{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:HPKDAGPFKP3PXQETYN23ZVO6WL","short_pith_number":"pith:HPKDAGPF","canonical_record":{"source":{"id":"2306.00014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:41:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"78747e5d15a7b0bb82232dcb59971eee187c1c5832fc41654f3db6d4a555b885","abstract_canon_sha256":"8d2fd4196b4a37e46f50fba2b0c49c779017e93e0a7fc54be08e3cd9b9c08851"},"schema_version":"1.0"},"canonical_sha256":"3bd43019e553f6fbc093c375bcd5deb2e9a23d6bf07c0e2fd574b793adf6e6df","source":{"kind":"arxiv","id":"2306.00014","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00014","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00014v1","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00014","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"HPKDAGPFKP3P","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"HPKDAGPFKP3PXQET","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"HPKDAGPF","created_at":"2026-07-05T06:16:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:HPKDAGPFKP3PXQETYN23ZVO6WL","target":"record","payload":{"canonical_record":{"source":{"id":"2306.00014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:41:33Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"78747e5d15a7b0bb82232dcb59971eee187c1c5832fc41654f3db6d4a555b885","abstract_canon_sha256":"8d2fd4196b4a37e46f50fba2b0c49c779017e93e0a7fc54be08e3cd9b9c08851"},"schema_version":"1.0"},"canonical_sha256":"3bd43019e553f6fbc093c375bcd5deb2e9a23d6bf07c0e2fd574b793adf6e6df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:20.308708Z","signature_b64":"lqWVumRu94OdlghqQ68ctk1AAIN1J47iK9vAVN18pxLVzXeNxmIu/ryxv0uWtdhIm0TRvELDrGCPDKG6VeHHBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bd43019e553f6fbc093c375bcd5deb2e9a23d6bf07c0e2fd574b793adf6e6df","last_reissued_at":"2026-07-05T06:16:20.308217Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:20.308217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2306.00014","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":"2026-07-05T06:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vJOzyJV8m11RWz/243DEvfIdH7o1P0pqUrul//+rOJ6Yrh/bTLJDQtWYBOPPGU9ffMRV4cwgoz/EsZSJu/3VCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:01:32.072761Z"},"content_sha256":"1173f6703ba6dc15fcb813130b57a9edbbd02f36a38c45815aa86033afc20c8d","schema_version":"1.0","event_id":"sha256:1173f6703ba6dc15fcb813130b57a9edbbd02f36a38c45815aa86033afc20c8d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:HPKDAGPFKP3PXQETYN23ZVO6WL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Dongyan Zhao, Jiahao Liu, Jingang Wang, Qifan Wang, Rui Yan, Wei Wu, Yang Yang, Yunsen Xian, Zhuocheng Gong","submitted_at":"2023-05-30T08:41:33Z","abstract_excerpt":"While transformer-based pre-trained language models (PLMs) have dominated a number of NLP applications, these models are heavy to deploy and expensive to use. Therefore, effectively compressing large-scale PLMs becomes an increasingly important problem. Quantization, which represents high-precision tensors with low-bit fix-point format, is a viable solution. However, most existing quantization methods are task-specific, requiring customized training and quantization with a large number of trainable parameters on each individual task. Inspired by the observation that the over-parameterization n"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00014","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/2306.00014/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":"2026-07-05T06:16:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rj42ypBrFMO5lTnUS36TYT9sgmqEmV7/zXUGp3ECYDOv7qAnPpgziQuL0SNKVu2eVlGDEH3JhqUh25Khv2HoAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:01:32.073139Z"},"content_sha256":"7161b964cd1bd5a03a119344210c11da37a444f7f7418d540221b9fdbf0b3430","schema_version":"1.0","event_id":"sha256:7161b964cd1bd5a03a119344210c11da37a444f7f7418d540221b9fdbf0b3430"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HPKDAGPFKP3PXQETYN23ZVO6WL/bundle.json","state_url":"https://pith.science/pith/HPKDAGPFKP3PXQETYN23ZVO6WL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HPKDAGPFKP3PXQETYN23ZVO6WL/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":"2026-07-07T10:01:32Z","links":{"resolver":"https://pith.science/pith/HPKDAGPFKP3PXQETYN23ZVO6WL","bundle":"https://pith.science/pith/HPKDAGPFKP3PXQETYN23ZVO6WL/bundle.json","state":"https://pith.science/pith/HPKDAGPFKP3PXQETYN23ZVO6WL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HPKDAGPFKP3PXQETYN23ZVO6WL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:HPKDAGPFKP3PXQETYN23ZVO6WL","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":"8d2fd4196b4a37e46f50fba2b0c49c779017e93e0a7fc54be08e3cd9b9c08851","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:41:33Z","title_canon_sha256":"78747e5d15a7b0bb82232dcb59971eee187c1c5832fc41654f3db6d4a555b885"},"schema_version":"1.0","source":{"id":"2306.00014","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.00014","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"arxiv_version","alias_value":"2306.00014v1","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.00014","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"pith_short_12","alias_value":"HPKDAGPFKP3P","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"pith_short_16","alias_value":"HPKDAGPFKP3PXQET","created_at":"2026-07-05T06:16:20Z"},{"alias_kind":"pith_short_8","alias_value":"HPKDAGPF","created_at":"2026-07-05T06:16:20Z"}],"graph_snapshots":[{"event_id":"sha256:7161b964cd1bd5a03a119344210c11da37a444f7f7418d540221b9fdbf0b3430","target":"graph","created_at":"2026-07-05T06:16:20Z","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/2306.00014/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While transformer-based pre-trained language models (PLMs) have dominated a number of NLP applications, these models are heavy to deploy and expensive to use. Therefore, effectively compressing large-scale PLMs becomes an increasingly important problem. Quantization, which represents high-precision tensors with low-bit fix-point format, is a viable solution. However, most existing quantization methods are task-specific, requiring customized training and quantization with a large number of trainable parameters on each individual task. Inspired by the observation that the over-parameterization n","authors_text":"Dongyan Zhao, Jiahao Liu, Jingang Wang, Qifan Wang, Rui Yan, Wei Wu, Yang Yang, Yunsen Xian, Zhuocheng Gong","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:41:33Z","title":"PreQuant: A Task-agnostic Quantization Approach for Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.00014","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":"sha256:1173f6703ba6dc15fcb813130b57a9edbbd02f36a38c45815aa86033afc20c8d","target":"record","created_at":"2026-07-05T06:16:20Z","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":"8d2fd4196b4a37e46f50fba2b0c49c779017e93e0a7fc54be08e3cd9b9c08851","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T08:41:33Z","title_canon_sha256":"78747e5d15a7b0bb82232dcb59971eee187c1c5832fc41654f3db6d4a555b885"},"schema_version":"1.0","source":{"id":"2306.00014","kind":"arxiv","version":1}},"canonical_sha256":"3bd43019e553f6fbc093c375bcd5deb2e9a23d6bf07c0e2fd574b793adf6e6df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3bd43019e553f6fbc093c375bcd5deb2e9a23d6bf07c0e2fd574b793adf6e6df","first_computed_at":"2026-07-05T06:16:20.308217Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:16:20.308217Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lqWVumRu94OdlghqQ68ctk1AAIN1J47iK9vAVN18pxLVzXeNxmIu/ryxv0uWtdhIm0TRvELDrGCPDKG6VeHHBg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:16:20.308708Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.00014","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1173f6703ba6dc15fcb813130b57a9edbbd02f36a38c45815aa86033afc20c8d","sha256:7161b964cd1bd5a03a119344210c11da37a444f7f7418d540221b9fdbf0b3430"],"state_sha256":"5ecb6b0696828046984181cc499b8a97a98df68044ff17ba9f0193ae526a1ec2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wVH7JN8q8F0qYsG+arYCjmGfSUTrYyzH70kzgYIdOVyElIfeSrpgzwrDnjjEQ3tuVLh5VyKqr08aAN4gbdIUBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:01:32.075420Z","bundle_sha256":"73ca419eca1ade0268195b9fe975f954c52447a6f06cc0fa328b8fc0eedaa5d9"}}