{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZYRWG4C7KD37J4R4NITG5K5S27","short_pith_number":"pith:ZYRWG4C7","canonical_record":{"source":{"id":"2401.17902","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-31T15:06:34Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"b0ba15817f41fc7ebcdea4a3525f9fcc80ef5f4c9571476b6f9e976bdc5b9af9","abstract_canon_sha256":"5d888b5e6e087a65094be4d84b9880dcc20bff2cddbabb188ade379b762eefa6"},"schema_version":"1.0"},"canonical_sha256":"ce2363705f50f7f4f23c6a266eabb2d7f6314eb300e880d54f5b01162f57b721","source":{"kind":"arxiv","id":"2401.17902","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17902","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17902v1","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17902","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZYRWG4C7KD37","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZYRWG4C7KD37J4R4","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZYRWG4C7","created_at":"2026-07-05T07:39:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZYRWG4C7KD37J4R4NITG5K5S27","target":"record","payload":{"canonical_record":{"source":{"id":"2401.17902","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-31T15:06:34Z","cross_cats_sorted":["cs.CL","cs.SD"],"title_canon_sha256":"b0ba15817f41fc7ebcdea4a3525f9fcc80ef5f4c9571476b6f9e976bdc5b9af9","abstract_canon_sha256":"5d888b5e6e087a65094be4d84b9880dcc20bff2cddbabb188ade379b762eefa6"},"schema_version":"1.0"},"canonical_sha256":"ce2363705f50f7f4f23c6a266eabb2d7f6314eb300e880d54f5b01162f57b721","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:39:44.133840Z","signature_b64":"9pG1rEcIAmGFz65WHTszu4mdVn2KageWOA9QnOE5CkI8kqBryHzljl4WISLyhJvjA29D/Mkoh6xXMRfdYL6eDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce2363705f50f7f4f23c6a266eabb2d7f6314eb300e880d54f5b01162f57b721","last_reissued_at":"2026-07-05T07:39:44.133393Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:39:44.133393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.17902","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":"2026-07-05T07:39:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0PHq0TpzwN5DbVRG7f6BuGueO2j7FrBOnED5Jtxr/l8pkl8Cej4UGiA3TkKF624LNirkGIbD2VSSwXzHb+yxDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:06:16.544969Z"},"content_sha256":"ab1992b6c6488e8ece33d995ec2bc57e782f8e59228c6016cf7c9b37768291f7","schema_version":"1.0","event_id":"sha256:ab1992b6c6488e8ece33d995ec2bc57e782f8e59228c6016cf7c9b37768291f7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZYRWG4C7KD37J4R4NITG5K5S27","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting speech segmentation and lexicon learning with better features","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.SD"],"primary_cat":"eess.AS","authors_text":"Benjamin van Niekerk, Herman Kamper","submitted_at":"2024-01-31T15:06:34Z","abstract_excerpt":"We revisit a self-supervised method that segments unlabelled speech into word-like segments. We start from the two-stage duration-penalised dynamic programming method that performs zero-resource segmentation without learning an explicit lexicon. In the first acoustic unit discovery stage, we replace contrastive predictive coding features with HuBERT. After word segmentation in the second stage, we get an acoustic word embedding for each segment by averaging HuBERT features. These embeddings are clustered using K-means to get a lexicon. The result is good full-coverage segmentation with a lexic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17902","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/2401.17902/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":"2026-07-05T07:39:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ct1XGzqietDer8+IjpQZs1NKMhtaaNvgw1B/6I0cpG1sYHwKffFNs8Xx9Q8Hyk/R38hDLntGp5mMg9PWdEl0Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T19:06:16.545500Z"},"content_sha256":"e172517b2c372db496fd583c9ba0928a4c8a098acb2a7fe17378c8295cb03c63","schema_version":"1.0","event_id":"sha256:e172517b2c372db496fd583c9ba0928a4c8a098acb2a7fe17378c8295cb03c63"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZYRWG4C7KD37J4R4NITG5K5S27/bundle.json","state_url":"https://pith.science/pith/ZYRWG4C7KD37J4R4NITG5K5S27/