{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:33KSSHVYXMZAQLSDFUALVWJ5OT","short_pith_number":"pith:33KSSHVY","canonical_record":{"source":{"id":"2306.02379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T15:26:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19d92dfc31f8d941845ba30ca7010e33ac16a848104aeaba6147f055acaa8448","abstract_canon_sha256":"3671f19be0bb28e4c83bf7871c82e0dd7bfa97655228eae0154000fbdc5c5aa5"},"schema_version":"1.0"},"canonical_sha256":"ded5291eb8bb32082e432d00bad93d74c76faa15bd422e79052f224ff3a8fc65","source":{"kind":"arxiv","id":"2306.02379","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02379","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02379v1","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02379","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"33KSSHVYXMZA","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"pith_short_16","alias_value":"33KSSHVYXMZAQLSD","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"pith_short_8","alias_value":"33KSSHVY","created_at":"2026-07-05T06:17:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:33KSSHVYXMZAQLSDFUALVWJ5OT","target":"record","payload":{"canonical_record":{"source":{"id":"2306.02379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T15:26:28Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"19d92dfc31f8d941845ba30ca7010e33ac16a848104aeaba6147f055acaa8448","abstract_canon_sha256":"3671f19be0bb28e4c83bf7871c82e0dd7bfa97655228eae0154000fbdc5c5aa5"},"schema_version":"1.0"},"canonical_sha256":"ded5291eb8bb32082e432d00bad93d74c76faa15bd422e79052f224ff3a8fc65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:16.595283Z","signature_b64":"OfviVeupc0WrbYI/wno3KFBe/LeoXLjxviwKaKMS0EDO+L+OJ+7rm1k/TYBFID+315liTkn8tScD/t0w9uoJDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ded5291eb8bb32082e432d00bad93d74c76faa15bd422e79052f224ff3a8fc65","last_reissued_at":"2026-07-05T06:17:16.594810Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:16.594810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.02379","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":"2026-07-05T06:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qVtMaCM150GttfyF5paf3UNt5ceETxgEZXbE+E/kxzjqDF5T/bzi/QPCmg7FALpeCc1J8kvIRsCpdOvYoy9cCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T08:29:44.005759Z"},"content_sha256":"4cdde5819048ddd96933b5841bdcbb591d018a23215422d7d253c14eab08939c","schema_version":"1.0","event_id":"sha256:4cdde5819048ddd96933b5841bdcbb591d018a23215422d7d253c14eab08939c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:33KSSHVYXMZAQLSDFUALVWJ5OT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ronan Le Bras, Wangchunshu Zhou, Yejin Choi","submitted_at":"2023-06-04T15:26:28Z","abstract_excerpt":"Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network compression techniques such as knowledge distillation or quantization are limited to static compression where the compression ratio is fixed. In this paper, we introduce Modular Transformers, a modularized encoder-decoder framework for flexible sequence-to-sequence model compression. Modular Transformers train modularized layers that have the same function "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02379","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/2306.02379/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":"2026-07-05T06:17:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ABzXB/bFioBiHHSpsKBy1F3/ThxHpQL7R1Cad/tEYWsuIRds9m1j49TojmYoWSY6yNo8kNOV+Ji3zlK6DUHiCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-17T08:29:44.006134Z"},"content_sha256":"9ca127d30433496a2718351d72d7bd910e483946d645f699629f556bd952eccb","schema_version":"1.0","event_id":"sha256:9ca127d30433496a2718351d72d7bd910e483946d645f699629f556bd952eccb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/33KSSHVYXMZAQLSDFUALVWJ5OT/bundle.json","state_url":"https://pith.science/pith/33KSSHVYXMZAQLSDFUALVWJ5OT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/33KSSHVYXMZAQLSDFUALVWJ5OT/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":"2026-07-17T08:29:44Z","links":{"resolver":"https://pith.science/pith/33KSSHVYXMZAQLSDFUALVWJ5OT","bundle":"https://pith.science/pith/33KSSHVYXMZAQLSDFUALVWJ5OT/bundle.json","state":"https://pith.science/pith/33KSSHVYXMZAQLSDFUALVWJ5OT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/33KSSHVYXMZAQLSDFUALVWJ5OT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:33KSSHVYXMZAQLSDFUALVWJ5OT","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":"3671f19be0bb28e4c83bf7871c82e0dd7bfa97655228eae0154000fbdc5c5aa5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T15:26:28Z","title_canon_sha256":"19d92dfc31f8d941845ba30ca7010e33ac16a848104aeaba6147f055acaa8448"},"schema_version":"1.0","source":{"id":"2306.02379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.02379","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"arxiv_version","alias_value":"2306.02379v1","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.02379","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"pith_short_12","alias_value":"33KSSHVYXMZA","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"pith_short_16","alias_value":"33KSSHVYXMZAQLSD","created_at":"2026-07-05T06:17:16Z"},{"alias_kind":"pith_short_8","alias_value":"33KSSHVY","created_at":"2026-07-05T06:17:16Z"}],"graph_snapshots":[{"event_id":"sha256:9ca127d30433496a2718351d72d7bd910e483946d645f699629f556bd952eccb","target":"graph","created_at":"2026-07-05T06:17:16Z","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/2306.02379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Pre-trained Transformer models like T5 and BART have advanced the state of the art on a wide range of text generation tasks. Compressing these models into smaller ones has become critically important for practical use. Common neural network compression techniques such as knowledge distillation or quantization are limited to static compression where the compression ratio is fixed. In this paper, we introduce Modular Transformers, a modularized encoder-decoder framework for flexible sequence-to-sequence model compression. Modular Transformers train modularized layers that have the same function ","authors_text":"Ronan Le Bras, Wangchunshu Zhou, Yejin Choi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T15:26:28Z","title":"Modular Transformers: Compressing Transformers into Modularized Layers for Flexible Efficient Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.02379","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":"sha256:4cdde5819048ddd96933b5841bdcbb591d018a23215422d7d253c14eab08939c","target":"record","created_at":"2026-07-05T06:17:16Z","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":"3671f19be0bb28e4c83bf7871c82e0dd7bfa97655228eae0154000fbdc5c5aa5","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-06-04T15:26:28Z","title_canon_sha256":"19d92dfc31f8d941845ba30ca7010e33ac16a848104aeaba6147f055acaa8448"},"schema_version":"1.0","source":{"id":"2306.02379","kind":"arxiv","version":1}},"canonical_sha256":"ded5291eb8bb32082e432d00bad93d74c76faa15bd422e79052f224ff3a8fc65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ded5291eb8bb32082e432d00bad93d74c76faa15bd422e79052f224ff3a8fc65","first_computed_at":"2026-07-05T06:17:16.594810Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:16.594810Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"OfviVeupc0WrbYI/wno3KFBe/LeoXLjxviwKaKMS0EDO+L+OJ+7rm1k/TYBFID+315liTkn8tScD/t0w9uoJDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:16.595283Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.02379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4cdde5819048ddd96933b5841bdcbb591d018a23215422d7d253c14eab08939c","sha256:9ca127d30433496a2718351d72d7bd910e483946d645f699629f556bd952eccb"],"state_sha256":"8e97ea75291332e5711e94d4c9226f263b621b2d54faae5416dfaf2fa63c86db"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ETc6OCwPWiMHjLJiT9E1rWl4FMmvuOkrlL6mlGi3ZzzZpXEE2cTWxwef360QqxvZ4pNIWlvQbRMEfrY5SbUMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-17T08:29:44.008262Z","bundle_sha256":"69c830c2347d51eea9adfc81cbe50916b8a1e27d66c3ebe03b4f5cd4bcc09807"}}