{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DIE34DSBU7JZLQ3GZPZRRQLQIY","short_pith_number":"pith:DIE34DSB","canonical_record":{"source":{"id":"2109.03137","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-07T15:06:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f2e1dcef318a2f3a5ef92a1a049d3aa9b5decb5a938f3a743f0ce4a3bdecff30","abstract_canon_sha256":"336c79a35cf80ddafd2dbae3abff82a2d20e74494cc2daa3b831bbf47bb10465"},"schema_version":"1.0"},"canonical_sha256":"1a09be0e41a7d395c366cbf318c170460b4540238596f4da091f9a27f00c2524","source":{"kind":"arxiv","id":"2109.03137","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.03137","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2109.03137v2","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03137","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"DIE34DSBU7JZ","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"DIE34DSBU7JZLQ3G","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"DIE34DSB","created_at":"2026-07-05T03:22:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DIE34DSBU7JZLQ3GZPZRRQLQIY","target":"record","payload":{"canonical_record":{"source":{"id":"2109.03137","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-07T15:06:12Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"f2e1dcef318a2f3a5ef92a1a049d3aa9b5decb5a938f3a743f0ce4a3bdecff30","abstract_canon_sha256":"336c79a35cf80ddafd2dbae3abff82a2d20e74494cc2daa3b831bbf47bb10465"},"schema_version":"1.0"},"canonical_sha256":"1a09be0e41a7d395c366cbf318c170460b4540238596f4da091f9a27f00c2524","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:23.943356Z","signature_b64":"jo6GSAz2aApvsRwBbOmB2NAazz72FIgOkjViG5A1VVvCdt/qja6GOJFwBCvsiwPXG3Pz+8bUXHW/64Wq39WKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1a09be0e41a7d395c366cbf318c170460b4540238596f4da091f9a27f00c2524","last_reissued_at":"2026-07-05T03:22:23.942874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:23.942874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.03137","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:22:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3dO7PUz/zjFS0DiPeK2TROINCNejvQCIXmB2r4EhE1e3iMQSdG2aQTXl41I3EgRQcEkMwKTq69vof3TnHw2MBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:17:04.872325Z"},"content_sha256":"7a1ce28c4afe249bedc8704dc98acd225997a6452f4fa981d60ae10958e26b43","schema_version":"1.0","event_id":"sha256:7a1ce28c4afe249bedc8704dc98acd225997a6452f4fa981d60ae10958e26b43"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DIE34DSBU7JZLQ3GZPZRRQLQIY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NumGPT: Improving Numeracy Ability of Generative Pre-trained Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Huamin Qu, Qun Liu, Xiaozhe Ren, Xingbo Wang, Xin Jiang, Yong Wang, Zhihua Jin","submitted_at":"2021-09-07T15:06:12Z","abstract_excerpt":"Existing generative pre-trained language models (e.g., GPT) focus on modeling the language structure and semantics of general texts. However, those models do not consider the numerical properties of numbers and cannot perform robustly on numerical reasoning tasks (e.g., math word problems and measurement estimation). In this paper, we propose NumGPT, a generative pre-trained model that explicitly models the numerical properties of numbers in texts. Specifically, it leverages a prototype-based numeral embedding to encode the mantissa of the number and an individual embedding to encode the expon"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03137","kind":"arxiv","version":2},"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/2109.03137/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":"2026-07-05T03:22:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NLKfxmOrX3iF12Aqz/QNPJqop6r351F5ALNs6nc/a3iOtXnBErIzgEPgXMXjLL+Zp8QVcs6pDCUp6WLwO604Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T22:17:04.873227Z"},"content_sha256":"80f0032919940e7a4b7ad493216dff647aedcd3ef41e5a3fa9ebab1f309c5160","schema_version":"1.0","event_id":"sha256:80f0032919940e7a4b7ad493216dff647aedcd3ef41e5a3fa9ebab1f309c5160"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DIE34DSBU7JZLQ3GZPZRRQLQIY/bundle.json","state_url":"https://pith.science/pith/DIE34DSBU7JZLQ3GZPZRRQLQIY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