{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:LU3KZE7E3JTX2CHVD475MNTYCK","short_pith_number":"pith:LU3KZE7E","canonical_record":{"source":{"id":"2506.16251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T12:11:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"230986b2bbc4862eab917d617cfae88c69b834be7b7df5eb6d9b0b6dcd962ecf","abstract_canon_sha256":"3272ca2575488c8db5f17d5b9ec923223d6d681b0a95948f34d0118a191242be"},"schema_version":"1.0"},"canonical_sha256":"5d36ac93e4da677d08f51f3fd6367812a25c5b0dde591c121ef7fd716f3e791c","source":{"kind":"arxiv","id":"2506.16251","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16251","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16251v1","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16251","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"pith_short_12","alias_value":"LU3KZE7E3JTX","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"pith_short_16","alias_value":"LU3KZE7E3JTX2CHV","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"pith_short_8","alias_value":"LU3KZE7E","created_at":"2026-07-05T11:24:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:LU3KZE7E3JTX2CHVD475MNTYCK","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16251","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T12:11:01Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"230986b2bbc4862eab917d617cfae88c69b834be7b7df5eb6d9b0b6dcd962ecf","abstract_canon_sha256":"3272ca2575488c8db5f17d5b9ec923223d6d681b0a95948f34d0118a191242be"},"schema_version":"1.0"},"canonical_sha256":"5d36ac93e4da677d08f51f3fd6367812a25c5b0dde591c121ef7fd716f3e791c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:33.382671Z","signature_b64":"7VqG8Vmf8pvkCcg4aUUQd5uQCpTT4N9KyGoWfGSz1TqgEpsZjb6lxNEvKdMc1devHQFh6ZPYJdDnnnjgtyYWDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5d36ac93e4da677d08f51f3fd6367812a25c5b0dde591c121ef7fd716f3e791c","last_reissued_at":"2026-07-05T11:24:33.382199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:33.382199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16251","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":"2026-07-05T11:24:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CjKacGGS0ZKZjLzSC+qLhpSiFgZBRNE0ZVz8PXEGY+1M9N6j7YBUYIZvcPEMXP9WTfRsJV07OSAqDzwNJ6BFDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:10:15.780229Z"},"content_sha256":"c8881ada302035aec5989581efa52e10d7fb1f374e6db426af9473cfbaa27dd9","schema_version":"1.0","event_id":"sha256:c8881ada302035aec5989581efa52e10d7fb1f374e6db426af9473cfbaa27dd9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:LU3KZE7E3JTX2CHVD475MNTYCK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Aishwarya Pothula, Anil Kumar Vuppala, Bhavana Akkiraju, Charan D, Santosh Kesiraju, Srihari Bandarupalli","submitted_at":"2025-06-19T12:11:01Z","abstract_excerpt":"The scarcity of high-quality annotated data presents a significant challenge in developing effective end-to-end speech-to-text translation (ST) systems, particularly for low-resource languages. This paper explores the hypothesis that weakly labeled data can be used to build ST models for low-resource language pairs. We constructed speech-to-text translation datasets with the help of bitext mining using state-of-the-art sentence encoders. We mined the multilingual Shrutilipi corpus to build Shrutilipi-anuvaad, a dataset comprising ST data for language pairs Bengali-Hindi, Malayalam-Hindi, Odia-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16251","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/2506.16251/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":"2026-07-05T11:24:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ennWoHXyNNCpDhwCD/SjQZ3eZifrEphI35NDq2Ry0nGgm5GFtXC6ohImnzJRHVuSI7gNKvJhaCRbtCUR2ccaBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:10:15.780775Z"},"content_sha256":"747fef3ec54856e9f97679c45144b3fa1bf341e0190d56cdaf86c01f4a58f01c","schema_version":"1.0","event_id":"sha256:747fef3ec54856e9f97679c45144b3fa1bf341e0190d56cdaf86c01f4a58f01c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LU3KZE7E3JTX2CHVD475MNTYCK/bundle.json","state_url":"https://pith.science/pith/LU3KZE7E3JTX2CHVD475MNTYCK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LU3KZE7E3JTX2CHVD475MNTYCK/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":"2026-08-04T09:10:15Z","links":{"resolver":"https://pith.science/pith/LU3KZE7E3JTX2CHVD475MNTYCK","bundle":"https://pith.science/pith/LU3KZE7E3JTX2CHVD475MNTYCK/bundle.json","state":"https://pith.science/pith/LU3KZE7E3JTX2CHVD475MNTYCK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LU3KZE7E3JTX2CHVD475MNTYCK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:LU3KZE7E3JTX2CHVD475MNTYCK","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":"3272ca2575488c8db5f17d5b9ec923223d6d681b0a95948f34d0118a191242be","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T12:11:01Z","title_canon_sha256":"230986b2bbc4862eab917d617cfae88c69b834be7b7df5eb6d9b0b6dcd962ecf"},"schema_version":"1.0","source":{"id":"2506.16251","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16251","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16251v1","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16251","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"pith_short_12","alias_value":"LU3KZE7E3JTX","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"pith_short_16","alias_value":"LU3KZE7E3JTX2CHV","created_at":"2026-07-05T11:24:33Z"},{"alias_kind":"pith_short_8","alias_value":"LU3KZE7E","created_at":"2026-07-05T11:24:33Z"}],"graph_snapshots":[{"event_id":"sha256:747fef3ec54856e9f97679c45144b3fa1bf341e0190d56cdaf86c01f4a58f01c","target":"graph","created_at":"2026-07-05T11:24:33Z","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/2506.16251/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The scarcity of high-quality annotated data presents a significant challenge in developing effective end-to-end speech-to-text translation (ST) systems, particularly for low-resource languages. This paper explores the hypothesis that weakly labeled data can be used to build ST models for low-resource language pairs. We constructed speech-to-text translation datasets with the help of bitext mining using state-of-the-art sentence encoders. We mined the multilingual Shrutilipi corpus to build Shrutilipi-anuvaad, a dataset comprising ST data for language pairs Bengali-Hindi, Malayalam-Hindi, Odia-","authors_text":"Aishwarya Pothula, Anil Kumar Vuppala, Bhavana Akkiraju, Charan D, Santosh Kesiraju, Srihari Bandarupalli","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T12:11:01Z","title":"End-to-End Speech Translation for Low-Resource Languages Using Weakly Labeled Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16251","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:c8881ada302035aec5989581efa52e10d7fb1f374e6db426af9473cfbaa27dd9","target":"record","created_at":"2026-07-05T11:24:33Z","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":"3272ca2575488c8db5f17d5b9ec923223d6d681b0a95948f34d0118a191242be","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T12:11:01Z","title_canon_sha256":"230986b2bbc4862eab917d617cfae88c69b834be7b7df5eb6d9b0b6dcd962ecf"},"schema_version":"1.0","source":{"id":"2506.16251","kind":"arxiv","version":1}},"canonical_sha256":"5d36ac93e4da677d08f51f3fd6367812a25c5b0dde591c121ef7fd716f3e791c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d36ac93e4da677d08f51f3fd6367812a25c5b0dde591c121ef7fd716f3e791c","first_computed_at":"2026-07-05T11:24:33.382199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:33.382199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7VqG8Vmf8pvkCcg4aUUQd5uQCpTT4N9KyGoWfGSz1TqgEpsZjb6lxNEvKdMc1devHQFh6ZPYJdDnnnjgtyYWDg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:33.382671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16251","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8881ada302035aec5989581efa52e10d7fb1f374e6db426af9473cfbaa27dd9","sha256:747fef3ec54856e9f97679c45144b3fa1bf341e0190d56cdaf86c01f4a58f01c"],"state_sha256":"0c4a5d54d43c75f85634b018acce5991ebb20044f43464252c96140c91f97c95"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"q0dHw3qKOEmaTpaKTkBYsks1Y704uybD3R6orXQCtQSHd6T7LI4/9+d7ErUjdGpfoEmF68p5DlCoegsxtt6DBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:10:15.785073Z","bundle_sha256":"f98aa67cac2d8692f354ea8d1045f532a11cdfe80876dcd26bc8fffea1e8bd06"}}