{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:6EP2RER6NJYYEMW3CRKB7CCA7B","short_pith_number":"pith:6EP2RER6","canonical_record":{"source":{"id":"2301.08721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-19T02:29:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"438f7c5fcc2dfa51ee2e5c2d28c3dd864b8bd7ba5f5842304f742d830e2219f0","abstract_canon_sha256":"11c1573274e048ebcbc5278e199848ea3094a3fbad82d3ef76e10cb7155e7dbc"},"schema_version":"1.0"},"canonical_sha256":"f11fa8923e6a718232db14541f8840f84aef5a8f902abd3ed9d7eeb2512f89d1","source":{"kind":"arxiv","id":"2301.08721","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08721","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08721v2","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08721","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"6EP2RER6NJYY","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"6EP2RER6NJYYEMW3","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"6EP2RER6","created_at":"2026-07-05T07:04:12Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:6EP2RER6NJYYEMW3CRKB7CCA7B","target":"record","payload":{"canonical_record":{"source":{"id":"2301.08721","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-19T02:29:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"438f7c5fcc2dfa51ee2e5c2d28c3dd864b8bd7ba5f5842304f742d830e2219f0","abstract_canon_sha256":"11c1573274e048ebcbc5278e199848ea3094a3fbad82d3ef76e10cb7155e7dbc"},"schema_version":"1.0"},"canonical_sha256":"f11fa8923e6a718232db14541f8840f84aef5a8f902abd3ed9d7eeb2512f89d1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:12.337709Z","signature_b64":"2rBBFbEARvmBqgMUMDsCpcwvoPyQxdvcGqRMXM7xklU4Q29DVeKRNcWKqfcQKDxFCm5Mt5/smw0zF6kF7YeZDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f11fa8923e6a718232db14541f8840f84aef5a8f902abd3ed9d7eeb2512f89d1","last_reissued_at":"2026-07-05T07:04:12.337206Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:12.337206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.08721","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":"2026-07-05T07:04:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YCIVxlqY4ARfVT0xw2Pos7VQ3x+0Gcyvh26nrXRLWOU7sxzCQrZ8Hqx1NNB9vcvmVOQC61Coalcb+VU8F+maDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:12:51.878672Z"},"content_sha256":"28d8a0f9beb9f0db261274fe0afc98dbd129fb9bba379fee92e1f0d02abd522a","schema_version":"1.0","event_id":"sha256:28d8a0f9beb9f0db261274fe0afc98dbd129fb9bba379fee92e1f0d02abd522a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:6EP2RER6NJYYEMW3CRKB7CCA7B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Batch Prompting: Efficient Inference with Large Language Model APIs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jungo Kasai, Tao Yu, Zhoujun Cheng","submitted_at":"2023-01-19T02:29:23Z","abstract_excerpt":"Performing inference on large volumes of samples with large language models (LLMs) can be computationally and financially costly in industry and real-world use. We propose batch prompting, a simple yet effective prompting approach that enables the LLM to run inference in batches, instead of one sample at a time. Our method reduces both token and time costs while retaining downstream performance. We theoretically demonstrate that under a few-shot in-context learning setting, the inference costs decrease almost inverse linearly with the number of samples in each batch. We extensively validate th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08721","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/2301.08721/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":"2026-07-05T07:04:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2GEmYLhRzJ1RNUz6lf8N/JTNif4/vWAKhTFyDooPCbtBRtiGXC+41ZPQXKiNyNHJuw2X0671fncn1V2bcW/MCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T06:12:51.879433Z"},"content_sha256":"3c291c12d20c4fdc7db11c7672642d839107d10c1a5978afef88d591347c8840","schema_version":"1.0","event_id":"sha256:3c291c12d20c4fdc7db11c7672642d839107d10c1a5978afef88d591347c8840"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EP2RER6NJYYEMW3CRKB7CCA7B/bundle.json","state_url":"https://pith.science/pith/6EP2RER6NJYYEMW3CRKB7CCA7B