{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:RRM3EU2QQR3C6BUVHQE2HJZVTQ","short_pith_number":"pith:RRM3EU2Q","canonical_record":{"source":{"id":"2008.02385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-05T22:21:03Z","cross_cats_sorted":[],"title_canon_sha256":"d41a03202d779f4cde2a9c3ad45b52cbb0cb5833cda988af6417b5b8f8bcf22d","abstract_canon_sha256":"46e622a227c456b348773ab919cf63b8148c1aa0bff94ff0823d4b9530721e74"},"schema_version":"1.0"},"canonical_sha256":"8c59b2535084762f06953c09a3a7359c307c28019bb72bad101e909ceeaa785b","source":{"kind":"arxiv","id":"2008.02385","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02385","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02385v1","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02385","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"pith_short_12","alias_value":"RRM3EU2QQR3C","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"pith_short_16","alias_value":"RRM3EU2QQR3C6BUV","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"pith_short_8","alias_value":"RRM3EU2Q","created_at":"2026-07-05T01:25:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:RRM3EU2QQR3C6BUVHQE2HJZVTQ","target":"record","payload":{"canonical_record":{"source":{"id":"2008.02385","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-05T22:21:03Z","cross_cats_sorted":[],"title_canon_sha256":"d41a03202d779f4cde2a9c3ad45b52cbb0cb5833cda988af6417b5b8f8bcf22d","abstract_canon_sha256":"46e622a227c456b348773ab919cf63b8148c1aa0bff94ff0823d4b9530721e74"},"schema_version":"1.0"},"canonical_sha256":"8c59b2535084762f06953c09a3a7359c307c28019bb72bad101e909ceeaa785b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:25:04.562519Z","signature_b64":"jfdxxOzd0K0vbv2gY7817oijZIzpL+75buqJVuCf6yUBae5O/imjRya+oK1zQu5Oj5RLZ5SC30iALC1HnQtHBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c59b2535084762f06953c09a3a7359c307c28019bb72bad101e909ceeaa785b","last_reissued_at":"2026-07-05T01:25:04.562087Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:25:04.562087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2008.02385","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":"2026-07-05T01:25:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RhOPlSPPWXZfoUYODSaNynF0jO7epkNL7Aq7wrGToT7aEhrKnWqgr9MA0UoyWal8AI1Q856w92Ym1Kg1EpsWDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:06:45.449733Z"},"content_sha256":"eaf1bc0e18c58272d9d66acab161aa928cd69031c397471f462fa4ec2154374a","schema_version":"1.0","event_id":"sha256:eaf1bc0e18c58272d9d66acab161aa928cd69031c397471f462fa4ec2154374a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:RRM3EU2QQR3C6BUVHQE2HJZVTQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Efficient MDI Adaptation for n-gram Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Arora, Dan Povey, Ke Li, Ruizhe Huang, Sanjeev Khudanpur","submitted_at":"2020-08-05T22:21:03Z","abstract_excerpt":"This paper presents an efficient algorithm for n-gram language model adaptation under the minimum discrimination information (MDI) principle, where an out-of-domain language model is adapted to satisfy the constraints of marginal probabilities of the in-domain data. The challenge for MDI language model adaptation is its computational complexity. By taking advantage of the backoff structure of n-gram model and the idea of hierarchical training method, originally proposed for maximum entropy (ME) language models, we show that MDI adaptation can be computed in linear-time complexity to the inputs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02385","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/2008.02385/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":"2026-07-05T01:25:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I96nw0+CCly+mfjWok0iyWnweSM1xAx74ao1n+akOvjPb4pPj1+kwSiE8fBwTYcfpREJiX30ckJ/6+h/XaBmDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:06:45.450240Z"},"content_sha256":"52c07762fdf8f5f8de5bc9a3b2345a2243fb98def054722fff32c0d2c51a81db","schema_version":"1.0","event_id":"sha256:52c07762fdf8f5f8de5bc9a3b2345a2243fb98def054722fff32c0d2c51a81db"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/bundle.json","state