{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ETW2J3BWB75OKB4SBI45TPN7RR","short_pith_number":"pith:ETW2J3BW","canonical_record":{"source":{"id":"1609.06530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-21T12:43:53Z","cross_cats_sorted":[],"title_canon_sha256":"cbe157ed650d0b7f607d1932d9d07d763e4afd7b90954de426629147b34c67eb","abstract_canon_sha256":"1b5da368ff88515ef451ceaf0b9bc48a51fc317014576259882bfa79800c3718"},"schema_version":"1.0"},"canonical_sha256":"24eda4ec360ffae507920a39d9bdbf8c6a55d5e6756bd59b536b42595434b48e","source":{"kind":"arxiv","id":"1609.06530","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.06530","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"1609.06530v1","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.06530","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"ETW2J3BWB75O","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"ETW2J3BWB75OKB4S","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"ETW2J3BW","created_at":"2026-05-18T12:30:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ETW2J3BWB75OKB4SBI45TPN7RR","target":"record","payload":{"canonical_record":{"source":{"id":"1609.06530","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-21T12:43:53Z","cross_cats_sorted":[],"title_canon_sha256":"cbe157ed650d0b7f607d1932d9d07d763e4afd7b90954de426629147b34c67eb","abstract_canon_sha256":"1b5da368ff88515ef451ceaf0b9bc48a51fc317014576259882bfa79800c3718"},"schema_version":"1.0"},"canonical_sha256":"24eda4ec360ffae507920a39d9bdbf8c6a55d5e6756bd59b536b42595434b48e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:04:08.026436Z","signature_b64":"SZB8AiOSVwYbkQ4HnJeSkHLJaT2AH767WjXoBkdWBt2P3PSmePZsGicsujUEDq2vbrPggmenisADAWpD9vUDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"24eda4ec360ffae507920a39d9bdbf8c6a55d5e6756bd59b536b42595434b48e","last_reissued_at":"2026-05-18T01:04:08.025925Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:04:08.025925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.06530","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":"2026-05-18T01:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6BT686pSLlF523yIpFnY0Teh1A4BqgAAEGewgiPm88AT+jIHNJRPvzIbCYaTpx/+Ls2WH5uqqkfcLx0jALz2Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:09:58.713634Z"},"content_sha256":"9e78e4e9287ba269e94b068407a99478edf1449b1a0b04d51ac39c883db40dc6","schema_version":"1.0","event_id":"sha256:9e78e4e9287ba269e94b068407a99478edf1449b1a0b04d51ac39c883db40dc6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ETW2J3BWB75OKB4SBI45TPN7RR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Weakly supervised spoken term discovery using cross-lingual side information","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adam Lopez, Herman Kamper, Sameer Bansal, Sharon Goldwater","submitted_at":"2016-09-21T12:43:53Z","abstract_excerpt":"Recent work on unsupervised term discovery (UTD) aims to identify and cluster repeated word-like units from audio alone. These systems are promising for some very low-resource languages where transcribed audio is unavailable, or where no written form of the language exists. However, in some cases it may still be feasible (e.g., through crowdsourcing) to obtain (possibly noisy) text translations of the audio. If so, this information could be used as a source of side information to improve UTD. Here, we present a simple method for rescoring the output of a UTD system using text translations, and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.06530","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":""},"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":"2026-05-18T01:04:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5eRgIfkdQg94Z9bKMJYXpNU6CA4fQg2mV8ONZNs6xCW80axiRoo33UOOSoLiUHDo703nR7E/1rPALh0n59wjAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T23:09:58.713977Z"},"content_sha256":"c1e9c6a2db37e1a45797588bf1f44bae634c4706bbc1dc1c43ea5e1df901b5e3","schema_version":"1.0","event_id":"sha256:c1e9c6a2db37e1a45797588bf1f44bae634c4706bbc1dc1c43ea5e1df901b5e3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ETW2J3BWB75OKB4SBI45TPN7RR/bundle.json","state_url":"https://pith.science/pith/ETW2J3BWB75OKB4SBI45TPN7RR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ETW2J3BWB75OKB4SBI45TPN7RR/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":"2026-06-02T23:09:58Z","links":{"resolver":"https://pith.science/pith/ETW2J3BWB75OKB4SBI45TPN7RR","bundle":"https://pith.science/pith/ETW2J3BWB75OKB4SBI45TPN7RR/bundle.json","state":"https://pith.science/pith/ETW2J3BWB75OKB4SBI45TPN7RR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ETW2J3BWB75OKB4SBI45TPN7RR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ETW2J3BWB75OKB4SBI45TPN7RR","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":"1b5da368ff88515ef451ceaf0b9bc48a51fc317014576259882bfa79800c3718","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-21T12:43:53Z","title_canon_sha256":"cbe157ed650d0b7f607d1932d9d07d763e4afd7b90954de426629147b34c67eb"},"schema_version":"1.0","source":{"id":"1609.06530","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.06530","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"arxiv_version","alias_value":"1609.06530v1","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.06530","created_at":"2026-05-18T01:04:08Z"},{"alias_kind":"pith_short_12","alias_value":"ETW2J3BWB75O","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_16","alias_value":"ETW2J3BWB75OKB4S","created_at":"2026-05-18T12:30:15Z"},{"alias_kind":"pith_short_8","alias_value":"ETW2J3BW","created_at":"2026-05-18T12:30:15Z"}],"graph_snapshots":[{"event_id":"sha256:c1e9c6a2db37e1a45797588bf1f44bae634c4706bbc1dc1c43ea5e1df901b5e3","target":"graph","created_at":"2026-05-18T01:04:08Z","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":"Recent work on unsupervised term discovery (UTD) aims to identify and cluster repeated word-like units from audio alone. These systems are promising for some very low-resource languages where transcribed audio is unavailable, or where no written form of the language exists. However, in some cases it may still be feasible (e.g., through crowdsourcing) to obtain (possibly noisy) text translations of the audio. If so, this information could be used as a source of side information to improve UTD. Here, we present a simple method for rescoring the output of a UTD system using text translations, and","authors_text":"Adam Lopez, Herman Kamper, Sameer Bansal, Sharon Goldwater","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-21T12:43:53Z","title":"Weakly supervised spoken term discovery using cross-lingual side information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.06530","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":"sha256:9e78e4e9287ba269e94b068407a99478edf1449b1a0b04d51ac39c883db40dc6","target":"record","created_at":"2026-05-18T01:04:08Z","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":"1b5da368ff88515ef451ceaf0b9bc48a51fc317014576259882bfa79800c3718","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-21T12:43:53Z","title_canon_sha256":"cbe157ed650d0b7f607d1932d9d07d763e4afd7b90954de426629147b34c67eb"},"schema_version":"1.0","source":{"id":"1609.06530","kind":"arxiv","version":1}},"canonical_sha256":"24eda4ec360ffae507920a39d9bdbf8c6a55d5e6756bd59b536b42595434b48e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"24eda4ec360ffae507920a39d9bdbf8c6a55d5e6756bd59b536b42595434b48e","first_computed_at":"2026-05-18T01:04:08.025925Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:04:08.025925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SZB8AiOSVwYbkQ4HnJeSkHLJaT2AH767WjXoBkdWBt2P3PSmePZsGicsujUEDq2vbrPggmenisADAWpD9vUDDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:04:08.026436Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.06530","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e78e4e9287ba269e94b068407a99478edf1449b1a0b04d51ac39c883db40dc6","sha256:c1e9c6a2db37e1a45797588bf1f44bae634c4706bbc1dc1c43ea5e1df901b5e3"],"state_sha256":"40b7c4d6900ae86d6a838345a54b5417ac8ae43c6248dbd21a4b52f7f7262b1b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b2ymJiZ5XTFh933WGma84P/Ve7k3EmYZdowhjtMhsFZLMfygheO4b6I4Ejlix9/GekjZZjA2zrBetDsapBhcDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T23:09:58.716292Z","bundle_sha256":"d20f5b42e5eae2c6ee5b5e0f0bf189e5b5b0e2ca5e2eae003e9f17102255422e"}}