{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:FPALU7EQBEZ2EYQJEGZT2D6VAV","short_pith_number":"pith:FPALU7EQ","canonical_record":{"source":{"id":"2008.04034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T11:42:43Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"7f36ed82f7aebab6433b3ff4625f43c17b873ed52934f216f214b1d6c4c987ce","abstract_canon_sha256":"75e2a633a6432d35df89e164d78008f71d426ce4b24041efe58b48b08fdec810"},"schema_version":"1.0"},"canonical_sha256":"2bc0ba7c900933a2620921b33d0fd505795d781bde0516ce21e4a65b8a9377f1","source":{"kind":"arxiv","id":"2008.04034","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.04034","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"arxiv_version","alias_value":"2008.04034v1","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04034","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"pith_short_12","alias_value":"FPALU7EQBEZ2","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"pith_short_16","alias_value":"FPALU7EQBEZ2EYQJ","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"pith_short_8","alias_value":"FPALU7EQ","created_at":"2026-07-05T01:25:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:FPALU7EQBEZ2EYQJEGZT2D6VAV","target":"record","payload":{"canonical_record":{"source":{"id":"2008.04034","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T11:42:43Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"7f36ed82f7aebab6433b3ff4625f43c17b873ed52934f216f214b1d6c4c987ce","abstract_canon_sha256":"75e2a633a6432d35df89e164d78008f71d426ce4b24041efe58b48b08fdec810"},"schema_version":"1.0"},"canonical_sha256":"2bc0ba7c900933a2620921b33d0fd505795d781bde0516ce21e4a65b8a9377f1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:59.092929Z","signature_b64":"uVzuNBUQrsZ30dsnF8jVFEjmxwY4XV+E+cXa57P5hyuMDThv12nbKxyo1507JSZUHpQ2Yz2CguJUFPtVFYd6DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2bc0ba7c900933a2620921b33d0fd505795d781bde0516ce21e4a65b8a9377f1","last_reissued_at":"2026-07-05T01:25:59.092471Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:59.092471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.04034","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":"2026-07-05T01:25:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h+H6iz1kRFS0etTyY3iOC19kNUhz8ISTL2iWkYcdk9ESQfutxob6PhAen0ywhsc2ROYQd3vKC5P9MJUML+CnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:32:48.418189Z"},"content_sha256":"afee2860bd1480ca60e076f3b96cc28cb521dd69bc3e854a637b802f4bda0c56","schema_version":"1.0","event_id":"sha256:afee2860bd1480ca60e076f3b96cc28cb521dd69bc3e854a637b802f4bda0c56"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:FPALU7EQBEZ2EYQJEGZT2D6VAV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Subword Regularization: An Analysis of Scalability and Generalization for End-to-End Automatic Speech Recognition","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Egor Lakomkin, Ilya Sklyar, Jahn Heymann, Simon Wiesler","submitted_at":"2020-08-10T11:42:43Z","abstract_excerpt":"Subwords are the most widely used output units in end-to-end speech recognition. They combine the best of two worlds by modeling the majority of frequent words directly and at the same time allow open vocabulary speech recognition by backing off to shorter units or characters to construct words unseen during training. However, mapping text to subwords is ambiguous and often multiple segmentation variants are possible. Yet, many systems are trained using only the most likely segmentation. Recent research suggests that sampling subword segmentations during training acts as a regularizer for neur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04034","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/2008.04034/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":"2026-07-05T01:25:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"w0XksIWUdUEPdOAD6VNkCNGK0F8Q1IkxarA/50WeU9hg5aVERvQ4sHl31BxHEw7E1eu8SKPjXFffwai9cg9RCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-12T18:32:48.418575Z"},"content_sha256":"938b9ac1c000bbf2ab8035d271a3f3b8e9ce65ea96fbd2dc85efbb0a60fcdb8a","schema_version":"1.0","event_id":"sha256:938b9ac1c000bbf2ab8035d271a3f3b8e9ce65ea96fbd2dc85efbb0a60fcdb8a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FPALU7EQBEZ2EYQJEGZT2D6VAV/bundle.json","state_url":"https://pith