{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QS4U53RZK7UKJQXSKVJXJAVUHW","short_pith_number":"pith:QS4U53RZ","canonical_record":{"source":{"id":"2204.13094","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-27T17:43:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3e9bc0cc4e31c37ca76eeab420da34cbee011f5c3bdd50c2bdaada2bb5c4d9eb","abstract_canon_sha256":"f424a82ed085852fb5aaae9a35fb7b732edb1af33bcd5fbb2a3d6b77cd592f60"},"schema_version":"1.0"},"canonical_sha256":"84b94eee3957e8a4c2f255537482b43d8f6c59419f2497358f9cbb3c402e906f","source":{"kind":"arxiv","id":"2204.13094","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.13094","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2204.13094v1","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.13094","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"QS4U53RZK7UK","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"QS4U53RZK7UKJQXS","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"QS4U53RZ","created_at":"2026-07-05T04:18:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QS4U53RZK7UKJQXSKVJXJAVUHW","target":"record","payload":{"canonical_record":{"source":{"id":"2204.13094","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-27T17:43:50Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"3e9bc0cc4e31c37ca76eeab420da34cbee011f5c3bdd50c2bdaada2bb5c4d9eb","abstract_canon_sha256":"f424a82ed085852fb5aaae9a35fb7b732edb1af33bcd5fbb2a3d6b77cd592f60"},"schema_version":"1.0"},"canonical_sha256":"84b94eee3957e8a4c2f255537482b43d8f6c59419f2497358f9cbb3c402e906f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:18:25.784144Z","signature_b64":"8qN/PLycogkMdy552aoIbI74BBnkR4OuKHXXlykePqDa0shlf8ZnRAQk/zCqT803nBGMFry5lV3fjMJCC2EvCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"84b94eee3957e8a4c2f255537482b43d8f6c59419f2497358f9cbb3c402e906f","last_reissued_at":"2026-07-05T04:18:25.783741Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:18:25.783741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.13094","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":"2026-07-05T04:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sb1MrEV98uJDQwXieEL0PYguCnqfua3RuK/yeICn+JPhSEENptiIGvX1MC2d+5YMLygO28mkj7dOuGnqHtzDDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:59:53.481069Z"},"content_sha256":"2c5e4d12cd7f5e403feb5b7ccac1b7c7dd05ebfd491492fc28f3aaa80ae71e11","schema_version":"1.0","event_id":"sha256:2c5e4d12cd7f5e403feb5b7ccac1b7c7dd05ebfd491492fc28f3aaa80ae71e11"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QS4U53RZK7UKJQXSKVJXJAVUHW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Unsupervised Word Segmentation using K Nearest Neighbors","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Joseph Keshet, Tzeviya Sylvia Fuchs, Yedid Hoshen","submitted_at":"2022-04-27T17:43:50Z","abstract_excerpt":"In this paper, we propose an unsupervised kNN-based approach for word segmentation in speech utterances. Our method relies on self-supervised pre-trained speech representations, and compares each audio segment of a given utterance to its K nearest neighbors within the training set. Our main assumption is that a segment containing more than one word would occur less often than a segment containing a single word. Our method does not require phoneme discovery and is able to operate directly on pre-trained audio representations. This is in contrast to current methods that use a two-stage approach;"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.13094","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/2204.13094/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":"2026-07-05T04:18:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bqXgcIXOfXv2lhSpN0V9FgwPIdIjXVfthjkuTtdHwwBlwdmiC7QrNq9UYm6XRMZCk/OygD6aE4ipZUdPC+OmCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T13:59:53.481999Z"},"content_sha256":"5bc670f2bfd12013c0404b2d8cfa639d16acb4b8c2e789863b44f76bee0ec2de","schema_version":"1.0","event_id":"sha256:5bc670f2bfd12013c0404b2d8cfa639d16acb4b8c2e789863b44f76bee0ec2de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QS4U53RZK7UKJQXSKVJXJAVUHW/bundle.json","state_url":"https://pith.science/pith/QS4U53RZK7UKJQXSKVJXJAVUHW