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EP2RER6NJYYEMW3CRKB7CCA7B/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":"2026-08-16T06:12:51Z","links":{"resolver":"https://pith.science/pith/6EP2RER6NJYYEMW3CRKB7CCA7B","bundle":"https://pith.science/pith/6EP2RER6NJYYEMW3CRKB7CCA7B/bundle.json","state":"https://pith.science/pith/6EP2RER6NJYYEMW3CRKB7CCA7B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EP2RER6NJYYEMW3CRKB7CCA7B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:6EP2RER6NJYYEMW3CRKB7CCA7B","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":"11c1573274e048ebcbc5278e199848ea3094a3fbad82d3ef76e10cb7155e7dbc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-19T02:29:23Z","title_canon_sha256":"438f7c5fcc2dfa51ee2e5c2d28c3dd864b8bd7ba5f5842304f742d830e2219f0"},"schema_version":"1.0","source":{"id":"2301.08721","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.08721","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"arxiv_version","alias_value":"2301.08721v2","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.08721","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"pith_short_12","alias_value":"6EP2RER6NJYY","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"pith_short_16","alias_value":"6EP2RER6NJYYEMW3","created_at":"2026-07-05T07:04:12Z"},{"alias_kind":"pith_short_8","alias_value":"6EP2RER6","created_at":"2026-07-05T07:04:12Z"}],"graph_snapshots":[{"event_id":"sha256:3c291c12d20c4fdc7db11c7672642d839107d10c1a5978afef88d591347c8840","target":"graph","created_at":"2026-07-05T07:04:12Z","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/2301.08721/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Performing inference on large volumes of samples with large language models (LLMs) can be computationally and financially costly in industry and real-world use. We propose batch prompting, a simple yet effective prompting approach that enables the LLM to run inference in batches, instead of one sample at a time. Our method reduces both token and time costs while retaining downstream performance. We theoretically demonstrate that under a few-shot in-context learning setting, the inference costs decrease almost inverse linearly with the number of samples in each batch. We extensively validate th","authors_text":"Jungo Kasai, Tao Yu, Zhoujun Cheng","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-19T02:29:23Z","title":"Batch Prompting: Efficient Inference with Large Language Model APIs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.08721","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":"sha256:28d8a0f9beb9f0db261274fe0afc98dbd129fb9bba379fee92e1f0d02abd522a","target":"record","created_at":"2026-07-05T07:04:12Z","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":"11c1573274e048ebcbc5278e199848ea3094a3fbad82d3ef76e10cb7155e7dbc","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-01-19T02:29:23Z","title_canon_sha256":"438f7c5fcc2dfa51ee2e5c2d28c3dd864b8bd7ba5f5842304f742d830e2219f0"},"schema_version":"1.0","source":{"id":"2301.08721","kind":"arxiv","version":2}},"canonical_sha256":"f11fa8923e6a718232db14541f8840f84aef5a8f902abd3ed9d7eeb2512f89d1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f11fa8923e6a718232db14541f8840f84aef5a8f902abd3ed9d7eeb2512f89d1","first_computed_at":"2026-07-05T07:04:12.337206Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:12.337206Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2rBBFbEARvmBqgMUMDsCpcwvoPyQxdvcGqRMXM7xklU4Q29DVeKRNcWKqfcQKDxFCm5Mt5/smw0zF6kF7YeZDA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:12.337709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.08721","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:28d8a0f9beb9f0db261274fe0afc98dbd129fb9bba379fee92e1f0d02abd522a","sha256:3c291c12d20c4fdc7db11c7672642d839107d10c1a5978afef88d591347c8840"],"state_sha256":"9b602bc112d22bdae2b5c33eab73f0e5c177b251b297830447e63d7656183f37"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WrZIYSayysjvKWc4CfPnZYVMQYZOH+RFKXJ41xUS03Msd9EMLegrXJ9SmvyNl1VT0T/RNrYRTfav5GjJsFl4Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T06:12:51.884917Z","bundle_sha256":"8266d304734e63e85a481f8d896f7afd20172e5f23451f427ee0a9cc842196ce"}}