{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:XLQQIJJTPFGPCMQGG2V6JDUGXD","short_pith_number":"pith:XLQQIJJT","canonical_record":{"source":{"id":"2110.10305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T22:56:49Z","cross_cats_sorted":[],"title_canon_sha256":"588348bf7ed17eb1922c5dee3a27d4871ecf5446b2c020ad044064fda50034dc","abstract_canon_sha256":"5a801ba6509eea61303625c80edc4f0245dd84ff0f046afe2810a7ac968dda50"},"schema_version":"1.0"},"canonical_sha256":"bae1042533794cf1320636abe48e86b8c76fe4bb544331fb8bea01f73f286815","source":{"kind":"arxiv","id":"2110.10305","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10305","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10305v1","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10305","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"XLQQIJJTPFGP","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"XLQQIJJTPFGPCMQG","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"XLQQIJJT","created_at":"2026-07-05T03:24:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:XLQQIJJTPFGPCMQGG2V6JDUGXD","target":"record","payload":{"canonical_record":{"source":{"id":"2110.10305","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T22:56:49Z","cross_cats_sorted":[],"title_canon_sha256":"588348bf7ed17eb1922c5dee3a27d4871ecf5446b2c020ad044064fda50034dc","abstract_canon_sha256":"5a801ba6509eea61303625c80edc4f0245dd84ff0f046afe2810a7ac968dda50"},"schema_version":"1.0"},"canonical_sha256":"bae1042533794cf1320636abe48e86b8c76fe4bb544331fb8bea01f73f286815","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:24:15.634249Z","signature_b64":"20HAAT1ref8bDHKMMOhmHNHcCNpPxivbKbbNFtKFR98LWljjEKL6u45ZidviJXLzdhwQM07HgEcy+vi+gmsSCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bae1042533794cf1320636abe48e86b8c76fe4bb544331fb8bea01f73f286815","last_reissued_at":"2026-07-05T03:24:15.633928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:24:15.633928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.10305","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":"2026-07-05T03:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1Mvkbo4PiBO1ZB4BqM1nK6YunuLNl+H8YYVttiJGTRdJM8Oqwxeo+FpXh71YlnWRCQaDbRhgXtl8FrVh8RXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:48:46.191397Z"},"content_sha256":"93f06461c7efc8941693979246809357f39bb7eec8ef76381ff174670601e1b9","schema_version":"1.0","event_id":"sha256:93f06461c7efc8941693979246809357f39bb7eec8ef76381ff174670601e1b9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:XLQQIJJTPFGPCMQGG2V6JDUGXD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"When in Doubt, Summon the Titans: Efficient Inference with Large Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aditya Krishna Menon, Amr Ahmed, Ankit Singh Rawat, Manzil Zaheer, Sanjiv Kumar","submitted_at":"2021-10-19T22:56:49Z","abstract_excerpt":"Scaling neural networks to \"large\" sizes, with billions of parameters, has been shown to yield impressive results on many challenging problems. However, the inference cost incurred by such large models often prevents their application in most real-world settings. In this paper, we propose a two-stage framework based on distillation that realizes the modelling benefits of the large models, while largely preserving the computational benefits of inference with more lightweight models. In a nutshell, we use the large teacher models to guide the lightweight student models to only make correct predi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10305","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/2110.10305/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":"2026-07-05T03:24:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RrpTTIxBxQtoBz5K9ZfzRQcDhXMuENNjLqMy7pUqiVrwee/BGR7Cwvp9HbBquJfekmbQghkkt+atEj5BDhZBAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T16:48:46.192361Z"},"content_sha256":"893abf4f40c69c6220fb9b82344d753b76ae5b579f18d24b5c8f1c3b79366c4e","schema_version":"1.0","event_id":"sha256:893abf4f40c69c6220fb9b82344d753b76ae5b579f18d24b5c8f1c3b79366c4e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XLQQIJJTPFGPCMQGG2V6JDUGXD/bundle.json","state_url":"https://pith.science/pith/XLQQIJJTPFGPCMQGG2V6JDUGXD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XLQQIJJTPFGPCMQGG2V6JDUGXD/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":"2026-08-04T16:48:46Z","links":{"resolver":"https://pith.science/pith/XLQQIJJTPFGPCMQGG2V6JDUGXD","bundle":"https://pith.science/pith/XLQQIJJTPFGPCMQGG2V6JDUGXD/bundle.json","state":"https://pith.science/pith/XLQQIJJTPFGPCMQGG2V6JDUGXD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XLQQIJJTPFGPCMQGG2V6JDUGXD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:XLQQIJJTPFGPCMQGG2V6JDUGXD","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":"5a801ba6509eea61303625c80edc4f0245dd84ff0f046afe2810a7ac968dda50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T22:56:49Z","title_canon_sha256":"588348bf7ed17eb1922c5dee3a27d4871ecf5446b2c020ad044064fda50034dc"},"schema_version":"1.0","source":{"id":"2110.10305","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.10305","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"arxiv_version","alias_value":"2110.10305v1","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.10305","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_12","alias_value":"XLQQIJJTPFGP","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_16","alias_value":"XLQQIJJTPFGPCMQG","created_at":"2026-07-05T03:24:15Z"},{"alias_kind":"pith_short_8","alias_value":"XLQQIJJT","created_at":"2026-07-05T03:24:15Z"}],"graph_snapshots":[{"event_id":"sha256:893abf4f40c69c6220fb9b82344d753b76ae5b579f18d24b5c8f1c3b79366c4e","target":"graph","created_at":"2026-07-05T03:24:15Z","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/2110.10305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scaling neural networks to \"large\" sizes, with billions of parameters, has been shown to yield impressive results on many challenging problems. However, the inference cost incurred by such large models often prevents their application in most real-world settings. In this paper, we propose a two-stage framework based on distillation that realizes the modelling benefits of the large models, while largely preserving the computational benefits of inference with more lightweight models. In a nutshell, we use the large teacher models to guide the lightweight student models to only make correct predi","authors_text":"Aditya Krishna Menon, Amr Ahmed, Ankit Singh Rawat, Manzil Zaheer, Sanjiv Kumar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T22:56:49Z","title":"When in Doubt, Summon the Titans: Efficient Inference with Large Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.10305","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":"sha256:93f06461c7efc8941693979246809357f39bb7eec8ef76381ff174670601e1b9","target":"record","created_at":"2026-07-05T03:24:15Z","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":"5a801ba6509eea61303625c80edc4f0245dd84ff0f046afe2810a7ac968dda50","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2021-10-19T22:56:49Z","title_canon_sha256":"588348bf7ed17eb1922c5dee3a27d4871ecf5446b2c020ad044064fda50034dc"},"schema_version":"1.0","source":{"id":"2110.10305","kind":"arxiv","version":1}},"canonical_sha256":"bae1042533794cf1320636abe48e86b8c76fe4bb544331fb8bea01f73f286815","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bae1042533794cf1320636abe48e86b8c76fe4bb544331fb8bea01f73f286815","first_computed_at":"2026-07-05T03:24:15.633928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:24:15.633928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"20HAAT1ref8bDHKMMOhmHNHcCNpPxivbKbbNFtKFR98LWljjEKL6u45ZidviJXLzdhwQM07HgEcy+vi+gmsSCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:24:15.634249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.10305","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:93f06461c7efc8941693979246809357f39bb7eec8ef76381ff174670601e1b9","sha256:893abf4f40c69c6220fb9b82344d753b76ae5b579f18d24b5c8f1c3b79366c4e"],"state_sha256":"9609d8b03bab59386baa0230c2ff535223989d1120f7e49010754e83807f8e49"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ep2ZUlRRxw2EJUapiVU+o5FkMV6qCDHkDviSavcx64Y/trxiiRe1p+BrC5gva0w/LZDazjg6otr6UopkcnW5Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T16:48:46.198465Z","bundle_sha256":"5c5d3b70e9a7d9832a9e603963e78f3d522ec4afe6060baaff4c58a44da64080"}}