{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:7GTNM6FC6DSXZVTAZJ6VIYSCAW","short_pith_number":"pith:7GTNM6FC","canonical_record":{"source":{"id":"2409.18044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T16:46:46Z","cross_cats_sorted":[],"title_canon_sha256":"e3a614e3dcbb94b0b88aaedd01ee9c13f80766d8bc39f61eeb54227f07b0a60a","abstract_canon_sha256":"3ed3a92873f4b11b2202fa6f08a1ca14807d19b11176f2a0b81b1f4c297ba8f9"},"schema_version":"1.0"},"canonical_sha256":"f9a6d678a2f0e57cd660ca7d546242058ac56c12cb8d25f8a53b5012f012aa5a","source":{"kind":"arxiv","id":"2409.18044","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18044","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18044v1","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18044","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"7GTNM6FC6DSX","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"pith_short_16","alias_value":"7GTNM6FC6DSXZVTA","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"pith_short_8","alias_value":"7GTNM6FC","created_at":"2026-07-05T09:12:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:7GTNM6FC6DSXZVTAZJ6VIYSCAW","target":"record","payload":{"canonical_record":{"source":{"id":"2409.18044","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T16:46:46Z","cross_cats_sorted":[],"title_canon_sha256":"e3a614e3dcbb94b0b88aaedd01ee9c13f80766d8bc39f61eeb54227f07b0a60a","abstract_canon_sha256":"3ed3a92873f4b11b2202fa6f08a1ca14807d19b11176f2a0b81b1f4c297ba8f9"},"schema_version":"1.0"},"canonical_sha256":"f9a6d678a2f0e57cd660ca7d546242058ac56c12cb8d25f8a53b5012f012aa5a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:12:19.711108Z","signature_b64":"xOLqtKZTdoXEHVQTdqVFBdve8+wWkz4ULt1g2ke1fkVefDhkCWUHAP+kSYDJ8dw1LG0XEXSvUcEv+GrEOPW9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9a6d678a2f0e57cd660ca7d546242058ac56c12cb8d25f8a53b5012f012aa5a","last_reissued_at":"2026-07-05T09:12:19.710632Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:12:19.710632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.18044","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":"2026-07-05T09:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hAPwcFp6euajutbM7AUGW4F5Rl5fEGmFp3QgXU9c/vVheCnPK4U0SkOdhffoIgUHU1+Wm7zqUcmpIng7MRHAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:26:15.911928Z"},"content_sha256":"3075549c7bb1f307a32486d8e772e1c0f57e0e520fca41e7c240e96f5080c289","schema_version":"1.0","event_id":"sha256:3075549c7bb1f307a32486d8e772e1c0f57e0e520fca41e7c240e96f5080c289"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:7GTNM6FC6DSXZVTAZJ6VIYSCAW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unveiling the Role of Pretraining in Direct Speech Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Belen Alastruey, Gerard I. G\\'allego, Marta R. Costa-juss\\`a","submitted_at":"2024-09-26T16:46:46Z","abstract_excerpt":"Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this study, we compare the training dynamics of a system using a pretrained encoder, the conventional approach, and one trained from scratch. We observe that, throughout the training, the randomly initialized model struggles to incorporate information from the speech inputs for its predictions. Hence, we hypothesize that this issue stems from the difficulty of effect"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18044","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/2409.18044/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":"2026-07-05T09:12:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"USCt3xNDXgpuba1AgmuGSeEAlTY5yfqI+FN8IUAATVqkb8ITjXjH/ri0/GDQF7BxJsj5q1Y7IOp0kWd/9kIhDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:26:15.912295Z"},"content_sha256":"caf517d541379a775a31e7932bae4e7326d42455893675f5d148908024d14770","schema_version":"1.0","event_id":"sha256:caf517d541379a775a31e7932bae4e7326d42455893675f5d148908024d14770"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7GTNM6FC6DSXZVTAZJ6VIYSCAW/bundle.json","state_url":"https://pith.science/pith/7GTNM6FC6DSXZVTAZJ6VIYSCAW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7GTNM6FC6DSXZVTAZJ6VIYSCAW/