DIE34DSBU7JZLQ3GZPZRRQLQIY/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":"2026-08-07T22:17:04Z","links":{"resolver":"https://pith.science/pith/DIE34DSBU7JZLQ3GZPZRRQLQIY","bundle":"https://pith.science/pith/DIE34DSBU7JZLQ3GZPZRRQLQIY/bundle.json","state":"https://pith.science/pith/DIE34DSBU7JZLQ3GZPZRRQLQIY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DIE34DSBU7JZLQ3GZPZRRQLQIY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DIE34DSBU7JZLQ3GZPZRRQLQIY","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":"336c79a35cf80ddafd2dbae3abff82a2d20e74494cc2daa3b831bbf47bb10465","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-07T15:06:12Z","title_canon_sha256":"f2e1dcef318a2f3a5ef92a1a049d3aa9b5decb5a938f3a743f0ce4a3bdecff30"},"schema_version":"1.0","source":{"id":"2109.03137","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.03137","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"arxiv_version","alias_value":"2109.03137v2","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03137","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"pith_short_12","alias_value":"DIE34DSBU7JZ","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"pith_short_16","alias_value":"DIE34DSBU7JZLQ3G","created_at":"2026-07-05T03:22:23Z"},{"alias_kind":"pith_short_8","alias_value":"DIE34DSB","created_at":"2026-07-05T03:22:23Z"}],"graph_snapshots":[{"event_id":"sha256:80f0032919940e7a4b7ad493216dff647aedcd3ef41e5a3fa9ebab1f309c5160","target":"graph","created_at":"2026-07-05T03:22:23Z","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/2109.03137/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing generative pre-trained language models (e.g., GPT) focus on modeling the language structure and semantics of general texts. However, those models do not consider the numerical properties of numbers and cannot perform robustly on numerical reasoning tasks (e.g., math word problems and measurement estimation). In this paper, we propose NumGPT, a generative pre-trained model that explicitly models the numerical properties of numbers in texts. Specifically, it leverages a prototype-based numeral embedding to encode the mantissa of the number and an individual embedding to encode the expon","authors_text":"Huamin Qu, Qun Liu, Xiaozhe Ren, Xingbo Wang, Xin Jiang, Yong Wang, Zhihua Jin","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-07T15:06:12Z","title":"NumGPT: Improving Numeracy Ability of Generative Pre-trained Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03137","kind":"arxiv","version":2},"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":"sha256:7a1ce28c4afe249bedc8704dc98acd225997a6452f4fa981d60ae10958e26b43","target":"record","created_at":"2026-07-05T03:22:23Z","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":"336c79a35cf80ddafd2dbae3abff82a2d20e74494cc2daa3b831bbf47bb10465","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-07T15:06:12Z","title_canon_sha256":"f2e1dcef318a2f3a5ef92a1a049d3aa9b5decb5a938f3a743f0ce4a3bdecff30"},"schema_version":"1.0","source":{"id":"2109.03137","kind":"arxiv","version":2}},"canonical_sha256":"1a09be0e41a7d395c366cbf318c170460b4540238596f4da091f9a27f00c2524","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1a09be0e41a7d395c366cbf318c170460b4540238596f4da091f9a27f00c2524","first_computed_at":"2026-07-05T03:22:23.942874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:22:23.942874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jo6GSAz2aApvsRwBbOmB2NAazz72FIgOkjViG5A1VVvCdt/qja6GOJFwBCvsiwPXG3Pz+8bUXHW/64Wq39WKDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:22:23.943356Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.03137","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7a1ce28c4afe249bedc8704dc98acd225997a6452f4fa981d60ae10958e26b43","sha256:80f0032919940e7a4b7ad493216dff647aedcd3ef41e5a3fa9ebab1f309c5160"],"state_sha256":"4fbdd44ba105de095ac6691a7487855b000e9197c147af2b43ab235cac91eb2f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kL1KSSqru5hP/fbNM64KQftjeeiffuddsoRMIngmtuIA9j8QasX+ORG53PIW6XJUiMtf40AgK6zsEEByM7rMAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T22:17:04.878753Z","bundle_sha256":"ae40053c4b42614d87959d4b0eb5f03a6f36c4fbc3569c1e3e2f0edb0c58d9ce"}}