{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:YVPQDTP36NXXMA4OCZO43PNPUZ","short_pith_number":"pith:YVPQDTP3","canonical_record":{"source":{"id":"2312.17543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T10:18:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0f0a2d7630401fd1dc0e98d4d61acd05ea531917ff75718e09ce5f785e5e380f","abstract_canon_sha256":"571046c0a919ed96f2f2d4110969c378dc32f5349b31dceb05ee10144815a095"},"schema_version":"1.0"},"canonical_sha256":"c55f01cdfbf36f76038e165dcdbdafa659e2257014ddf57ee015c9a8ead5724d","source":{"kind":"arxiv","id":"2312.17543","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17543","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17543v2","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17543","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"YVPQDTP36NXX","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"YVPQDTP36NXXMA4O","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"YVPQDTP3","created_at":"2026-07-05T07:59:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:YVPQDTP36NXXMA4OCZO43PNPUZ","target":"record","payload":{"canonical_record":{"source":{"id":"2312.17543","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T10:18:36Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0f0a2d7630401fd1dc0e98d4d61acd05ea531917ff75718e09ce5f785e5e380f","abstract_canon_sha256":"571046c0a919ed96f2f2d4110969c378dc32f5349b31dceb05ee10144815a095"},"schema_version":"1.0"},"canonical_sha256":"c55f01cdfbf36f76038e165dcdbdafa659e2257014ddf57ee015c9a8ead5724d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:59:20.814256Z","signature_b64":"EXqKrS3ereXI/Es6aC0nv1nFha1xPYDUdJva8Y+W0LTrXpK+KsVEl8JylV51A54i3Rg8k1ZE3AR5WMI40YnwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c55f01cdfbf36f76038e165dcdbdafa659e2257014ddf57ee015c9a8ead5724d","last_reissued_at":"2026-07-05T07:59:20.813813Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:59:20.813813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2312.17543","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":"2026-07-05T07:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1qBQNg8UVqFhBXEIE74CPOfDHvNME9kvqME2VgK+DR+6NFSusqYMK2WwSMcfm3NDhpk3ZKKAyAXgjRZs0FapAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:30:43.660041Z"},"content_sha256":"797da29942e436b26b6192afff1a1d48142039c2f41fe5a2185e1da587fecf12","schema_version":"1.0","event_id":"sha256:797da29942e436b26b6192afff1a1d48142039c2f41fe5a2185e1da587fecf12"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:YVPQDTP36NXXMA4OCZO43PNPUZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Building Efficient Universal Classifiers with Natural Language Inference","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andreu Casas, Kasper Welbers, Moritz Laurer, Wouter van Atteveldt","submitted_at":"2023-12-29T10:18:36Z","abstract_excerpt":"Generative Large Language Models (LLMs) have become the mainstream choice for fewshot and zeroshot learning thanks to the universality of text generation. Many users, however, do not need the broad capabilities of generative LLMs when they only want to automate a classification task. Smaller BERT-like models can also learn universal tasks, which allow them to do any text classification task without requiring fine-tuning (zeroshot classification) or to learn new tasks with only a few examples (fewshot), while being significantly more efficient than generative LLMs. This paper (1) explains how N"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17543","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/2312.17543/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":"2026-07-05T07:59:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uS+9hLcx2MQXs6lzMoz22FwzSvPH4bpxjj5Bq5XvA2sVnywlNSSr7CQ1jHB4F8Gw3+kfnfGVphVsFtWKVQj7AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:30:43.660694Z"},"content_sha256":"b38de03fa8f818d0518525bc07f9b9cb157fc0effc23675f9bfb523b05e767dc","schema_version":"1.0","event_id":"sha256:b38de03fa8f818d0518525bc07f9b9cb157fc0effc23675f9bfb523b05e767dc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YVPQDTP36NXXMA4OCZO43PNPUZ/bundle.json","state_url":"https://pith.science/pith/YVPQDTP36NXXMA4OCZO43PNPUZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YVPQDTP36NXXMA4OCZO43PNPUZ/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":"2026-08-09T13:30:43Z","links":{"resolver":"https://pith.science/pith/YVPQDTP36NXXMA4OCZO43PNPUZ","bundle":"https://pith.science/pith/YVPQDTP36NXXMA4OCZO43PNPUZ/bundle.json","state":"https://pith.science/pith/YVPQDTP36NXXMA4OCZO43PNPUZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YVPQDTP36NXXMA4OCZO43PNPUZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:YVPQDTP36NXXMA4OCZO43PNPUZ","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":"571046c0a919ed96f2f2d4110969c378dc32f5349b31dceb05ee10144815a095","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T10:18:36Z","title_canon_sha256":"0f0a2d7630401fd1dc0e98d4d61acd05ea531917ff75718e09ce5f785e5e380f"},"schema_version":"1.0","source":{"id":"2312.17543","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.17543","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"arxiv_version","alias_value":"2312.17543v2","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.17543","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"pith_short_12","alias_value":"YVPQDTP36NXX","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"pith_short_16","alias_value":"YVPQDTP36NXXMA4O","created_at":"2026-07-05T07:59:20Z"},{"alias_kind":"pith_short_8","alias_value":"YVPQDTP3","created_at":"2026-07-05T07:59:20Z"}],"graph_snapshots":[{"event_id":"sha256:b38de03fa8f818d0518525bc07f9b9cb157fc0effc23675f9bfb523b05e767dc","target":"graph","created_at":"2026-07-05T07:59:20Z","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/2312.17543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generative Large Language Models (LLMs) have become the mainstream choice for fewshot and zeroshot learning thanks to the universality of text generation. Many users, however, do not need the broad capabilities of generative LLMs when they only want to automate a classification task. Smaller BERT-like models can also learn universal tasks, which allow them to do any text classification task without requiring fine-tuning (zeroshot classification) or to learn new tasks with only a few examples (fewshot), while being significantly more efficient than generative LLMs. This paper (1) explains how N","authors_text":"Andreu Casas, Kasper Welbers, Moritz Laurer, Wouter van Atteveldt","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T10:18:36Z","title":"Building Efficient Universal Classifiers with Natural Language Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.17543","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":"sha256:797da29942e436b26b6192afff1a1d48142039c2f41fe5a2185e1da587fecf12","target":"record","created_at":"2026-07-05T07:59:20Z","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":"571046c0a919ed96f2f2d4110969c378dc32f5349b31dceb05ee10144815a095","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-29T10:18:36Z","title_canon_sha256":"0f0a2d7630401fd1dc0e98d4d61acd05ea531917ff75718e09ce5f785e5e380f"},"schema_version":"1.0","source":{"id":"2312.17543","kind":"arxiv","version":2}},"canonical_sha256":"c55f01cdfbf36f76038e165dcdbdafa659e2257014ddf57ee015c9a8ead5724d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c55f01cdfbf36f76038e165dcdbdafa659e2257014ddf57ee015c9a8ead5724d","first_computed_at":"2026-07-05T07:59:20.813813Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:59:20.813813Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"EXqKrS3ereXI/Es6aC0nv1nFha1xPYDUdJva8Y+W0LTrXpK+KsVEl8JylV51A54i3Rg8k1ZE3AR5WMI40YnwBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:59:20.814256Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.17543","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:797da29942e436b26b6192afff1a1d48142039c2f41fe5a2185e1da587fecf12","sha256:b38de03fa8f818d0518525bc07f9b9cb157fc0effc23675f9bfb523b05e767dc"],"state_sha256":"970cd9dd91b0530e3b5cad9a052c200518c0f4382212683856e372fc3a29e2ad"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Iau07tuQ9+SZyBK7NpHidVp4gOO6vKwvYVOjkBW7GiAZgSz+5yLfg7UlKcCjEbuZbJGqqc+eLtFLSZRRnd/UAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:30:43.665735Z","bundle_sha256":"fc5639901ba2e3bb7c29b7969d4325a99dfa3f4e845b567c1ccc45c9d5047560"}}