{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:CSALTPIHNOKE3MO4IXJ2FS62LQ","short_pith_number":"pith:CSALTPIH","canonical_record":{"source":{"id":"2011.06226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-12T06:41:27Z","cross_cats_sorted":[],"title_canon_sha256":"4f59a825008e1818987757070e702660a18c53d02b5f0c0bf59aad844d51c264","abstract_canon_sha256":"7affc77c36414491d855dfa6ceee7ea1e46745bcb1de390b1ecc8b382cb0a889"},"schema_version":"1.0"},"canonical_sha256":"1480b9bd076b944db1dc45d3a2cbda5c38a6b815b6e18a84273b4058d4a62b65","source":{"kind":"arxiv","id":"2011.06226","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06226","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06226v1","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06226","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"pith_short_12","alias_value":"CSALTPIHNOKE","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"pith_short_16","alias_value":"CSALTPIHNOKE3MO4","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"pith_short_8","alias_value":"CSALTPIH","created_at":"2026-07-05T01:51:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:CSALTPIHNOKE3MO4IXJ2FS62LQ","target":"record","payload":{"canonical_record":{"source":{"id":"2011.06226","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-12T06:41:27Z","cross_cats_sorted":[],"title_canon_sha256":"4f59a825008e1818987757070e702660a18c53d02b5f0c0bf59aad844d51c264","abstract_canon_sha256":"7affc77c36414491d855dfa6ceee7ea1e46745bcb1de390b1ecc8b382cb0a889"},"schema_version":"1.0"},"canonical_sha256":"1480b9bd076b944db1dc45d3a2cbda5c38a6b815b6e18a84273b4058d4a62b65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:13.286119Z","signature_b64":"I6yslyO3jGu9xHdSZn5+0HDvItKWhBFKc/by5ytPxLNHMcIA7vFsTLPRB/0NLQya2imveH4fdu5dP+Gc8WXVAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1480b9bd076b944db1dc45d3a2cbda5c38a6b815b6e18a84273b4058d4a62b65","last_reissued_at":"2026-07-05T01:51:13.285734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:13.285734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.06226","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":"2026-07-05T01:51:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"T1bNODAxMMBKktXcYTfQVk8O5IqPkEjZM8+fiivPZL/e+haqcxgaLwQzMh6bv7DEpm9ID2yMj+bOE374ipCwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:33:59.842273Z"},"content_sha256":"440d5b4b258e3acc7296dda5b4dac440a3e23cc99cf7f946a05070ea9e6b6b85","schema_version":"1.0","event_id":"sha256:440d5b4b258e3acc7296dda5b4dac440a3e23cc99cf7f946a05070ea9e6b6b85"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:CSALTPIHNOKE3MO4IXJ2FS62LQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Cross-lingual and Multilingual Spoken Term Detection for Low-Resource Indian Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Sanket Shah, Satarupa Guha, Simran Khanuja, Sunayana Sitaram","submitted_at":"2020-11-12T06:41:27Z","abstract_excerpt":"Spoken Term Detection (STD) is the task of searching for words or phrases within audio, given either text or spoken input as a query. In this work, we use state-of-the-art Hindi, Tamil and Telugu ASR systems cross-lingually for lexical Spoken Term Detection in ten low-resource Indian languages. Since no publicly available dataset exists for Spoken Term Detection in these languages, we create a new dataset using a publicly available TTS dataset. We report a standard metric for STD, Mean Term Weighted Value (MTWV) and show that ASR systems built in languages that are phonetically similar to the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06226","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/2011.06226/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":"2026-07-05T01:51:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y5b1NKxVQIuuEGIlhFah6Gep+twzb5AZ7Sw3Q45H+H8T41/xbLSj/VQ8QUq5S9Z9wksl4QjxOVH4nCHADNOzDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T07:33:59.842936Z"},"content_sha256":"70c7966a8d11c6ed6a70d36658d4c3e60926d9e6798478a5bf1badf0a6e4b99c","schema_version":"1.0","event_id":"sha256:70c7966a8d11c6ed6a70d36658d4c3e60926d9e6798478a5bf1badf0a6e4b99c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/bundle.json","state_url