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":"2026-07-07T14:26:15Z","links":{"resolver":"https://pith.science/pith/7GTNM6FC6DSXZVTAZJ6VIYSCAW","bundle":"https://pith.science/pith/7GTNM6FC6DSXZVTAZJ6VIYSCAW/bundle.json","state":"https://pith.science/pith/7GTNM6FC6DSXZVTAZJ6VIYSCAW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7GTNM6FC6DSXZVTAZJ6VIYSCAW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7GTNM6FC6DSXZVTAZJ6VIYSCAW","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":"3ed3a92873f4b11b2202fa6f08a1ca14807d19b11176f2a0b81b1f4c297ba8f9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T16:46:46Z","title_canon_sha256":"e3a614e3dcbb94b0b88aaedd01ee9c13f80766d8bc39f61eeb54227f07b0a60a"},"schema_version":"1.0","source":{"id":"2409.18044","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.18044","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"arxiv_version","alias_value":"2409.18044v1","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.18044","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"pith_short_12","alias_value":"7GTNM6FC6DSX","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"pith_short_16","alias_value":"7GTNM6FC6DSXZVTA","created_at":"2026-07-05T09:12:19Z"},{"alias_kind":"pith_short_8","alias_value":"7GTNM6FC","created_at":"2026-07-05T09:12:19Z"}],"graph_snapshots":[{"event_id":"sha256:caf517d541379a775a31e7932bae4e7326d42455893675f5d148908024d14770","target":"graph","created_at":"2026-07-05T09:12:19Z","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/2409.18044/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct speech-to-text translation systems encounter an important drawback in data scarcity. A common solution consists on pretraining the encoder on automatic speech recognition, hence losing efficiency in the training process. In this study, we compare the training dynamics of a system using a pretrained encoder, the conventional approach, and one trained from scratch. We observe that, throughout the training, the randomly initialized model struggles to incorporate information from the speech inputs for its predictions. Hence, we hypothesize that this issue stems from the difficulty of effect","authors_text":"Belen Alastruey, Gerard I. G\\'allego, Marta R. Costa-juss\\`a","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T16:46:46Z","title":"Unveiling the Role of Pretraining in Direct Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.18044","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":"sha256:3075549c7bb1f307a32486d8e772e1c0f57e0e520fca41e7c240e96f5080c289","target":"record","created_at":"2026-07-05T09:12:19Z","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":"3ed3a92873f4b11b2202fa6f08a1ca14807d19b11176f2a0b81b1f4c297ba8f9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-26T16:46:46Z","title_canon_sha256":"e3a614e3dcbb94b0b88aaedd01ee9c13f80766d8bc39f61eeb54227f07b0a60a"},"schema_version":"1.0","source":{"id":"2409.18044","kind":"arxiv","version":1}},"canonical_sha256":"f9a6d678a2f0e57cd660ca7d546242058ac56c12cb8d25f8a53b5012f012aa5a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9a6d678a2f0e57cd660ca7d546242058ac56c12cb8d25f8a53b5012f012aa5a","first_computed_at":"2026-07-05T09:12:19.710632Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:12:19.710632Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xOLqtKZTdoXEHVQTdqVFBdve8+wWkz4ULt1g2ke1fkVefDhkCWUHAP+kSYDJ8dw1LG0XEXSvUcEv+GrEOPW9Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T09:12:19.711108Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.18044","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3075549c7bb1f307a32486d8e772e1c0f57e0e520fca41e7c240e96f5080c289","sha256:caf517d541379a775a31e7932bae4e7326d42455893675f5d148908024d14770"],"state_sha256":"8d72bcadae529c16801d7be9b71e5c817518f87f7e5b834b5fc5e70edf7b2c49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kTOYtedRrvyWxh2OlWNhDXThgyDfJW0UYwJnkIUiGcTAP61MlwD+PU/7Eud11q29SvBGJxp0fFWxjDfx0hNjDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:26:15.914387Z","bundle_sha256":"d27eff1f3320e7675b95489ccce93bf01c507d5ea4eed10b8c25e1b4f8c5bf92"}}