{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MCGPEXB6NENS4K53UF4X562VOZ","short_pith_number":"pith:MCGPEXB6","canonical_record":{"source":{"id":"2101.08890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T23:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b676e656b7062ed9a743ae0945f29f18a981484b39457793d3acfac56d721b85","abstract_canon_sha256":"b63dcf66abd8213734b95efc8cf6b3be30f656a178f905441a4d36c1068d81a3"},"schema_version":"1.0"},"canonical_sha256":"608cf25c3e691b2e2bbba1797efb55765994e3e27c376f083aed369b0b5d7ac3","source":{"kind":"arxiv","id":"2101.08890","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08890","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08890v1","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08890","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"MCGPEXB6NENS","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"MCGPEXB6NENS4K53","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"MCGPEXB6","created_at":"2026-07-05T02:08:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MCGPEXB6NENS4K53UF4X562VOZ","target":"record","payload":{"canonical_record":{"source":{"id":"2101.08890","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T23:45:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b676e656b7062ed9a743ae0945f29f18a981484b39457793d3acfac56d721b85","abstract_canon_sha256":"b63dcf66abd8213734b95efc8cf6b3be30f656a178f905441a4d36c1068d81a3"},"schema_version":"1.0"},"canonical_sha256":"608cf25c3e691b2e2bbba1797efb55765994e3e27c376f083aed369b0b5d7ac3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:08:41.670115Z","signature_b64":"PrU9e2wwXJLBpcDKTta87jOH/s95y+aCJ+0r5LaiGuK4UPZ7UgSFmjPWD/Xk6Ythu9W3uttYjlyRhDnZ50ieBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"608cf25c3e691b2e2bbba1797efb55765994e3e27c376f083aed369b0b5d7ac3","last_reissued_at":"2026-07-05T02:08:41.669678Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:08:41.669678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.08890","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":"2026-07-05T02:08:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5abTm4eTne6hcFs5s6hpaBpbuQFpQWJrffGQqEkBAco6TSzKVaSm+yPWGHqofX9WWLsRta6NO9Hbx26xPsXRBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:22:36.199313Z"},"content_sha256":"a325936b726ea6b785f1d9726ba8489afe54144710a1cfbe860bd5fc194e0b3d","schema_version":"1.0","event_id":"sha256:a325936b726ea6b785f1d9726ba8489afe54144710a1cfbe860bd5fc194e0b3d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MCGPEXB6NENS4K53UF4X562VOZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Distilling Large Language Models into Tiny and Effective Students using pQRNN","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aditya Siddhant, Edward Li, Melvin Johnson, Prabhu Kaliamoorthi","submitted_at":"2021-01-21T23:45:50Z","abstract_excerpt":"Large pre-trained multilingual models like mBERT, XLM-R achieve state of the art results on language understanding tasks. However, they are not well suited for latency critical applications on both servers and edge devices. It's important to reduce the memory and compute resources required by these models. To this end, we propose pQRNN, a projection-based embedding-free neural encoder that is tiny and effective for natural language processing tasks. Without pre-training, pQRNNs significantly outperform LSTM models with pre-trained embeddings despite being 140x smaller. With the same number of "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08890","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/2101.08890/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":"2026-07-05T02:08:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gtfdqHPcxz5VdeK9xSosOY3j8KYRsGeXGiysvDSsHEnxA+v+a4AOFf/xM3vI57flxfsaCvziZ6RLMZ6UdJ8pBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T05:22:36.200175Z"},"content_sha256":"ce24f16e9ef6e933f523adb398d67d05e4fae51fe9bf86c1ce36b07cc755f126","schema_version":"1.0","event_id":"sha256:ce24f16e9ef6e933f523adb398d67d05e4fae51fe9bf86c1ce36b07cc755f126"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCGPEXB6NENS4K53UF4X562VOZ/bundle.json","state_url":"https://pith.science/pith/MCGPEXB6NENS4K53UF4X562VOZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCGPEXB6NENS4K53UF4X562VOZ/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":"2026-08-21T05:22:36Z","links":{"resolver":"https://pith.science/pith/MCGPEXB6NENS4K53UF4X562VOZ","bundle":"https://pith.science/pith/MCGPEXB6NENS4K53UF4X562VOZ/bundle.json","state":"https://pith.science/pith/MCGPEXB6NENS4K53UF4X562VOZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCGPEXB6NENS4K53UF4X562VOZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MCGPEXB6NENS4K53UF4X562VOZ","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":"b63dcf66abd8213734b95efc8cf6b3be30f656a178f905441a4d36c1068d81a3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T23:45:50Z","title_canon_sha256":"b676e656b7062ed9a743ae0945f29f18a981484b39457793d3acfac56d721b85"},"schema_version":"1.0","source":{"id":"2101.08890","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.08890","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"arxiv_version","alias_value":"2101.08890v1","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.08890","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"pith_short_12","alias_value":"MCGPEXB6NENS","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"pith_short_16","alias_value":"MCGPEXB6NENS4K53","created_at":"2026-07-05T02:08:41Z"},{"alias_kind":"pith_short_8","alias_value":"MCGPEXB6","created_at":"2026-07-05T02:08:41Z"}],"graph_snapshots":[{"event_id":"sha256:ce24f16e9ef6e933f523adb398d67d05e4fae51fe9bf86c1ce36b07cc755f126","target":"graph","created_at":"2026-07-05T02:08:41Z","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/2101.08890/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large pre-trained multilingual models like mBERT, XLM-R achieve state of the art results on language understanding tasks. However, they are not well suited for latency critical applications on both servers and edge devices. It's important to reduce the memory and compute resources required by these models. To this end, we propose pQRNN, a projection-based embedding-free neural encoder that is tiny and effective for natural language processing tasks. Without pre-training, pQRNNs significantly outperform LSTM models with pre-trained embeddings despite being 140x smaller. With the same number of ","authors_text":"Aditya Siddhant, Edward Li, Melvin Johnson, Prabhu Kaliamoorthi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T23:45:50Z","title":"Distilling Large Language Models into Tiny and Effective Students using pQRNN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.08890","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:a325936b726ea6b785f1d9726ba8489afe54144710a1cfbe860bd5fc194e0b3d","target":"record","created_at":"2026-07-05T02:08:41Z","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":"b63dcf66abd8213734b95efc8cf6b3be30f656a178f905441a4d36c1068d81a3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-21T23:45:50Z","title_canon_sha256":"b676e656b7062ed9a743ae0945f29f18a981484b39457793d3acfac56d721b85"},"schema_version":"1.0","source":{"id":"2101.08890","kind":"arxiv","version":1}},"canonical_sha256":"608cf25c3e691b2e2bbba1797efb55765994e3e27c376f083aed369b0b5d7ac3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"608cf25c3e691b2e2bbba1797efb55765994e3e27c376f083aed369b0b5d7ac3","first_computed_at":"2026-07-05T02:08:41.669678Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:08:41.669678Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PrU9e2wwXJLBpcDKTta87jOH/s95y+aCJ+0r5LaiGuK4UPZ7UgSFmjPWD/Xk6Ythu9W3uttYjlyRhDnZ50ieBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:08:41.670115Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.08890","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a325936b726ea6b785f1d9726ba8489afe54144710a1cfbe860bd5fc194e0b3d","sha256:ce24f16e9ef6e933f523adb398d67d05e4fae51fe9bf86c1ce36b07cc755f126"],"state_sha256":"bcf1f80b88a19f3299e517aa380a1eec2f5295158130665d7309bcaf31eb7158"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AWnfZvBPKpWHzQ45zRMwu846iP3Jvm3+lzi8B7juy4AukwOWMvZ5HEHa4cKTbGBZs8ZLW/xQVtoOHb2ykpP/Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T05:22:36.206259Z","bundle_sha256":"23cc020c94685cd3fd6a2a5d80c67e277deaccb6ef88d2ef733aae77e733983e"}}