{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5PDPJFTHHMMOUJSZ3BDDQUQ5ZF","short_pith_number":"pith:5PDPJFTH","canonical_record":{"source":{"id":"2104.00994","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-04-02T11:43:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"356897c711800a23439cdde859eb7a0276d003e42fe6f8ac8cbc2bfcd5e28667","abstract_canon_sha256":"bb98243c1b121994b5a668924b1a9d83c95a445d53b7b486cc3a390ff7610961"},"schema_version":"1.0"},"canonical_sha256":"ebc6f496673b18ea2659d84638521dc9790a3e84769f28804509e4b9a6ae31df","source":{"kind":"arxiv","id":"2104.00994","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00994","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00994v2","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00994","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_12","alias_value":"5PDPJFTHHMMO","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_16","alias_value":"5PDPJFTHHMMOUJSZ","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_8","alias_value":"5PDPJFTH","created_at":"2026-07-05T02:46:45Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5PDPJFTHHMMOUJSZ3BDDQUQ5ZF","target":"record","payload":{"canonical_record":{"source":{"id":"2104.00994","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-04-02T11:43:07Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"356897c711800a23439cdde859eb7a0276d003e42fe6f8ac8cbc2bfcd5e28667","abstract_canon_sha256":"bb98243c1b121994b5a668924b1a9d83c95a445d53b7b486cc3a390ff7610961"},"schema_version":"1.0"},"canonical_sha256":"ebc6f496673b18ea2659d84638521dc9790a3e84769f28804509e4b9a6ae31df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:46:45.324781Z","signature_b64":"rdmXmGgUbKsb/7AINP2CZSiNO3iyZDsxgKC9BOSrkUdddrhhbkrf2mWauca+J5g6jDZ1FFRcrf1eMbR6DMn1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebc6f496673b18ea2659d84638521dc9790a3e84769f28804509e4b9a6ae31df","last_reissued_at":"2026-07-05T02:46:45.324410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:46:45.324410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2104.00994","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":"2026-07-05T02:46:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c9TTbMtqgneNbjMAMBT9thkuXtrYECkYHhuN1e8r0o8GWwKDdebo4C8X524Bd2ZQSHAcsr97OEq/9PrPt32QDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:14:44.710982Z"},"content_sha256":"bed4e8c6322361023573fecd041e7105a677ec4d165906927b88f66bc4b09941","schema_version":"1.0","event_id":"sha256:bed4e8c6322361023573fecd041e7105a677ec4d165906927b88f66bc4b09941"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5PDPJFTHHMMOUJSZ3BDDQUQ5ZF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Laureano Moro-Vel\\'azquez, Odette Scharenborg, Piotr \\.Zelasko, Siyuan Feng","submitted_at":"2021-04-02T11:43:07Z","abstract_excerpt":"This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stage approach: the first stage learns a subword-discriminative feature representation and the second stage applies clustering to the learned representation and obtains phone-like clusters as the discovered acoustic units. In the first stage, a recently proposed method in the task of unsupervised subword modeling is improved by replacing a monolingual out-of-domain (OOD) ASR system with a multilingual one to create a sub"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00994","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/2104.00994/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":"2026-07-05T02:46:45Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UyAc7zgIEY4lorfe6kaVBrUN6nu9DD1O575DHWrQYL6qWl5NTlII3qDbIpw718CeGgQVBc6c+wHNKnsygj/wDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:14:44.711362Z"},"content_sha256":"c7721f3d8a87ad2f8da6ae1ffc7a5d30cd59d012103b808866dce53730062c4b","schema_version":"1.0","event_id":"sha256:c7721f3d8a87ad2f8da6ae1ffc7a5d30cd59d012103b808866dce53730062c4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5PDPJFTHHMMOUJSZ3BDDQUQ5ZF/bundle.json","state_url":"https://pith.science/pith/5PDPJFTHHMMOUJSZ3BDDQUQ5ZF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5PDPJFTHHMMOUJSZ3BDDQUQ5ZF/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":"2026-07-06T16:14:44Z","links":{"resolver":"https://pith.science/pith/5PDPJFTHHMMOUJSZ3BDDQUQ5ZF","bundle":"https://pith.science/pith/5PDPJFTHHMMOUJSZ3BDDQUQ5ZF/bundle.json","state":"https://pith.science/pith/5PDPJFTHHMMOUJSZ3BDDQUQ5ZF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5PDPJFTHHMMOUJSZ3BDDQUQ5ZF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5PDPJFTHHMMOUJSZ3BDDQUQ5ZF","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":"bb98243c1b121994b5a668924b1a9d83c95a445d53b7b486cc3a390ff7610961","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-04-02T11:43:07Z","title_canon_sha256":"356897c711800a23439cdde859eb7a0276d003e42fe6f8ac8cbc2bfcd5e28667"},"schema_version":"1.0","source":{"id":"2104.00994","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2104.00994","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"arxiv_version","alias_value":"2104.00994v2","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2104.00994","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_12","alias_value":"5PDPJFTHHMMO","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_16","alias_value":"5PDPJFTHHMMOUJSZ","created_at":"2026-07-05T02:46:45Z"},{"alias_kind":"pith_short_8","alias_value":"5PDPJFTH","created_at":"2026-07-05T02:46:45Z"}],"graph_snapshots":[{"event_id":"sha256:c7721f3d8a87ad2f8da6ae1ffc7a5d30cd59d012103b808866dce53730062c4b","target":"graph","created_at":"2026-07-05T02:46:45Z","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/2104.00994/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper tackles automatically discovering phone-like acoustic units (AUD) from unlabeled speech data. Past studies usually proposed single-step approaches. We propose a two-stage approach: the first stage learns a subword-discriminative feature representation and the second stage applies clustering to the learned representation and obtains phone-like clusters as the discovered acoustic units. In the first stage, a recently proposed method in the task of unsupervised subword modeling is improved by replacing a monolingual out-of-domain (OOD) ASR system with a multilingual one to create a sub","authors_text":"Laureano Moro-Vel\\'azquez, Odette Scharenborg, Piotr \\.Zelasko, Siyuan Feng","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-04-02T11:43:07Z","title":"Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2104.00994","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:bed4e8c6322361023573fecd041e7105a677ec4d165906927b88f66bc4b09941","target":"record","created_at":"2026-07-05T02:46:45Z","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":"bb98243c1b121994b5a668924b1a9d83c95a445d53b7b486cc3a390ff7610961","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2021-04-02T11:43:07Z","title_canon_sha256":"356897c711800a23439cdde859eb7a0276d003e42fe6f8ac8cbc2bfcd5e28667"},"schema_version":"1.0","source":{"id":"2104.00994","kind":"arxiv","version":2}},"canonical_sha256":"ebc6f496673b18ea2659d84638521dc9790a3e84769f28804509e4b9a6ae31df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ebc6f496673b18ea2659d84638521dc9790a3e84769f28804509e4b9a6ae31df","first_computed_at":"2026-07-05T02:46:45.324410Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:46:45.324410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rdmXmGgUbKsb/7AINP2CZSiNO3iyZDsxgKC9BOSrkUdddrhhbkrf2mWauca+J5g6jDZ1FFRcrf1eMbR6DMn1Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T02:46:45.324781Z","signed_message":"canonical_sha256_bytes"},"source_id":"2104.00994","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bed4e8c6322361023573fecd041e7105a677ec4d165906927b88f66bc4b09941","sha256:c7721f3d8a87ad2f8da6ae1ffc7a5d30cd59d012103b808866dce53730062c4b"],"state_sha256":"356edd2851dcf2f73c5c2ee6cff814e73a99f33b56bae62cdd21debd918be094"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NL+lk6paPxGEe+nx8l9EMyRsS5CAubjasJ/aA7d7U1+lvTEesVqmqqCDUFYUOAwBY3XoqrAqJyd79IOgUoKSAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:14:44.713662Z","bundle_sha256":"c310ed542437a0acec92629d20af5d7dd23945f311f641544d7f8ec9a2dea65e"}}