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QS4U53RZK7UKJQXSKVJXJAVUHW/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":"2026-08-21T13:59:53Z","links":{"resolver":"https://pith.science/pith/QS4U53RZK7UKJQXSKVJXJAVUHW","bundle":"https://pith.science/pith/QS4U53RZK7UKJQXSKVJXJAVUHW/bundle.json","state":"https://pith.science/pith/QS4U53RZK7UKJQXSKVJXJAVUHW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QS4U53RZK7UKJQXSKVJXJAVUHW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QS4U53RZK7UKJQXSKVJXJAVUHW","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":"f424a82ed085852fb5aaae9a35fb7b732edb1af33bcd5fbb2a3d6b77cd592f60","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-27T17:43:50Z","title_canon_sha256":"3e9bc0cc4e31c37ca76eeab420da34cbee011f5c3bdd50c2bdaada2bb5c4d9eb"},"schema_version":"1.0","source":{"id":"2204.13094","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.13094","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"arxiv_version","alias_value":"2204.13094v1","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.13094","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"pith_short_12","alias_value":"QS4U53RZK7UK","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"pith_short_16","alias_value":"QS4U53RZK7UKJQXS","created_at":"2026-07-05T04:18:25Z"},{"alias_kind":"pith_short_8","alias_value":"QS4U53RZ","created_at":"2026-07-05T04:18:25Z"}],"graph_snapshots":[{"event_id":"sha256:5bc670f2bfd12013c0404b2d8cfa639d16acb4b8c2e789863b44f76bee0ec2de","target":"graph","created_at":"2026-07-05T04:18:25Z","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/2204.13094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose an unsupervised kNN-based approach for word segmentation in speech utterances. Our method relies on self-supervised pre-trained speech representations, and compares each audio segment of a given utterance to its K nearest neighbors within the training set. Our main assumption is that a segment containing more than one word would occur less often than a segment containing a single word. Our method does not require phoneme discovery and is able to operate directly on pre-trained audio representations. This is in contrast to current methods that use a two-stage approach;","authors_text":"Joseph Keshet, Tzeviya Sylvia Fuchs, Yedid Hoshen","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-27T17:43:50Z","title":"Unsupervised Word Segmentation using K Nearest Neighbors"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.13094","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":"sha256:2c5e4d12cd7f5e403feb5b7ccac1b7c7dd05ebfd491492fc28f3aaa80ae71e11","target":"record","created_at":"2026-07-05T04:18:25Z","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":"f424a82ed085852fb5aaae9a35fb7b732edb1af33bcd5fbb2a3d6b77cd592f60","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-04-27T17:43:50Z","title_canon_sha256":"3e9bc0cc4e31c37ca76eeab420da34cbee011f5c3bdd50c2bdaada2bb5c4d9eb"},"schema_version":"1.0","source":{"id":"2204.13094","kind":"arxiv","version":1}},"canonical_sha256":"84b94eee3957e8a4c2f255537482b43d8f6c59419f2497358f9cbb3c402e906f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"84b94eee3957e8a4c2f255537482b43d8f6c59419f2497358f9cbb3c402e906f","first_computed_at":"2026-07-05T04:18:25.783741Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:18:25.783741Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8qN/PLycogkMdy552aoIbI74BBnkR4OuKHXXlykePqDa0shlf8ZnRAQk/zCqT803nBGMFry5lV3fjMJCC2EvCg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:18:25.784144Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.13094","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2c5e4d12cd7f5e403feb5b7ccac1b7c7dd05ebfd491492fc28f3aaa80ae71e11","sha256:5bc670f2bfd12013c0404b2d8cfa639d16acb4b8c2e789863b44f76bee0ec2de"],"state_sha256":"f25371a6314db6df4cc3cd09f5ddf70ecbbbd3417c8373808bedc42a55ba8695"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"eDZQYypZgeDID5Xm2xI+Gv7VDzJwPsjN9nbpfCQ8fuSTqj7Mq8wHVPMqne4zWhJqO75P9Xw4IkNOHk6GgnrpBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T13:59:53.495380Z","bundle_sha256":"2a3c64363f1a316cd8b0e6a83fc7bb8e2ec1f2a2e0dccd0b0492d171986cae31"}}