{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:PBY2O7OXM52CZNYIL75FG334XP","short_pith_number":"pith:PBY2O7OX","canonical_record":{"source":{"id":"1609.08139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-26T19:50:59Z","cross_cats_sorted":[],"title_canon_sha256":"6540f80594dd52f3bd9c1521fe9954e0c1f477a428d61a0f172d53a4712a6dec","abstract_canon_sha256":"885576da17d5b63acc7d9330594fd6c7c3d975bfc3732f61980b3d4df50b9a56"},"schema_version":"1.0"},"canonical_sha256":"7871a77dd767742cb7085ffa536f7cbbf94ac613e6bd8454eeeb8e46c97317f8","source":{"kind":"arxiv","id":"1609.08139","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.08139","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"1609.08139v1","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08139","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"PBY2O7OXM52C","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PBY2O7OXM52CZNYI","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PBY2O7OX","created_at":"2026-05-18T12:30:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:PBY2O7OXM52CZNYIL75FG334XP","target":"record","payload":{"canonical_record":{"source":{"id":"1609.08139","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-26T19:50:59Z","cross_cats_sorted":[],"title_canon_sha256":"6540f80594dd52f3bd9c1521fe9954e0c1f477a428d61a0f172d53a4712a6dec","abstract_canon_sha256":"885576da17d5b63acc7d9330594fd6c7c3d975bfc3732f61980b3d4df50b9a56"},"schema_version":"1.0"},"canonical_sha256":"7871a77dd767742cb7085ffa536f7cbbf94ac613e6bd8454eeeb8e46c97317f8","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:54.315194Z","signature_b64":"vZuN8CVRRnEOcmpboRlcUsXG/3CBZh7Bglu0KOvyGwjEVsnYF7zdOW1BhlJM/fBSeDBgssbQI+k8AekdmKyvAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7871a77dd767742cb7085ffa536f7cbbf94ac613e6bd8454eeeb8e46c97317f8","last_reissued_at":"2026-05-18T01:03:54.314614Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:54.314614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.08139","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":"2026-05-18T01:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLJ5ijFFu2TmQPqcQrM7df/UmBo98k5av9NyjttpjJGmLKIZtSXfga17S99uvpZyqknfbyK93sHUx68pC4DbCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:30:13.231968Z"},"content_sha256":"6db370c72585a9096c9ca695b1b1f09867c06931c9cee9d23bc79f03b43114f6","schema_version":"1.0","event_id":"sha256:6db370c72585a9096c9ca695b1b1f09867c06931c9cee9d23bc79f03b43114f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:PBY2O7OXM52CZNYIL75FG334XP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Antonios Anastasopoulos, David Chiang, Long Duong","submitted_at":"2016-09-26T19:50:59Z","abstract_excerpt":"For many low-resource languages, spoken language resources are more likely to be annotated with translations than with transcriptions. Translated speech data is potentially valuable for documenting endangered languages or for training speech translation systems. A first step towards making use of such data would be to automatically align spoken words with their translations. We present a model that combines Dyer et al.'s reparameterization of IBM Model 2 (fast-align) and k-means clustering using Dynamic Time Warping as a distance metric. The two components are trained jointly using expectation"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08139","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":"2026-05-18T01:03:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"efxNldvJOMHnDQURWiJ1UFLD9gZXAm+07YdJEdM05FMNpvyZjBHQqUnc085yCZfT55XFQUWAMJt4vWzuwSDTBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T14:30:13.232361Z"},"content_sha256":"1daccdf73a891f41376b2b8bd81abaa1fa6fba1cd9aed90b450fd6594645f03e","schema_version":"1.0","event_id":"sha256:1daccdf73a891f41376b2b8bd81abaa1fa6fba1cd9aed90b450fd6594645f03e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PBY2O7OXM52CZNYIL75FG334XP/bundle.json","state_url":"https://pith.science/pith/PBY2O7OXM52CZNYIL75FG334XP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PBY2O7OXM52CZNYIL75FG334XP/