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZYRWG4C7KD37J4R4NITG5K5S27/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":"2026-08-21T19:06:16Z","links":{"resolver":"https://pith.science/pith/ZYRWG4C7KD37J4R4NITG5K5S27","bundle":"https://pith.science/pith/ZYRWG4C7KD37J4R4NITG5K5S27/bundle.json","state":"https://pith.science/pith/ZYRWG4C7KD37J4R4NITG5K5S27/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZYRWG4C7KD37J4R4NITG5K5S27/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZYRWG4C7KD37J4R4NITG5K5S27","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":"5d888b5e6e087a65094be4d84b9880dcc20bff2cddbabb188ade379b762eefa6","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-31T15:06:34Z","title_canon_sha256":"b0ba15817f41fc7ebcdea4a3525f9fcc80ef5f4c9571476b6f9e976bdc5b9af9"},"schema_version":"1.0","source":{"id":"2401.17902","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.17902","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"arxiv_version","alias_value":"2401.17902v1","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.17902","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"pith_short_12","alias_value":"ZYRWG4C7KD37","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"pith_short_16","alias_value":"ZYRWG4C7KD37J4R4","created_at":"2026-07-05T07:39:44Z"},{"alias_kind":"pith_short_8","alias_value":"ZYRWG4C7","created_at":"2026-07-05T07:39:44Z"}],"graph_snapshots":[{"event_id":"sha256:e172517b2c372db496fd583c9ba0928a4c8a098acb2a7fe17378c8295cb03c63","target":"graph","created_at":"2026-07-05T07:39:44Z","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/2401.17902/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We revisit a self-supervised method that segments unlabelled speech into word-like segments. We start from the two-stage duration-penalised dynamic programming method that performs zero-resource segmentation without learning an explicit lexicon. In the first acoustic unit discovery stage, we replace contrastive predictive coding features with HuBERT. After word segmentation in the second stage, we get an acoustic word embedding for each segment by averaging HuBERT features. These embeddings are clustered using K-means to get a lexicon. The result is good full-coverage segmentation with a lexic","authors_text":"Benjamin van Niekerk, Herman Kamper","cross_cats":["cs.CL","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-31T15:06:34Z","title":"Revisiting speech segmentation and lexicon learning with better features"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.17902","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:ab1992b6c6488e8ece33d995ec2bc57e782f8e59228c6016cf7c9b37768291f7","target":"record","created_at":"2026-07-05T07:39:44Z","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":"5d888b5e6e087a65094be4d84b9880dcc20bff2cddbabb188ade379b762eefa6","cross_cats_sorted":["cs.CL","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-01-31T15:06:34Z","title_canon_sha256":"b0ba15817f41fc7ebcdea4a3525f9fcc80ef5f4c9571476b6f9e976bdc5b9af9"},"schema_version":"1.0","source":{"id":"2401.17902","kind":"arxiv","version":1}},"canonical_sha256":"ce2363705f50f7f4f23c6a266eabb2d7f6314eb300e880d54f5b01162f57b721","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ce2363705f50f7f4f23c6a266eabb2d7f6314eb300e880d54f5b01162f57b721","first_computed_at":"2026-07-05T07:39:44.133393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:39:44.133393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9pG1rEcIAmGFz65WHTszu4mdVn2KageWOA9QnOE5CkI8kqBryHzljl4WISLyhJvjA29D/Mkoh6xXMRfdYL6eDw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:39:44.133840Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.17902","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab1992b6c6488e8ece33d995ec2bc57e782f8e59228c6016cf7c9b37768291f7","sha256:e172517b2c372db496fd583c9ba0928a4c8a098acb2a7fe17378c8295cb03c63"],"state_sha256":"76f336a099b0df53c5153f06efa88ca32aaba70b5d0c83f94f86c92a53a4e92b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/uGit3YQJIGyPiNtnaAzjvawbCuLjH16sJQQoe9c87Tt/Oomu/99YIxNTi2/ZPlc6CN5iIxN9EV/WwrcB2CUDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T19:06:16.549702Z","bundle_sha256":"56b47d541207ec65b7d7cc0b132182dd404fefce2c6b2dd8116002e2dcf957f4"}}