":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/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":"2026-07-09T07:33:59Z","links":{"resolver":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ","bundle":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/bundle.json","state":"https://pith.science/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CSALTPIHNOKE3MO4IXJ2FS62LQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:CSALTPIHNOKE3MO4IXJ2FS62LQ","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":"7affc77c36414491d855dfa6ceee7ea1e46745bcb1de390b1ecc8b382cb0a889","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-12T06:41:27Z","title_canon_sha256":"4f59a825008e1818987757070e702660a18c53d02b5f0c0bf59aad844d51c264"},"schema_version":"1.0","source":{"id":"2011.06226","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.06226","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"arxiv_version","alias_value":"2011.06226v1","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.06226","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"pith_short_12","alias_value":"CSALTPIHNOKE","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"pith_short_16","alias_value":"CSALTPIHNOKE3MO4","created_at":"2026-07-05T01:51:13Z"},{"alias_kind":"pith_short_8","alias_value":"CSALTPIH","created_at":"2026-07-05T01:51:13Z"}],"graph_snapshots":[{"event_id":"sha256:70c7966a8d11c6ed6a70d36658d4c3e60926d9e6798478a5bf1badf0a6e4b99c","target":"graph","created_at":"2026-07-05T01:51:13Z","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/2011.06226/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken Term Detection (STD) is the task of searching for words or phrases within audio, given either text or spoken input as a query. In this work, we use state-of-the-art Hindi, Tamil and Telugu ASR systems cross-lingually for lexical Spoken Term Detection in ten low-resource Indian languages. Since no publicly available dataset exists for Spoken Term Detection in these languages, we create a new dataset using a publicly available TTS dataset. We report a standard metric for STD, Mean Term Weighted Value (MTWV) and show that ASR systems built in languages that are phonetically similar to the ","authors_text":"Sanket Shah, Satarupa Guha, Simran Khanuja, Sunayana Sitaram","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-12T06:41:27Z","title":"Cross-lingual and Multilingual Spoken Term Detection for Low-Resource Indian Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.06226","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":"sha256:440d5b4b258e3acc7296dda5b4dac440a3e23cc99cf7f946a05070ea9e6b6b85","target":"record","created_at":"2026-07-05T01:51:13Z","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":"7affc77c36414491d855dfa6ceee7ea1e46745bcb1de390b1ecc8b382cb0a889","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-12T06:41:27Z","title_canon_sha256":"4f59a825008e1818987757070e702660a18c53d02b5f0c0bf59aad844d51c264"},"schema_version":"1.0","source":{"id":"2011.06226","kind":"arxiv","version":1}},"canonical_sha256":"1480b9bd076b944db1dc45d3a2cbda5c38a6b815b6e18a84273b4058d4a62b65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1480b9bd076b944db1dc45d3a2cbda5c38a6b815b6e18a84273b4058d4a62b65","first_computed_at":"2026-07-05T01:51:13.285734Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:13.285734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"I6yslyO3jGu9xHdSZn5+0HDvItKWhBFKc/by5ytPxLNHMcIA7vFsTLPRB/0NLQya2imveH4fdu5dP+Gc8WXVAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:13.286119Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.06226","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:440d5b4b258e3acc7296dda5b4dac440a3e23cc99cf7f946a05070ea9e6b6b85","sha256:70c7966a8d11c6ed6a70d36658d4c3e60926d9e6798478a5bf1badf0a6e4b99c"],"state_sha256":"b3f2e8f4b6d4f76653a7dcfec2c72ad868092abf714dfde25d6a843eee342378"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UTb8FdaU0zrKMjx2zqolSp5dxXF9zMMQ1MUVsx9G8X0Km0spWtVTinLK5xk5BsWcRlhWVqFaVgG6svIks8ERDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T07:33:59.846694Z","bundle_sha256":"4815f86d2d98e99576a6295b2cfb1f546308f20e9d9355e17c936232282a4c99"}}