{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VOQHOXME4SMWIVCS6IMXQA43YF","short_pith_number":"pith:VOQHOXME","canonical_record":{"source":{"id":"2203.14380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-27T19:52:01Z","cross_cats_sorted":[],"title_canon_sha256":"8a9deedafca991f976325b6b76f7088e7e7b4bddebe2195240190a83d86f1843","abstract_canon_sha256":"d4ee8f714420a5ee6afc753d2ca4900e0b63a34f56cecd3eb97524be91c534d5"},"schema_version":"1.0"},"canonical_sha256":"aba0775d84e499645452f21978039bc163b0430f76391a3250f5306b39104623","source":{"kind":"arxiv","id":"2203.14380","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.14380","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"arxiv_version","alias_value":"2203.14380v1","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14380","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"pith_short_12","alias_value":"VOQHOXME4SMW","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"pith_short_16","alias_value":"VOQHOXME4SMWIVCS","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"pith_short_8","alias_value":"VOQHOXME","created_at":"2026-07-05T04:09:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VOQHOXME4SMWIVCS6IMXQA43YF","target":"record","payload":{"canonical_record":{"source":{"id":"2203.14380","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-27T19:52:01Z","cross_cats_sorted":[],"title_canon_sha256":"8a9deedafca991f976325b6b76f7088e7e7b4bddebe2195240190a83d86f1843","abstract_canon_sha256":"d4ee8f714420a5ee6afc753d2ca4900e0b63a34f56cecd3eb97524be91c534d5"},"schema_version":"1.0"},"canonical_sha256":"aba0775d84e499645452f21978039bc163b0430f76391a3250f5306b39104623","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:09:04.286128Z","signature_b64":"cYpONW5qKIZgjkXbASlZg7QdI+Hkf2JqMQlWxlVIn8m0l3GI7VISt8tlvpJzLPhoQwPt6UVJet/rO+5JM1ZbDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aba0775d84e499645452f21978039bc163b0430f76391a3250f5306b39104623","last_reissued_at":"2026-07-05T04:09:04.285709Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:09:04.285709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.14380","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":"2026-07-05T04:09:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z8lC+j3wnESCaNeIJjrokY5yCw6RhaEnD95va4l7cMfs/3EwDg2KaXsx+jBn+dIaV//7kFj/y5kheYO8jsy6BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:12:26.098868Z"},"content_sha256":"798f945bf19a2088afea9f1e598dcfe45b00b19e74f8d00d44d5218591d77957","schema_version":"1.0","event_id":"sha256:798f945bf19a2088afea9f1e598dcfe45b00b19e74f8d00d44d5218591d77957"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VOQHOXME4SMWIVCS6IMXQA43YF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ashish Khetan, Rene Bidart, Xin Huang, Zohar Karnin","submitted_at":"2022-03-27T19:52:01Z","abstract_excerpt":"Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive. A recent line of works use various heuristics to successively shorten sequence length while transforming tokens through encoders, in tasks such as classification and ranking that require a single token embedding for prediction. We present a novel solution to this problem, called Pyramid-BERT where we replace previously used heuristics with a {\\em core-set} based token selection method justified by theoretical results. The core-set based token "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14380","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/2203.14380/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":"2026-07-05T04:09:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Fi4IVAMzMhuNQ0weTve2DCTVN9F++70mUEX2gM0uhjjEvMsjhHvIZm04dYcZHpR0xrALFrOubTM650hx6rFnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:12:26.099242Z"},"content_sha256":"dd5fd9ba125e54b472a40d106e2773a4dbb297e975cfb94ea80f3dee0d5edb9d","schema_version":"1.0","event_id":"sha256:dd5fd9ba125e54b472a40d106e2773a4dbb297e975cfb94ea80f3dee0d5edb9d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VOQHOXME4SMWIVCS6IMXQA43YF/bundle.json","state_url":"https://pith.science/pith/VOQHOXME4SMWIVCS6IMXQA43YF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VOQHOXME4SMWIVCS6IMXQA43YF/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":"2026-07-07T12:12:26Z","links":{"resolver":"https://pith.science/pith/VOQHOXME4SMWIVCS6IMXQA43YF","bundle":"https://pith.science/pith/VOQHOXME4SMWIVCS6IMXQA43YF/bundle.json","state":"https://pith.science/pith/VOQHOXME4SMWIVCS6IMXQA43YF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VOQHOXME4SMWIVCS6IMXQA43YF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VOQHOXME4SMWIVCS6IMXQA43YF","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":"d4ee8f714420a5ee6afc753d2ca4900e0b63a34f56cecd3eb97524be91c534d5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-27T19:52:01Z","title_canon_sha256":"8a9deedafca991f976325b6b76f7088e7e7b4bddebe2195240190a83d86f1843"},"schema_version":"1.0","source":{"id":"2203.14380","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.14380","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"arxiv_version","alias_value":"2203.14380v1","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.14380","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"pith_short_12","alias_value":"VOQHOXME4SMW","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"pith_short_16","alias_value":"VOQHOXME4SMWIVCS","created_at":"2026-07-05T04:09:04Z"},{"alias_kind":"pith_short_8","alias_value":"VOQHOXME","created_at":"2026-07-05T04:09:04Z"}],"graph_snapshots":[{"event_id":"sha256:dd5fd9ba125e54b472a40d106e2773a4dbb297e975cfb94ea80f3dee0d5edb9d","target":"graph","created_at":"2026-07-05T04:09:04Z","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/2203.14380/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Transformer-based language models such as BERT have achieved the state-of-the-art performance on various NLP tasks, but are computationally prohibitive. A recent line of works use various heuristics to successively shorten sequence length while transforming tokens through encoders, in tasks such as classification and ranking that require a single token embedding for prediction. We present a novel solution to this problem, called Pyramid-BERT where we replace previously used heuristics with a {\\em core-set} based token selection method justified by theoretical results. The core-set based token ","authors_text":"Ashish Khetan, Rene Bidart, Xin Huang, Zohar Karnin","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-27T19:52:01Z","title":"Pyramid-BERT: Reducing Complexity via Successive Core-set based Token Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.14380","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":"sha256:798f945bf19a2088afea9f1e598dcfe45b00b19e74f8d00d44d5218591d77957","target":"record","created_at":"2026-07-05T04:09:04Z","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":"d4ee8f714420a5ee6afc753d2ca4900e0b63a34f56cecd3eb97524be91c534d5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2022-03-27T19:52:01Z","title_canon_sha256":"8a9deedafca991f976325b6b76f7088e7e7b4bddebe2195240190a83d86f1843"},"schema_version":"1.0","source":{"id":"2203.14380","kind":"arxiv","version":1}},"canonical_sha256":"aba0775d84e499645452f21978039bc163b0430f76391a3250f5306b39104623","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"aba0775d84e499645452f21978039bc163b0430f76391a3250f5306b39104623","first_computed_at":"2026-07-05T04:09:04.285709Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:09:04.285709Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cYpONW5qKIZgjkXbASlZg7QdI+Hkf2JqMQlWxlVIn8m0l3GI7VISt8tlvpJzLPhoQwPt6UVJet/rO+5JM1ZbDg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:09:04.286128Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.14380","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:798f945bf19a2088afea9f1e598dcfe45b00b19e74f8d00d44d5218591d77957","sha256:dd5fd9ba125e54b472a40d106e2773a4dbb297e975cfb94ea80f3dee0d5edb9d"],"state_sha256":"469372dce582d2731b66abb4aa78bcc0df9a6a2e7bd9b4004e6647d62c929ecf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EcYok97gHWdiXrp93dgQe7w0O/Xv8ZKb0+qRxB/L1rG2FrUgA4TmWRbSQd5V5bbIeolQqoEO0UTKeR+Pi7NRAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:12:26.101422Z","bundle_sha256":"3c13abf1fb713535ee55b9e976f11aedaf6b58a78dbf313efc2c6e8e51e17d40"}}