_url":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/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":"2026-07-07T13:06:45Z","links":{"resolver":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ","bundle":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/bundle.json","state":"https://pith.science/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RRM3EU2QQR3C6BUVHQE2HJZVTQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:RRM3EU2QQR3C6BUVHQE2HJZVTQ","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":"46e622a227c456b348773ab919cf63b8148c1aa0bff94ff0823d4b9530721e74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-05T22:21:03Z","title_canon_sha256":"d41a03202d779f4cde2a9c3ad45b52cbb0cb5833cda988af6417b5b8f8bcf22d"},"schema_version":"1.0","source":{"id":"2008.02385","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2008.02385","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"arxiv_version","alias_value":"2008.02385v1","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.02385","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"pith_short_12","alias_value":"RRM3EU2QQR3C","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"pith_short_16","alias_value":"RRM3EU2QQR3C6BUV","created_at":"2026-07-05T01:25:04Z"},{"alias_kind":"pith_short_8","alias_value":"RRM3EU2Q","created_at":"2026-07-05T01:25:04Z"}],"graph_snapshots":[{"event_id":"sha256:52c07762fdf8f5f8de5bc9a3b2345a2243fb98def054722fff32c0d2c51a81db","target":"graph","created_at":"2026-07-05T01:25:04Z","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/2008.02385/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper presents an efficient algorithm for n-gram language model adaptation under the minimum discrimination information (MDI) principle, where an out-of-domain language model is adapted to satisfy the constraints of marginal probabilities of the in-domain data. The challenge for MDI language model adaptation is its computational complexity. By taking advantage of the backoff structure of n-gram model and the idea of hierarchical training method, originally proposed for maximum entropy (ME) language models, we show that MDI adaptation can be computed in linear-time complexity to the inputs","authors_text":"Ashish Arora, Dan Povey, Ke Li, Ruizhe Huang, Sanjeev Khudanpur","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-05T22:21:03Z","title":"Efficient MDI Adaptation for n-gram Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.02385","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:eaf1bc0e18c58272d9d66acab161aa928cd69031c397471f462fa4ec2154374a","target":"record","created_at":"2026-07-05T01:25:04Z","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":"46e622a227c456b348773ab919cf63b8148c1aa0bff94ff0823d4b9530721e74","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-05T22:21:03Z","title_canon_sha256":"d41a03202d779f4cde2a9c3ad45b52cbb0cb5833cda988af6417b5b8f8bcf22d"},"schema_version":"1.0","source":{"id":"2008.02385","kind":"arxiv","version":1}},"canonical_sha256":"8c59b2535084762f06953c09a3a7359c307c28019bb72bad101e909ceeaa785b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c59b2535084762f06953c09a3a7359c307c28019bb72bad101e909ceeaa785b","first_computed_at":"2026-07-05T01:25:04.562087Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:25:04.562087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jfdxxOzd0K0vbv2gY7817oijZIzpL+75buqJVuCf6yUBae5O/imjRya+oK1zQu5Oj5RLZ5SC30iALC1HnQtHBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:25:04.562519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2008.02385","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:eaf1bc0e18c58272d9d66acab161aa928cd69031c397471f462fa4ec2154374a","sha256:52c07762fdf8f5f8de5bc9a3b2345a2243fb98def054722fff32c0d2c51a81db"],"state_sha256":"f094b0b3187c279133ab7a8e7cd8e0ef34aaced6eab053e7bc37942d5a344163"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aFq2RItOIV+QOf93KZqy73L27lX4NNUKkcoPtyOoMXDkO+LZ/K/IqUTKRVgAEtzFSyw9uGdRa5hgoAfd02whBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:06:45.452867Z","bundle_sha256":"d4b76c90da7135cfd4ee2e28d8e4f2e3936bd86c8ba4f36c1a73a85c8ada4b32"}}