{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:ZBDSAAEY2JGUPTE2Q25HUWATZT","short_pith_number":"pith:ZBDSAAEY","canonical_record":{"source":{"id":"2102.07219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-14T18:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"8eebb5f10c4e94008ae48a6c57b0c2d533894b3fad8faedbe76b0ac01068e899","abstract_canon_sha256":"26af6ca965d95e41294125f016d374c034552727438d2d404e56c8981f167499"},"schema_version":"1.0"},"canonical_sha256":"c847200098d24d47cc9a86ba7a5813cccd6a07448f987bf5a0e8be3746b20c28","source":{"kind":"arxiv","id":"2102.07219","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.07219","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"arxiv_version","alias_value":"2102.07219v1","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07219","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZBDSAAEY2JGU","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZBDSAAEY2JGUPTE2","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZBDSAAEY","created_at":"2026-07-05T02:15:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:ZBDSAAEY2JGUPTE2Q25HUWATZT","target":"record","payload":{"canonical_record":{"source":{"id":"2102.07219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-14T18:47:01Z","cross_cats_sorted":[],"title_canon_sha256":"8eebb5f10c4e94008ae48a6c57b0c2d533894b3fad8faedbe76b0ac01068e899","abstract_canon_sha256":"26af6ca965d95e41294125f016d374c034552727438d2d404e56c8981f167499"},"schema_version":"1.0"},"canonical_sha256":"c847200098d24d47cc9a86ba7a5813cccd6a07448f987bf5a0e8be3746b20c28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:15:02.764834Z","signature_b64":"OZYsakcW0C28WqI35WZQDbrvRebisPlENI95q67lV19+ullkPD7e3zh7ky9YWZkylUo9L6u+y+PkNZmo4i9RAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c847200098d24d47cc9a86ba7a5813cccd6a07448f987bf5a0e8be3746b20c28","last_reissued_at":"2026-07-05T02:15:02.764337Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:15:02.764337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.07219","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":"2026-07-05T02:15:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bz8YSlLqLC9seza26L0nOA3E2u3pSfQc2tbSOPT1VCZJz4VHKPpP6+AEZMMLNYBXmqhny3Lc24U2t5buQPtWBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:37:56.105008Z"},"content_sha256":"3ff464e9058896fb3dbea945275b872fa5438de57abffdd78322ac7ac254a767","schema_version":"1.0","event_id":"sha256:3ff464e9058896fb3dbea945275b872fa5438de57abffdd78322ac7ac254a767"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:ZBDSAAEY2JGUPTE2Q25HUWATZT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Error-driven Pruning of Language Models for Virtual Assistants","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christophe Van Gysel, Ernest Pusateri, Lyan Verwimp, Manos Tsagkias, Sashank Gondala","submitted_at":"2021-02-14T18:47:01Z","abstract_excerpt":"Language models (LMs) for virtual assistants (VAs) are typically trained on large amounts of data, resulting in prohibitively large models which require excessive memory and/or cannot be used to serve user requests in real-time. Entropy pruning results in smaller models but with significant degradation of effectiveness in the tail of the user request distribution. We customize entropy pruning by allowing for a keep list of infrequent n-grams that require a more relaxed pruning threshold, and propose three methods to construct the keep list. Each method has its own advantages and disadvantages "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07219","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/2102.07219/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":"2026-07-05T02:15:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VbEMdlT1xgFVcQI12omdVHu0jSrufhlZ4bJ+vTZtxXhE6fhYcXzrUnOZwF/fRQRlnQBMjPihAPB+6CpEZMGPCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T15:37:56.105514Z"},"content_sha256":"0a199589788feea41da0c38b31a40d2ecf61af2860948f4601d668131139200b","schema_version":"1.0","event_id":"sha256:0a199589788feea41da0c38b31a40d2ecf61af2860948f4601d668131139200b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZBDSAAEY2JGUPTE2Q25HUWATZT/bundle.json","state_url":"https://pith.science/pith/ZBDSAAEY2JGUPTE2Q25HUWATZT