{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IY3ET7Y34L2B2CDZOXUMH2N4HW","short_pith_number":"pith:IY3ET7Y3","canonical_record":{"source":{"id":"2104.06678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T07:44:52Z","cross_cats_sorted":[],"title_canon_sha256":"34f73e90077a6d2d99183a4fcdbbb0c6b0776389a2bad473169c6606d3e61dd9","abstract_canon_sha256":"70f7b09d7897b439aedcfbfb404d4b2b59f3500a43755d6fa00588120bf66230"},"schema_version":"1.0"},"canonical_sha256":"463649ff1be2f41d087975e8c3e9bc3d8792aaa18834cf1451aacfa19cbe6fb9","source":{"kind":"arxiv","id":"2104.06678","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06678","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06678v1","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06678","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_12","alias_value":"IY3ET7Y34L2B","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"IY3ET7Y34L2B2CDZ","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"IY3ET7Y3","created_at":"2026-07-05T02:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IY3ET7Y34L2B2CDZOXUMH2N4HW","target":"record","payload":{"canonical_record":{"source":{"id":"2104.06678","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T07:44:52Z","cross_cats_sorted":[],"title_canon_sha256":"34f73e90077a6d2d99183a4fcdbbb0c6b0776389a2bad473169c6606d3e61dd9","abstract_canon_sha256":"70f7b09d7897b439aedcfbfb404d4b2b59f3500a43755d6fa00588120bf66230"},"schema_version":"1.0"},"canonical_sha256":"463649ff1be2f41d087975e8c3e9bc3d8792aaa18834cf1451aacfa19cbe6fb9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:32:08.340080Z","signature_b64":"yR8v7+E1EA8eJxr1QNq0kdu8+UlnMN0LHUkw+ll9p9SrRpD2euuUMR7OSZw5uq7QOeZ0JvO/Hnn6ubLdsmewBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"463649ff1be2f41d087975e8c3e9bc3d8792aaa18834cf1451aacfa19cbe6fb9","last_reissued_at":"2026-07-05T02:32:08.339701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:32:08.339701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.06678","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":"2026-07-05T02:32:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T07jlcaEVyY0thnYerqfglgSvrWIrEJ/HBFD5YSWfvHbVNkCQ+mYiuKpTsa9jULI8n5JmiwHEnzBTp+hOwdmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:54:51.642018Z"},"content_sha256":"266ce45529193ac3763157d98f81cd1d77bfb6e8da581ca71441bebec1c68a5e","schema_version":"1.0","event_id":"sha256:266ce45529193ac3763157d98f81cd1d77bfb6e8da581ca71441bebec1c68a5e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IY3ET7Y34L2B2CDZOXUMH2N4HW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexei Baevski, Alexis Conneau, Anne Wu, Changhan Wang, Juan Pino, Michael Auli","submitted_at":"2021-04-14T07:44:52Z","abstract_excerpt":"In this paper, we improve speech translation (ST) through effectively leveraging large quantities of unlabeled speech and text data in different and complementary ways. We explore both pretraining and self-training by using the large Libri-Light speech audio corpus and language modeling with CommonCrawl. Our experiments improve over the previous state of the art by 2.6 BLEU on average on all four considered CoVoST 2 language pairs via a simple recipe of combining wav2vec 2.0 pretraining, a single iteration of self-training and decoding with a language model. Different to existing work, our app"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06678","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/2104.06678/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":"2026-07-05T02:32:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7CugGbkSRLC6TNm0uLQGDUMet/bcl9eFgBci+j/SLQdbZPDE62TiKrqcZUV3EBG1oydZl09Qsidf12i9QAejDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T00:54:51.642843Z"},"content_sha256":"9a1a19d7e38bafae8fdc7489b8006ef100ace0720e45902ef398af585024f59c","schema_version":"1.0","event_id":"sha256:9a1a19d7e38bafae8fdc7489b8006ef100ace0720e45902ef398af585024f59c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IY3ET7Y34L2B2CDZOXUMH2N4HW/bundle.json","state_url":"https://pith.science/pith/IY3ET7Y34L2B2CDZOXUMH2N4HW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