{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:CRFPVA2BSK2KJWOR5SYQJAU5I7","short_pith_number":"pith:CRFPVA2B","canonical_record":{"source":{"id":"2302.10871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T18:38:41Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"f0652a5bc0faf3f945caf3247c2d5af0e6eb207b11215c95e0783679b05e3ac5","abstract_canon_sha256":"b21a794b4112b0c38dc744621ef0e4f059da6053c7caf9fcd37d0873039b1fd9"},"schema_version":"1.0"},"canonical_sha256":"144afa834192b4a4d9d1ecb104829d47c05aa1e1dd6152749bc88200af2d2053","source":{"kind":"arxiv","id":"2302.10871","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10871","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10871v1","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10871","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"CRFPVA2BSK2K","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_16","alias_value":"CRFPVA2BSK2KJWOR","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_8","alias_value":"CRFPVA2B","created_at":"2026-07-05T05:44:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:CRFPVA2BSK2KJWOR5SYQJAU5I7","target":"record","payload":{"canonical_record":{"source":{"id":"2302.10871","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T18:38:41Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"f0652a5bc0faf3f945caf3247c2d5af0e6eb207b11215c95e0783679b05e3ac5","abstract_canon_sha256":"b21a794b4112b0c38dc744621ef0e4f059da6053c7caf9fcd37d0873039b1fd9"},"schema_version":"1.0"},"canonical_sha256":"144afa834192b4a4d9d1ecb104829d47c05aa1e1dd6152749bc88200af2d2053","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:44:22.802152Z","signature_b64":"935mduRNot+FjkHnL9XqsVHl+V44S3cEij2puTdZbtodBnw6I8QXyfq31mABIjEh3/a7o3VK/nJ+YURtA62zBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"144afa834192b4a4d9d1ecb104829d47c05aa1e1dd6152749bc88200af2d2053","last_reissued_at":"2026-07-05T05:44:22.801768Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:44:22.801768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2302.10871","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":"2026-07-05T05:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TetsnmRFeOmCAjhOFDPoqqJi7rgU0+JGLwdhC+5D4leM6wCpqW4DOT+dlObMr2IVBrKoa5r6Loe/zRAvUU6gDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:15:43.203175Z"},"content_sha256":"60f63211c89cf4bbb7527fb30b1fd6b5ebed4ac720c058159ebbe7bfa774118e","schema_version":"1.0","event_id":"sha256:60f63211c89cf4bbb7527fb30b1fd6b5ebed4ac720c058159ebbe7bfa774118e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:CRFPVA2BSK2KJWOR5SYQJAU5I7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Barry Haddow, Biao Zhang, Rico Sennrich","submitted_at":"2023-02-21T18:38:41Z","abstract_excerpt":"For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality metrics. However, CTC demands an extra prediction layer over the vocabulary space, bringing in nonnegligible model parameters and computational overheads, although this layer is typically not used for inference. In this paper, we re-examine the need for genuine vocabulary labels for CTC for regularization and explore strategies to reduce the CTC label space, targeting improved efficienc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10871","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/2302.10871/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":"2026-07-05T05:44:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KtUjIbY5feu9UmLCCWBLBSyApyhz29z+JtYWFNz9b/SvXSalKkrAWoMmUMUhpPkgazQRG3s3zTrouxlotXoGDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T08:15:43.203710Z"},"content_sha256":"554b9d0433bdef826f2e618a32d58256fc607bda8ea879d20c4289674f496760","schema_version":"1.0","event_id":"sha256:554b9d0433bdef826f2e618a32d58256fc607bda8ea879d20c4289674f496760"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CRFPVA2BSK2KJWOR5SYQJAU5I7/bundle.json","state_url":"https://pith.science/pith/CRFPVA2BSK2KJWOR5SYQJAU5I7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CRFPVA2BSK2KJWOR5SYQJAU5I7/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