{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:4TJ4NPTXB57NIIZW4NVWU7ENKF","short_pith_number":"pith:4TJ4NPTX","canonical_record":{"source":{"id":"1703.07476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T00:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"d9a6914fd9d23b454ba14ee677a3f9804e233e1aadd7ee2050b1ac2409f38b66","abstract_canon_sha256":"45f16afd5fce8646f4b296a894aab958c129ac82f11e1f318c4644038442d1c2"},"schema_version":"1.0"},"canonical_sha256":"e4d3c6be770f7ed42336e36b6a7c8d51608b787ba5471329f420d891327cdace","source":{"kind":"arxiv","id":"1703.07476","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07476","created_at":"2026-05-18T00:40:30Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07476v2","created_at":"2026-05-18T00:40:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07476","created_at":"2026-05-18T00:40:30Z"},{"alias_kind":"pith_short_12","alias_value":"4TJ4NPTXB57N","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4TJ4NPTXB57NIIZW","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4TJ4NPTX","created_at":"2026-05-18T12:31:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:4TJ4NPTXB57NIIZW4NVWU7ENKF","target":"record","payload":{"canonical_record":{"source":{"id":"1703.07476","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T00:37:33Z","cross_cats_sorted":[],"title_canon_sha256":"d9a6914fd9d23b454ba14ee677a3f9804e233e1aadd7ee2050b1ac2409f38b66","abstract_canon_sha256":"45f16afd5fce8646f4b296a894aab958c129ac82f11e1f318c4644038442d1c2"},"schema_version":"1.0"},"canonical_sha256":"e4d3c6be770f7ed42336e36b6a7c8d51608b787ba5471329f420d891327cdace","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:40:30.406470Z","signature_b64":"FWxbjYE7ZdcKxbhtjetCCASC/cR+ndICc3WCnAW0PZeB4JNY15U4MXVkX4gJiLnpkf2BcPWhkS8hufo/0rttDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4d3c6be770f7ed42336e36b6a7c8d51608b787ba5471329f420d891327cdace","last_reissued_at":"2026-05-18T00:40:30.405930Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:40:30.405930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1703.07476","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":"2026-05-18T00:40:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EkoHAx8bdmPVoKD2W8Fvqc1I0N6VEsAKnZvUBIzT3cwFedbPLm17kNmbBnqL/L7gf6bf3spMAf1pa2W1uUnBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:38:01.855986Z"},"content_sha256":"16c786243b280aa027aea01aa1ed116f2252aeeb1b82f51179d6f541068e2602","schema_version":"1.0","event_id":"sha256:16c786243b280aa027aea01aa1ed116f2252aeeb1b82f51179d6f541068e2602"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:4TJ4NPTXB57NIIZW4NVWU7ENKF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Topic Identification for Speech without ASR","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chunxi Liu, Craig Harman, Jan Trmal, Matthew Wiesner, Sanjeev Khudanpur","submitted_at":"2017-03-22T00:37:33Z","abstract_excerpt":"Modern topic identification (topic ID) systems for speech use automatic speech recognition (ASR) to produce speech transcripts, and perform supervised classification on such ASR outputs. However, under resource-limited conditions, the manually transcribed speech required to develop standard ASR systems can be severely limited or unavailable. In this paper, we investigate alternative unsupervised solutions to obtaining tokenizations of speech in terms of a vocabulary of automatically discovered word-like or phoneme-like units, without depending on the supervised training of ASR systems. Moreove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07476","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":""},"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":"2026-05-18T00:40:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Jz9M26XTS0Z3X3u2zkxqYU4lPgaLt2xJe+K8R0OLxFTPWH85F2xh0hyNoPOF4K2roNHHtl5RK6BIU05zKvmwCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T01:38:01.856639Z"},"content_sha256":"17b587dbb98f3ac3664a06fbed170ace68f949332adeb2c8185d6bb0b6a20fa3","schema_version":"1.0","event_id":"sha256:17b587dbb98f3ac3664a06fbed170ace68f949332adeb2c8185d6bb0b6a20fa3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4TJ4NPTXB57NIIZW4NVWU7ENKF/bundle.json","state_url":"https