith/S5LSQZXDCTFBHFC277KAYUSUVT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S5LSQZXDCTFBHFC277KAYUSUVT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:S5LSQZXDCTFBHFC277KAYUSUVT","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":"f0638df8bd41a044e929815e86d0d963a3d7665c45f01f9bbb321b3ce67a11d9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T14:17:36Z","title_canon_sha256":"1ca49a60acca5a8f27a7082593fc1bd9a7bf3286481aa712e24d07082ef3c0af"},"schema_version":"1.0","source":{"id":"2406.18373","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18373","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18373v1","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18373","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"pith_short_12","alias_value":"S5LSQZXDCTFB","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"pith_short_16","alias_value":"S5LSQZXDCTFBHFC2","created_at":"2026-07-05T08:37:08Z"},{"alias_kind":"pith_short_8","alias_value":"S5LSQZXD","created_at":"2026-07-05T08:37:08Z"}],"graph_snapshots":[{"event_id":"sha256:7b8f1407031a9b0cec3ccef02a60d1db2766ee9a2e47d466ba364bb51be10c54","target":"graph","created_at":"2026-07-05T08:37:08Z","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/2406.18373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent success of Automatic Speech Recognition (ASR) is largely attributed to the ever-growing amount of training data. However, this trend has made model training prohibitively costly and imposed computational demands. While data pruning has been proposed to mitigate this issue by identifying a small subset of relevant data, its application in ASR has been barely explored, and existing works often entail significant overhead to achieve meaningful results. To fill this gap, this paper presents the first investigation of dynamic data pruning for ASR, finding that we can reach the full-data ","authors_text":"Adriana Fernandez-Lopez, Boqian Wu, Decebal Constantin Mocanu, Lu Yin, Maja Pantic, Mykola Pechenizkiy, Pingchuan Ma, Qiao Xiao, Shiwei Liu, Stavros Petridis","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T14:17:36Z","title":"Dynamic Data Pruning for Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18373","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:eb54dbf539c239a13322ae489be9d5be0bd1412437fb826ab48f7ecb03ea5120","target":"record","created_at":"2026-07-05T08:37:08Z","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":"f0638df8bd41a044e929815e86d0d963a3d7665c45f01f9bbb321b3ce67a11d9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-26T14:17:36Z","title_canon_sha256":"1ca49a60acca5a8f27a7082593fc1bd9a7bf3286481aa712e24d07082ef3c0af"},"schema_version":"1.0","source":{"id":"2406.18373","kind":"arxiv","version":1}},"canonical_sha256":"97572866e314ca13945affd40c5254acede749e4427ceed2d06438699d2ddd08","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97572866e314ca13945affd40c5254acede749e4427ceed2d06438699d2ddd08","first_computed_at":"2026-07-05T08:37:08.460467Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:37:08.460467Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RxQaFdoHWAdJ6SI10u2hr/us7s87qQmqkP0d+T6t9U+si+pcVOVAByUirCpli1CBzCQdLWlKmyBnf7t9fkK0AA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:37:08.460943Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18373","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eb54dbf539c239a13322ae489be9d5be0bd1412437fb826ab48f7ecb03ea5120","sha256:7b8f1407031a9b0cec3ccef02a60d1db2766ee9a2e47d466ba364bb51be10c54"],"state_sha256":"c7dc350d97721af4adb7ad9e3a9ea125a4f89f488a4685c63607e896d6a07041"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9uEkweRFFqvcfpJqthugmDMAVgVPps9I9fYELg1Kf45jZFc3lhXXArzdD793vTItYqkdvBe4/lXGDW/n7c/GBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T14:43:59.243139Z","bundle_sha256":"2a5364d92ef85e10f89d38bfe83fcea56cf3df44519ecfe60f868dbf3ca9beba"}}