":"2026-08-19T08:15:43Z","links":{"resolver":"https://pith.science/pith/CRFPVA2BSK2KJWOR5SYQJAU5I7","bundle":"https://pith.science/pith/CRFPVA2BSK2KJWOR5SYQJAU5I7/bundle.json","state":"https://pith.science/pith/CRFPVA2BSK2KJWOR5SYQJAU5I7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CRFPVA2BSK2KJWOR5SYQJAU5I7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:CRFPVA2BSK2KJWOR5SYQJAU5I7","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":"b21a794b4112b0c38dc744621ef0e4f059da6053c7caf9fcd37d0873039b1fd9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T18:38:41Z","title_canon_sha256":"f0652a5bc0faf3f945caf3247c2d5af0e6eb207b11215c95e0783679b05e3ac5"},"schema_version":"1.0","source":{"id":"2302.10871","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2302.10871","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"arxiv_version","alias_value":"2302.10871v1","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10871","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_12","alias_value":"CRFPVA2BSK2K","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_16","alias_value":"CRFPVA2BSK2KJWOR","created_at":"2026-07-05T05:44:22Z"},{"alias_kind":"pith_short_8","alias_value":"CRFPVA2B","created_at":"2026-07-05T05:44:22Z"}],"graph_snapshots":[{"event_id":"sha256:554b9d0433bdef826f2e618a32d58256fc607bda8ea879d20c4289674f496760","target":"graph","created_at":"2026-07-05T05:44:22Z","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/2302.10871/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"For end-to-end speech translation, regularizing the encoder with the Connectionist Temporal Classification (CTC) objective using the source transcript or target translation as labels can greatly improve quality metrics. However, CTC demands an extra prediction layer over the vocabulary space, bringing in nonnegligible model parameters and computational overheads, although this layer is typically not used for inference. In this paper, we re-examine the need for genuine vocabulary labels for CTC for regularization and explore strategies to reduce the CTC label space, targeting improved efficienc","authors_text":"Barry Haddow, Biao Zhang, Rico Sennrich","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T18:38:41Z","title":"Efficient CTC Regularization via Coarse Labels for End-to-End Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10871","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":"sha256:60f63211c89cf4bbb7527fb30b1fd6b5ebed4ac720c058159ebbe7bfa774118e","target":"record","created_at":"2026-07-05T05:44:22Z","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":"b21a794b4112b0c38dc744621ef0e4f059da6053c7caf9fcd37d0873039b1fd9","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-02-21T18:38:41Z","title_canon_sha256":"f0652a5bc0faf3f945caf3247c2d5af0e6eb207b11215c95e0783679b05e3ac5"},"schema_version":"1.0","source":{"id":"2302.10871","kind":"arxiv","version":1}},"canonical_sha256":"144afa834192b4a4d9d1ecb104829d47c05aa1e1dd6152749bc88200af2d2053","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"144afa834192b4a4d9d1ecb104829d47c05aa1e1dd6152749bc88200af2d2053","first_computed_at":"2026-07-05T05:44:22.801768Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:44:22.801768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"935mduRNot+FjkHnL9XqsVHl+V44S3cEij2puTdZbtodBnw6I8QXyfq31mABIjEh3/a7o3VK/nJ+YURtA62zBw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:44:22.802152Z","signed_message":"canonical_sha256_bytes"},"source_id":"2302.10871","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:60f63211c89cf4bbb7527fb30b1fd6b5ebed4ac720c058159ebbe7bfa774118e","sha256:554b9d0433bdef826f2e618a32d58256fc607bda8ea879d20c4289674f496760"],"state_sha256":"c7d03c118edab4913cb1c65afa0b2fb688166749305e7f01decf209dfb5f3e65"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AN2wUGN1BcFZgBK24MelU1rvRDmkx4kY+hll2bR6xUTWwiebrNlK4m8Ynyb+opMS6C6oaR0UJSoymPtuQ9mBAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T08:15:43.209149Z","bundle_sha256":"85343d723faf89fc53625f8b3f77ac3b7efde3f92cabcfabecd6b97526aa392b"}}