{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:XFLM6AKG72JOGRM6CBTBCPSNTH","short_pith_number":"pith:XFLM6AKG","canonical_record":{"source":{"id":"2411.14100","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T13:05:18Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"1d6189ae1876a47bfbc836003c608de448d4b43ec989aa963400c82c16e5be22","abstract_canon_sha256":"f78ec772ecb8887c1f1924503921022e628547747b992727cc491afcc67e88a4"},"schema_version":"1.0"},"canonical_sha256":"b956cf0146fe92e3459e1066113e4d99e9c4d6d50b6fe3da2dc8bd1feb5c66e1","source":{"kind":"arxiv","id":"2411.14100","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14100","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14100v2","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14100","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"pith_short_12","alias_value":"XFLM6AKG72JO","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"pith_short_16","alias_value":"XFLM6AKG72JOGRM6","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"pith_short_8","alias_value":"XFLM6AKG","created_at":"2026-07-05T09:53:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:XFLM6AKG72JOGRM6CBTBCPSNTH","target":"record","payload":{"canonical_record":{"source":{"id":"2411.14100","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T13:05:18Z","cross_cats_sorted":["cs.CL","cs.IR"],"title_canon_sha256":"1d6189ae1876a47bfbc836003c608de448d4b43ec989aa963400c82c16e5be22","abstract_canon_sha256":"f78ec772ecb8887c1f1924503921022e628547747b992727cc491afcc67e88a4"},"schema_version":"1.0"},"canonical_sha256":"b956cf0146fe92e3459e1066113e4d99e9c4d6d50b6fe3da2dc8bd1feb5c66e1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:53:07.699004Z","signature_b64":"uKGoJrDIcE0nAX1gx+ThGEFXG+mk6FzTWOcOxuw3RycwLp6uUzW4K5uPPIIeguZlvVGxDBXFUTX22rQ8Wi1TBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b956cf0146fe92e3459e1066113e4d99e9c4d6d50b6fe3da2dc8bd1feb5c66e1","last_reissued_at":"2026-07-05T09:53:07.698534Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:53:07.698534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.14100","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:53:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PAp6pjS7otWEqpMke9i+yiBpuUO5erj+6THMZJs05OScxfVEIN/bH+QoLDTEyQVM1Cg4jqKrJSWRmt503j9IDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:04:49.544100Z"},"content_sha256":"11ab0e04879148035acdd0ecbe4934444daa680d473bf108c0f8b07fa98e8691","schema_version":"1.0","event_id":"sha256:11ab0e04879148035acdd0ecbe4934444daa680d473bf108c0f8b07fa98e8691"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:XFLM6AKG72JOGRM6CBTBCPSNTH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.IR"],"primary_cat":"eess.AS","authors_text":"Anup Singh, Kris Demuynck, Vipul Arora","submitted_at":"2024-11-21T13:05:18Z","abstract_excerpt":"Spoken term detection (STD) is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching, limiting its practicality. To address these challenges, we propose a novel approach that encodes speech into discrete, speaker-agnostic semantic tokens. This facilitates fast retrieval using text-based search algorithms and effectively handles out-of-vocabulary terms. Our approach focuses on generating consistent token sequences across varying utterances of the same term. We also propose a bidirectional state space modeling within the Mamba encoder, t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14100","kind":"arxiv","version":2},"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/2411.14100/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":"2026-07-05T09:53:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+B8ZlRvOt0qa7F0bRtsV+FNob7C1bJp3Q4RcI7A1ogvbfZSrD7SMaYPTUDQGmz9N9klx6LFho0M6TTpAjQJUDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T13:04:49.544608Z"},"content_sha256":"0b5b0966e1adf8d1dce7c7b0a8bdbfc562b6ec48d84bd8820040442b6d7d27e7","schema_version":"1.0","event_id":"sha256:0b5b0966e1adf8d1dce7c7b0a8bdbfc562b6ec48d84bd8820040442b6d7d27e7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/bundle.json","state_url":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/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