{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:B3MSYYNUE7XBZNQSWT4KHFWKGE","short_pith_number":"pith:B3MSYYNU","canonical_record":{"source":{"id":"2502.00377","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T09:29:21Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"93de35926995c4a98de561507d22d2e5ec5f5ef4d7aa144fc0b2e3f497a86fd6","abstract_canon_sha256":"3dd53db295f5e837fd7ba37d13e8d29a9ccf3df6229599b68b55ce5536029844"},"schema_version":"1.0"},"canonical_sha256":"0ed92c61b427ee1cb612b4f8a396ca31291c9aede7421e9e9d74aa75c7cf2ed5","source":{"kind":"arxiv","id":"2502.00377","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00377","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00377v1","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00377","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"B3MSYYNUE7XB","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"B3MSYYNUE7XBZNQS","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"B3MSYYNU","created_at":"2026-07-05T10:08:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:B3MSYYNUE7XBZNQSWT4KHFWKGE","target":"record","payload":{"canonical_record":{"source":{"id":"2502.00377","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T09:29:21Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"93de35926995c4a98de561507d22d2e5ec5f5ef4d7aa144fc0b2e3f497a86fd6","abstract_canon_sha256":"3dd53db295f5e837fd7ba37d13e8d29a9ccf3df6229599b68b55ce5536029844"},"schema_version":"1.0"},"canonical_sha256":"0ed92c61b427ee1cb612b4f8a396ca31291c9aede7421e9e9d74aa75c7cf2ed5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:08:32.881938Z","signature_b64":"2FDrx5b5fwJOrGq66+TUWpxGkLHJ0hqGefTZtZhIfGChuRg3DaomI8bWw9Nlo74SSQuzlU0NUhq5fOyM78ohAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ed92c61b427ee1cb612b4f8a396ca31291c9aede7421e9e9d74aa75c7cf2ed5","last_reissued_at":"2026-07-05T10:08:32.881536Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:08:32.881536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.00377","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":"2026-07-05T10:08:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UNu+bE1sI661xosy6ECX4fJFh0FKx6BjszaunMe4kBB/tlcEb7XJfn+BU7UlK09PzdnVXpgu7VGeEtYr83thCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:46:42.423874Z"},"content_sha256":"9e67b3536ed6055413b8e98b7e89dfabe628b827ef6b9e3ca35e00e7c623db53","schema_version":"1.0","event_id":"sha256:9e67b3536ed6055413b8e98b7e89dfabe628b827ef6b9e3ca35e00e7c623db53"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:B3MSYYNUE7XBZNQSWT4KHFWKGE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Anna Min, Chenxu Hu, Hang Zhao, Yi Ren","submitted_at":"2025-02-01T09:29:21Z","abstract_excerpt":"Though end-to-end speech-to-text translation has been a great success, we argue that the cascaded speech-to-text translation model still has its place, which is usually criticized for the error propagation between automatic speech recognition (ASR) and machine translation (MT) models. In this paper, we explore the benefits of incorporating multiple candidates from ASR and self-supervised speech features into MT. Our analysis reveals that the primary cause of cascading errors stems from the increased divergence between similar samples in the speech domain when mapped to the text domain. By incl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00377","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/2502.00377/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":"2026-07-05T10:08:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FpCrC8cEpgnvi+TCZus0Zx4RbSd/89dTXjOJ9tkFwizqVFTVR5fRlg8lappgHttN6/8Q3QQystdonsezp5f9BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:46:42.424250Z"},"content_sha256":"9dbb44ce37308ff6666ece238968e809ad0d42c36ffe0c7048e3c7668eca4722","schema_version":"1.0","event_id":"sha256:9dbb44ce37308ff6666ece238968e809ad0d42c36ffe0c7048e3c7668eca4722"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3MSYYNUE7XBZNQSWT4KHFWKGE/bundle.json","state_url":"https://pith.science/pith/B3MSYYNUE7XBZNQSWT4KHFWKGE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3MSYYNUE7XBZNQSWT4KHFWKGE/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":"2026-07-06T17:46:42Z","links":{"resolver":"https://pith.science/pith/B3MSYYNUE7XBZNQSWT4KHFWKGE","bundle":"https://pith.science/pith/B3MSYYNUE7XBZNQSWT4KHFWKGE/bundle.json","state":"https://pith.science/pith/B3MSYYNUE7XBZNQSWT4KHFWKGE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3MSYYNUE7XBZNQSWT4KHFWKGE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:B3MSYYNUE7XBZNQSWT4KHFWKGE","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":"3dd53db295f5e837fd7ba37d13e8d29a9ccf3df6229599b68b55ce5536029844","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T09:29:21Z","title_canon_sha256":"93de35926995c4a98de561507d22d2e5ec5f5ef4d7aa144fc0b2e3f497a86fd6"},"schema_version":"1.0","source":{"id":"2502.00377","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.00377","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"arxiv_version","alias_value":"2502.00377v1","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.00377","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_12","alias_value":"B3MSYYNUE7XB","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_16","alias_value":"B3MSYYNUE7XBZNQS","created_at":"2026-07-05T10:08:32Z"},{"alias_kind":"pith_short_8","alias_value":"B3MSYYNU","created_at":"2026-07-05T10:08:32Z"}],"graph_snapshots":[{"event_id":"sha256:9dbb44ce37308ff6666ece238968e809ad0d42c36ffe0c7048e3c7668eca4722","target":"graph","created_at":"2026-07-05T10:08:32Z","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/2502.00377/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Though end-to-end speech-to-text translation has been a great success, we argue that the cascaded speech-to-text translation model still has its place, which is usually criticized for the error propagation between automatic speech recognition (ASR) and machine translation (MT) models. In this paper, we explore the benefits of incorporating multiple candidates from ASR and self-supervised speech features into MT. Our analysis reveals that the primary cause of cascading errors stems from the increased divergence between similar samples in the speech domain when mapped to the text domain. By incl","authors_text":"Anna Min, Chenxu Hu, Hang Zhao, Yi Ren","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T09:29:21Z","title":"When End-to-End is Overkill: Rethinking Cascaded Speech-to-Text Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.00377","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":"sha256:9e67b3536ed6055413b8e98b7e89dfabe628b827ef6b9e3ca35e00e7c623db53","target":"record","created_at":"2026-07-05T10:08:32Z","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":"3dd53db295f5e837fd7ba37d13e8d29a9ccf3df6229599b68b55ce5536029844","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-02-01T09:29:21Z","title_canon_sha256":"93de35926995c4a98de561507d22d2e5ec5f5ef4d7aa144fc0b2e3f497a86fd6"},"schema_version":"1.0","source":{"id":"2502.00377","kind":"arxiv","version":1}},"canonical_sha256":"0ed92c61b427ee1cb612b4f8a396ca31291c9aede7421e9e9d74aa75c7cf2ed5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ed92c61b427ee1cb612b4f8a396ca31291c9aede7421e9e9d74aa75c7cf2ed5","first_computed_at":"2026-07-05T10:08:32.881536Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:08:32.881536Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2FDrx5b5fwJOrGq66+TUWpxGkLHJ0hqGefTZtZhIfGChuRg3DaomI8bWw9Nlo74SSQuzlU0NUhq5fOyM78ohAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:08:32.881938Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.00377","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e67b3536ed6055413b8e98b7e89dfabe628b827ef6b9e3ca35e00e7c623db53","sha256:9dbb44ce37308ff6666ece238968e809ad0d42c36ffe0c7048e3c7668eca4722"],"state_sha256":"aa75aa9ce998ae075226e581d4696435d6a7dabd6f345784b8fdd20c26ed4647"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ztilDRNjS4FhLTx1ryeYBan7p+sCImDIqyNGScYchac8gSWJl6qLTQ/DFdsrrOPCb1KpuMp/012zyoPbhhC7AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:46:42.426237Z","bundle_sha256":"1e8b1e3099e9af1a4c70759cf39a90f24b8979c9e9c08237a3242d831cdced11"}}