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZBDSAAEY2JGUPTE2Q25HUWATZT/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":"2026-08-03T15:37:56Z","links":{"resolver":"https://pith.science/pith/ZBDSAAEY2JGUPTE2Q25HUWATZT","bundle":"https://pith.science/pith/ZBDSAAEY2JGUPTE2Q25HUWATZT/bundle.json","state":"https://pith.science/pith/ZBDSAAEY2JGUPTE2Q25HUWATZT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZBDSAAEY2JGUPTE2Q25HUWATZT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:ZBDSAAEY2JGUPTE2Q25HUWATZT","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":"26af6ca965d95e41294125f016d374c034552727438d2d404e56c8981f167499","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-14T18:47:01Z","title_canon_sha256":"8eebb5f10c4e94008ae48a6c57b0c2d533894b3fad8faedbe76b0ac01068e899"},"schema_version":"1.0","source":{"id":"2102.07219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.07219","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"arxiv_version","alias_value":"2102.07219v1","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.07219","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"pith_short_12","alias_value":"ZBDSAAEY2JGU","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"pith_short_16","alias_value":"ZBDSAAEY2JGUPTE2","created_at":"2026-07-05T02:15:02Z"},{"alias_kind":"pith_short_8","alias_value":"ZBDSAAEY","created_at":"2026-07-05T02:15:02Z"}],"graph_snapshots":[{"event_id":"sha256:0a199589788feea41da0c38b31a40d2ecf61af2860948f4601d668131139200b","target":"graph","created_at":"2026-07-05T02:15:02Z","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/2102.07219/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language models (LMs) for virtual assistants (VAs) are typically trained on large amounts of data, resulting in prohibitively large models which require excessive memory and/or cannot be used to serve user requests in real-time. Entropy pruning results in smaller models but with significant degradation of effectiveness in the tail of the user request distribution. We customize entropy pruning by allowing for a keep list of infrequent n-grams that require a more relaxed pruning threshold, and propose three methods to construct the keep list. Each method has its own advantages and disadvantages ","authors_text":"Christophe Van Gysel, Ernest Pusateri, Lyan Verwimp, Manos Tsagkias, Sashank Gondala","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-14T18:47:01Z","title":"Error-driven Pruning of Language Models for Virtual Assistants"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.07219","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":"sha256:3ff464e9058896fb3dbea945275b872fa5438de57abffdd78322ac7ac254a767","target":"record","created_at":"2026-07-05T02:15:02Z","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":"26af6ca965d95e41294125f016d374c034552727438d2d404e56c8981f167499","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-14T18:47:01Z","title_canon_sha256":"8eebb5f10c4e94008ae48a6c57b0c2d533894b3fad8faedbe76b0ac01068e899"},"schema_version":"1.0","source":{"id":"2102.07219","kind":"arxiv","version":1}},"canonical_sha256":"c847200098d24d47cc9a86ba7a5813cccd6a07448f987bf5a0e8be3746b20c28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c847200098d24d47cc9a86ba7a5813cccd6a07448f987bf5a0e8be3746b20c28","first_computed_at":"2026-07-05T02:15:02.764337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:15:02.764337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OZYsakcW0C28WqI35WZQDbrvRebisPlENI95q67lV19+ullkPD7e3zh7ky9YWZkylUo9L6u+y+PkNZmo4i9RAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:15:02.764834Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.07219","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ff464e9058896fb3dbea945275b872fa5438de57abffdd78322ac7ac254a767","sha256:0a199589788feea41da0c38b31a40d2ecf61af2860948f4601d668131139200b"],"state_sha256":"a2f4663731d63471997cf71b098664b55e3431401aa92f336bd58ba891fc2fa1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dAb7YyqklALBPriXoRCQFW6XBYpaFGCXXpYpU+vRtM4q6ZKEN0h/QX0TmjFePPnKQU2n3dtcA3YJeov3fVs0Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T15:37:56.109374Z","bundle_sha256":"e2b3ed67e64605506e87eb16c690b4d80d4824b82ef98b8c93ddda88cefa56f9"}}