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":"2026-05-28T14:30:13Z","links":{"resolver":"https://pith.science/pith/PBY2O7OXM52CZNYIL75FG334XP","bundle":"https://pith.science/pith/PBY2O7OXM52CZNYIL75FG334XP/bundle.json","state":"https://pith.science/pith/PBY2O7OXM52CZNYIL75FG334XP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PBY2O7OXM52CZNYIL75FG334XP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:PBY2O7OXM52CZNYIL75FG334XP","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":"885576da17d5b63acc7d9330594fd6c7c3d975bfc3732f61980b3d4df50b9a56","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-26T19:50:59Z","title_canon_sha256":"6540f80594dd52f3bd9c1521fe9954e0c1f477a428d61a0f172d53a4712a6dec"},"schema_version":"1.0","source":{"id":"1609.08139","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.08139","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"arxiv_version","alias_value":"1609.08139v1","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.08139","created_at":"2026-05-18T01:03:54Z"},{"alias_kind":"pith_short_12","alias_value":"PBY2O7OXM52C","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_16","alias_value":"PBY2O7OXM52CZNYI","created_at":"2026-05-18T12:30:39Z"},{"alias_kind":"pith_short_8","alias_value":"PBY2O7OX","created_at":"2026-05-18T12:30:39Z"}],"graph_snapshots":[{"event_id":"sha256:1daccdf73a891f41376b2b8bd81abaa1fa6fba1cd9aed90b450fd6594645f03e","target":"graph","created_at":"2026-05-18T01:03:54Z","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":"For many low-resource languages, spoken language resources are more likely to be annotated with translations than with transcriptions. Translated speech data is potentially valuable for documenting endangered languages or for training speech translation systems. A first step towards making use of such data would be to automatically align spoken words with their translations. We present a model that combines Dyer et al.'s reparameterization of IBM Model 2 (fast-align) and k-means clustering using Dynamic Time Warping as a distance metric. The two components are trained jointly using expectation","authors_text":"Antonios Anastasopoulos, David Chiang, Long Duong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-26T19:50:59Z","title":"An Unsupervised Probability Model for Speech-to-Translation Alignment of Low-Resource Languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.08139","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":"sha256:6db370c72585a9096c9ca695b1b1f09867c06931c9cee9d23bc79f03b43114f6","target":"record","created_at":"2026-05-18T01:03:54Z","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":"885576da17d5b63acc7d9330594fd6c7c3d975bfc3732f61980b3d4df50b9a56","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-09-26T19:50:59Z","title_canon_sha256":"6540f80594dd52f3bd9c1521fe9954e0c1f477a428d61a0f172d53a4712a6dec"},"schema_version":"1.0","source":{"id":"1609.08139","kind":"arxiv","version":1}},"canonical_sha256":"7871a77dd767742cb7085ffa536f7cbbf94ac613e6bd8454eeeb8e46c97317f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7871a77dd767742cb7085ffa536f7cbbf94ac613e6bd8454eeeb8e46c97317f8","first_computed_at":"2026-05-18T01:03:54.314614Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:54.314614Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vZuN8CVRRnEOcmpboRlcUsXG/3CBZh7Bglu0KOvyGwjEVsnYF7zdOW1BhlJM/fBSeDBgssbQI+k8AekdmKyvAw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:54.315194Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.08139","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6db370c72585a9096c9ca695b1b1f09867c06931c9cee9d23bc79f03b43114f6","sha256:1daccdf73a891f41376b2b8bd81abaa1fa6fba1cd9aed90b450fd6594645f03e"],"state_sha256":"908b9b04dc57ac4867f4235ae874b01ee6848e4c766c38acbbd6de0aa7189770"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a+sOEjyn350Yog6dpz35Q9LGOOPvQiKV/SJhBE+yIfa52Sg4WlqqiIHJ4lQ4u2iOg3V98u8CFewg0hKUkeXWDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T14:30:13.234463Z","bundle_sha256":"b6a916bef3ee892f2bda30f6a4ee0901feb98f0fd6cfd60cb89c4e6b4e751a38"}}