://pith.science/pith/4TJ4NPTXB57NIIZW4NVWU7ENKF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4TJ4NPTXB57NIIZW4NVWU7ENKF/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":"2026-05-27T01:38:01Z","links":{"resolver":"https://pith.science/pith/4TJ4NPTXB57NIIZW4NVWU7ENKF","bundle":"https://pith.science/pith/4TJ4NPTXB57NIIZW4NVWU7ENKF/bundle.json","state":"https://pith.science/pith/4TJ4NPTXB57NIIZW4NVWU7ENKF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4TJ4NPTXB57NIIZW4NVWU7ENKF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:4TJ4NPTXB57NIIZW4NVWU7ENKF","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":"45f16afd5fce8646f4b296a894aab958c129ac82f11e1f318c4644038442d1c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T00:37:33Z","title_canon_sha256":"d9a6914fd9d23b454ba14ee677a3f9804e233e1aadd7ee2050b1ac2409f38b66"},"schema_version":"1.0","source":{"id":"1703.07476","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1703.07476","created_at":"2026-05-18T00:40:30Z"},{"alias_kind":"arxiv_version","alias_value":"1703.07476v2","created_at":"2026-05-18T00:40:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1703.07476","created_at":"2026-05-18T00:40:30Z"},{"alias_kind":"pith_short_12","alias_value":"4TJ4NPTXB57N","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"4TJ4NPTXB57NIIZW","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"4TJ4NPTX","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:17b587dbb98f3ac3664a06fbed170ace68f949332adeb2c8185d6bb0b6a20fa3","target":"graph","created_at":"2026-05-18T00:40:30Z","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"},"paper":{"abstract_excerpt":"Modern topic identification (topic ID) systems for speech use automatic speech recognition (ASR) to produce speech transcripts, and perform supervised classification on such ASR outputs. However, under resource-limited conditions, the manually transcribed speech required to develop standard ASR systems can be severely limited or unavailable. In this paper, we investigate alternative unsupervised solutions to obtaining tokenizations of speech in terms of a vocabulary of automatically discovered word-like or phoneme-like units, without depending on the supervised training of ASR systems. Moreove","authors_text":"Chunxi Liu, Craig Harman, Jan Trmal, Matthew Wiesner, Sanjeev Khudanpur","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T00:37:33Z","title":"Topic Identification for Speech without ASR"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1703.07476","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":"sha256:16c786243b280aa027aea01aa1ed116f2252aeeb1b82f51179d6f541068e2602","target":"record","created_at":"2026-05-18T00:40:30Z","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":"45f16afd5fce8646f4b296a894aab958c129ac82f11e1f318c4644038442d1c2","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-03-22T00:37:33Z","title_canon_sha256":"d9a6914fd9d23b454ba14ee677a3f9804e233e1aadd7ee2050b1ac2409f38b66"},"schema_version":"1.0","source":{"id":"1703.07476","kind":"arxiv","version":2}},"canonical_sha256":"e4d3c6be770f7ed42336e36b6a7c8d51608b787ba5471329f420d891327cdace","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e4d3c6be770f7ed42336e36b6a7c8d51608b787ba5471329f420d891327cdace","first_computed_at":"2026-05-18T00:40:30.405930Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:40:30.405930Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FWxbjYE7ZdcKxbhtjetCCASC/cR+ndICc3WCnAW0PZeB4JNY15U4MXVkX4gJiLnpkf2BcPWhkS8hufo/0rttDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:40:30.406470Z","signed_message":"canonical_sha256_bytes"},"source_id":"1703.07476","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:16c786243b280aa027aea01aa1ed116f2252aeeb1b82f51179d6f541068e2602","sha256:17b587dbb98f3ac3664a06fbed170ace68f949332adeb2c8185d6bb0b6a20fa3"],"state_sha256":"9e96838b8d21890dbadf9331f584e9a2dd1dc97b6c4465498caa389fba79cac2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"khBrz50Sg2BZme7vxiG425CsXq0a0BWZ+Ob4cXjLa2Diw3mutyHjWjJZP871zEPUUsl8Sc6N6XnOcav9vWiXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T01:38:01.859877Z","bundle_sha256":"72227cffee29be0afe0d85643798b0b6667952cf0ecec47c858f6fe4795a3297"}}