":"2026-08-11T13:04:49Z","links":{"resolver":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH","bundle":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/bundle.json","state":"https://pith.science/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XFLM6AKG72JOGRM6CBTBCPSNTH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:XFLM6AKG72JOGRM6CBTBCPSNTH","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":"f78ec772ecb8887c1f1924503921022e628547747b992727cc491afcc67e88a4","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T13:05:18Z","title_canon_sha256":"1d6189ae1876a47bfbc836003c608de448d4b43ec989aa963400c82c16e5be22"},"schema_version":"1.0","source":{"id":"2411.14100","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.14100","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"arxiv_version","alias_value":"2411.14100v2","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.14100","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"pith_short_12","alias_value":"XFLM6AKG72JO","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"pith_short_16","alias_value":"XFLM6AKG72JOGRM6","created_at":"2026-07-05T09:53:07Z"},{"alias_kind":"pith_short_8","alias_value":"XFLM6AKG","created_at":"2026-07-05T09:53:07Z"}],"graph_snapshots":[{"event_id":"sha256:0b5b0966e1adf8d1dce7c7b0a8bdbfc562b6ec48d84bd8820040442b6d7d27e7","target":"graph","created_at":"2026-07-05T09:53:07Z","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/2411.14100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken term detection (STD) is often hindered by reliance on frame-level features and the computationally intensive DTW-based template matching, limiting its practicality. To address these challenges, we propose a novel approach that encodes speech into discrete, speaker-agnostic semantic tokens. This facilitates fast retrieval using text-based search algorithms and effectively handles out-of-vocabulary terms. Our approach focuses on generating consistent token sequences across varying utterances of the same term. We also propose a bidirectional state space modeling within the Mamba encoder, t","authors_text":"Anup Singh, Kris Demuynck, Vipul Arora","cross_cats":["cs.CL","cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T13:05:18Z","title":"BEST-STD: Bidirectional Mamba-Enhanced Speech Tokenization for Spoken Term Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.14100","kind":"arxiv","version":2},"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":"sha256:11ab0e04879148035acdd0ecbe4934444daa680d473bf108c0f8b07fa98e8691","target":"record","created_at":"2026-07-05T09:53:07Z","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":"f78ec772ecb8887c1f1924503921022e628547747b992727cc491afcc67e88a4","cross_cats_sorted":["cs.CL","cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-11-21T13:05:18Z","title_canon_sha256":"1d6189ae1876a47bfbc836003c608de448d4b43ec989aa963400c82c16e5be22"},"schema_version":"1.0","source":{"id":"2411.14100","kind":"arxiv","version":2}},"canonical_sha256":"b956cf0146fe92e3459e1066113e4d99e9c4d6d50b6fe3da2dc8bd1feb5c66e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b956cf0146fe92e3459e1066113e4d99e9c4d6d50b6fe3da2dc8bd1feb5c66e1","first_computed_at":"2026-07-05T09:53:07.698534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:53:07.698534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uKGoJrDIcE0nAX1gx+ThGEFXG+mk6FzTWOcOxuw3RycwLp6uUzW4K5uPPIIeguZlvVGxDBXFUTX22rQ8Wi1TBw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:53:07.699004Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.14100","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:11ab0e04879148035acdd0ecbe4934444daa680d473bf108c0f8b07fa98e8691","sha256:0b5b0966e1adf8d1dce7c7b0a8bdbfc562b6ec48d84bd8820040442b6d7d27e7"],"state_sha256":"79550f548803469e36196aca75b1c4b7c97f49515f4e9b9a61f1de6e33e320e0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"55jdMiPL35TNNKCSp7eZq/5DRWx7MeqgGm1OkBXeKGo3UhrDKIYH3k0w/VY0kqCDJRnqfXTY7Scs4ViCKGMtAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T13:04:49.548466Z","bundle_sha256":"36e539cec5651cf517f01aaf6af8e363ecb89fa2b29ce9eea6ea1f3c60811c1a"}}