.science/pith/FPALU7EQBEZ2EYQJEGZT2D6VAV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FPALU7EQBEZ2EYQJEGZT2D6VAV/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":"2026-07-12T18:32:48Z","links":{"resolver":"https://pith.science/pith/FPALU7EQBEZ2EYQJEGZT2D6VAV","bundle":"https://pith.science/pith/FPALU7EQBEZ2EYQJEGZT2D6VAV/bundle.json","state":"https://pith.science/pith/FPALU7EQBEZ2EYQJEGZT2D6VAV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FPALU7EQBEZ2EYQJEGZT2D6VAV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:FPALU7EQBEZ2EYQJEGZT2D6VAV","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":"75e2a633a6432d35df89e164d78008f71d426ce4b24041efe58b48b08fdec810","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T11:42:43Z","title_canon_sha256":"7f36ed82f7aebab6433b3ff4625f43c17b873ed52934f216f214b1d6c4c987ce"},"schema_version":"1.0","source":{"id":"2008.04034","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.04034","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"arxiv_version","alias_value":"2008.04034v1","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04034","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"pith_short_12","alias_value":"FPALU7EQBEZ2","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"pith_short_16","alias_value":"FPALU7EQBEZ2EYQJ","created_at":"2026-07-05T01:25:59Z"},{"alias_kind":"pith_short_8","alias_value":"FPALU7EQ","created_at":"2026-07-05T01:25:59Z"}],"graph_snapshots":[{"event_id":"sha256:938b9ac1c000bbf2ab8035d271a3f3b8e9ce65ea96fbd2dc85efbb0a60fcdb8a","target":"graph","created_at":"2026-07-05T01:25:59Z","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/2008.04034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Subwords are the most widely used output units in end-to-end speech recognition. They combine the best of two worlds by modeling the majority of frequent words directly and at the same time allow open vocabulary speech recognition by backing off to shorter units or characters to construct words unseen during training. However, mapping text to subwords is ambiguous and often multiple segmentation variants are possible. Yet, many systems are trained using only the most likely segmentation. Recent research suggests that sampling subword segmentations during training acts as a regularizer for neur","authors_text":"Egor Lakomkin, Ilya Sklyar, Jahn Heymann, Simon Wiesler","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T11:42:43Z","title":"Subword Regularization: An Analysis of Scalability and Generalization for End-to-End Automatic Speech Recognition"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04034","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:afee2860bd1480ca60e076f3b96cc28cb521dd69bc3e854a637b802f4bda0c56","target":"record","created_at":"2026-07-05T01:25:59Z","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":"75e2a633a6432d35df89e164d78008f71d426ce4b24041efe58b48b08fdec810","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2020-08-10T11:42:43Z","title_canon_sha256":"7f36ed82f7aebab6433b3ff4625f43c17b873ed52934f216f214b1d6c4c987ce"},"schema_version":"1.0","source":{"id":"2008.04034","kind":"arxiv","version":1}},"canonical_sha256":"2bc0ba7c900933a2620921b33d0fd505795d781bde0516ce21e4a65b8a9377f1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2bc0ba7c900933a2620921b33d0fd505795d781bde0516ce21e4a65b8a9377f1","first_computed_at":"2026-07-05T01:25:59.092471Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:25:59.092471Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uVzuNBUQrsZ30dsnF8jVFEjmxwY4XV+E+cXa57P5hyuMDThv12nbKxyo1507JSZUHpQ2Yz2CguJUFPtVFYd6DA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:25:59.092929Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.04034","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:afee2860bd1480ca60e076f3b96cc28cb521dd69bc3e854a637b802f4bda0c56","sha256:938b9ac1c000bbf2ab8035d271a3f3b8e9ce65ea96fbd2dc85efbb0a60fcdb8a"],"state_sha256":"e04f5fb02df9d149cbe0e4472619a69af8de154bce1d3fa1ee1d04e5ecf0a141"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dEuTUGIip8DXPvjkJJ2xfakFOi9KKUUl3aCZ/QswTzhSZvdn6Lu9g0bLAtcGVgVvyPyCRr8Ou8VMASHFxsj7Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-12T18:32:48.420653Z","bundle_sha256":"b4255b3e1968073e9748beddacc3506ea1dd68cbe7bd0c2e15d0613fa99f29eb"}}