IY3ET7Y34L2B2CDZOXUMH2N4HW/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":"2026-08-07T00:54:51Z","links":{"resolver":"https://pith.science/pith/IY3ET7Y34L2B2CDZOXUMH2N4HW","bundle":"https://pith.science/pith/IY3ET7Y34L2B2CDZOXUMH2N4HW/bundle.json","state":"https://pith.science/pith/IY3ET7Y34L2B2CDZOXUMH2N4HW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IY3ET7Y34L2B2CDZOXUMH2N4HW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IY3ET7Y34L2B2CDZOXUMH2N4HW","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":"70f7b09d7897b439aedcfbfb404d4b2b59f3500a43755d6fa00588120bf66230","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T07:44:52Z","title_canon_sha256":"34f73e90077a6d2d99183a4fcdbbb0c6b0776389a2bad473169c6606d3e61dd9"},"schema_version":"1.0","source":{"id":"2104.06678","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.06678","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"arxiv_version","alias_value":"2104.06678v1","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.06678","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_12","alias_value":"IY3ET7Y34L2B","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"IY3ET7Y34L2B2CDZ","created_at":"2026-07-05T02:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"IY3ET7Y3","created_at":"2026-07-05T02:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:9a1a19d7e38bafae8fdc7489b8006ef100ace0720e45902ef398af585024f59c","target":"graph","created_at":"2026-07-05T02:32:08Z","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/2104.06678/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we improve speech translation (ST) through effectively leveraging large quantities of unlabeled speech and text data in different and complementary ways. We explore both pretraining and self-training by using the large Libri-Light speech audio corpus and language modeling with CommonCrawl. Our experiments improve over the previous state of the art by 2.6 BLEU on average on all four considered CoVoST 2 language pairs via a simple recipe of combining wav2vec 2.0 pretraining, a single iteration of self-training and decoding with a language model. Different to existing work, our app","authors_text":"Alexei Baevski, Alexis Conneau, Anne Wu, Changhan Wang, Juan Pino, Michael Auli","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T07:44:52Z","title":"Large-Scale Self- and Semi-Supervised Learning for Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.06678","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":"sha256:266ce45529193ac3763157d98f81cd1d77bfb6e8da581ca71441bebec1c68a5e","target":"record","created_at":"2026-07-05T02:32:08Z","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":"70f7b09d7897b439aedcfbfb404d4b2b59f3500a43755d6fa00588120bf66230","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-04-14T07:44:52Z","title_canon_sha256":"34f73e90077a6d2d99183a4fcdbbb0c6b0776389a2bad473169c6606d3e61dd9"},"schema_version":"1.0","source":{"id":"2104.06678","kind":"arxiv","version":1}},"canonical_sha256":"463649ff1be2f41d087975e8c3e9bc3d8792aaa18834cf1451aacfa19cbe6fb9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"463649ff1be2f41d087975e8c3e9bc3d8792aaa18834cf1451aacfa19cbe6fb9","first_computed_at":"2026-07-05T02:32:08.339701Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:32:08.339701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"yR8v7+E1EA8eJxr1QNq0kdu8+UlnMN0LHUkw+ll9p9SrRpD2euuUMR7OSZw5uq7QOeZ0JvO/Hnn6ubLdsmewBA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:32:08.340080Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.06678","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:266ce45529193ac3763157d98f81cd1d77bfb6e8da581ca71441bebec1c68a5e","sha256:9a1a19d7e38bafae8fdc7489b8006ef100ace0720e45902ef398af585024f59c"],"state_sha256":"26d2b4be0d7a80ec7bfde9b2c79140dc5a4cb71fa6287937b444cdb7355cf372"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RB+K8HgTgGuc3rNS3nCCIHTLD0oqbOzp0f4ulqh7F+5DdKpgrsX7WnvlnHzkyPTuaXc0kYVwOALXVaInK3DnAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T00:54:51.650113Z","bundle_sha256":"a5f55e1025f278774266303025d67626995c6d2c4cc98fb42f2ef222bbb11265"}}