{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:QRUSJR5KE5YR5AAPB2P6NDAW2Y","short_pith_number":"pith:QRUSJR5K","canonical_record":{"source":{"id":"2410.22480","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T19:17:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14e0957ee3e4beb1b2280956ce37a5a1bbe92f9c238786a4a60eda331b40ec74","abstract_canon_sha256":"3f844044c622ca130fdde53c5a26c64abf0f11f1fae4609d43ca425113b1bd59"},"schema_version":"1.0"},"canonical_sha256":"846924c7aa27711e800f0e9fe68c16d63e9b2f28be0f340145c5cdf0acb2864b","source":{"kind":"arxiv","id":"2410.22480","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22480","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22480v1","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22480","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"pith_short_12","alias_value":"QRUSJR5KE5YR","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"pith_short_16","alias_value":"QRUSJR5KE5YR5AAP","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"pith_short_8","alias_value":"QRUSJR5K","created_at":"2026-07-05T09:28:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:QRUSJR5KE5YR5AAPB2P6NDAW2Y","target":"record","payload":{"canonical_record":{"source":{"id":"2410.22480","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T19:17:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"14e0957ee3e4beb1b2280956ce37a5a1bbe92f9c238786a4a60eda331b40ec74","abstract_canon_sha256":"3f844044c622ca130fdde53c5a26c64abf0f11f1fae4609d43ca425113b1bd59"},"schema_version":"1.0"},"canonical_sha256":"846924c7aa27711e800f0e9fe68c16d63e9b2f28be0f340145c5cdf0acb2864b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:17.260011Z","signature_b64":"im3vY3ovk62x5pZ/X6hWpWSl/1a18fVb8Zi16vNmTu6PijZewDPhphaDkSxAvnlwEtWB2x+7LK+yj8WNN93aCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"846924c7aa27711e800f0e9fe68c16d63e9b2f28be0f340145c5cdf0acb2864b","last_reissued_at":"2026-07-05T09:28:17.259562Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:17.259562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.22480","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":"2026-07-05T09:28:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pk/sbP0Wdxn5SFzBce5oFMyk4oz6OxgYOLD4+0lBwvyiQJm7Iq7FYAuWy/MH12nwhyd7/EyQnhPqjvV6l0YCBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:13:04.149081Z"},"content_sha256":"724b6568110f6b81417900675a662a4fac5b7b59494b26b952e3fe30597b3cbc","schema_version":"1.0","event_id":"sha256:724b6568110f6b81417900675a662a4fac5b7b59494b26b952e3fe30597b3cbc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:QRUSJR5KE5YR5AAPB2P6NDAW2Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling LLM Inference with Optimized Sample Compute Allocation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Danqing Wang, Kexun Zhang, Lei Li, Shang Zhou, William Yang Wang","submitted_at":"2024-10-29T19:17:55Z","abstract_excerpt":"Sampling is a basic operation in many inference-time algorithms of large language models (LLMs). To scale up inference efficiently with a limited compute, it is crucial to find an optimal allocation for sample compute budgets: Which sampling configurations (model, temperature, language, etc.) do we use? How many samples do we generate in each configuration? We formulate these choices as a learning problem and propose OSCA, an algorithm that Optimizes Sample Compute Allocation by finding an optimal mix of different inference configurations. Our experiments show that with our learned mixed alloc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22480","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/2410.22480/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":"2026-07-05T09:28:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yIpZUNXbLvLVTKYQw5ro9QgZhVPvJjVy91QOQkVMRLefJ4qXoSpszBeSPp01kX6NAlS6RdkjkERErGqjaQvdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T11:13:04.149601Z"},"content_sha256":"58ec98ba58aa44975ea8320f68a2d7e2fee4e4defa803a468373482e2ea45a2a","schema_version":"1.0","event_id":"sha256:58ec98ba58aa44975ea8320f68a2d7e2fee4e4defa803a468373482e2ea45a2a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QRUSJR5KE5YR5AAPB2P6NDAW2Y/bundle.json","state_url":"https://pith.science/pith/QRUSJR5KE5YR5AAPB2P6NDAW2Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QRUSJR5KE5YR5AAPB2P6NDAW2Y/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":"2026-08-05T11:13:04Z","links":{"resolver":"https://pith.science/pith/QRUSJR5KE5YR5AAPB2P6NDAW2Y","bundle":"https://pith.science/pith/QRUSJR5KE5YR5AAPB2P6NDAW2Y/bundle.json","state":"https://pith.science/pith/QRUSJR5KE5YR5AAPB2P6NDAW2Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QRUSJR5KE5YR5AAPB2P6NDAW2Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QRUSJR5KE5YR5AAPB2P6NDAW2Y","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":"3f844044c622ca130fdde53c5a26c64abf0f11f1fae4609d43ca425113b1bd59","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T19:17:55Z","title_canon_sha256":"14e0957ee3e4beb1b2280956ce37a5a1bbe92f9c238786a4a60eda331b40ec74"},"schema_version":"1.0","source":{"id":"2410.22480","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.22480","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"arxiv_version","alias_value":"2410.22480v1","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.22480","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"pith_short_12","alias_value":"QRUSJR5KE5YR","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"pith_short_16","alias_value":"QRUSJR5KE5YR5AAP","created_at":"2026-07-05T09:28:17Z"},{"alias_kind":"pith_short_8","alias_value":"QRUSJR5K","created_at":"2026-07-05T09:28:17Z"}],"graph_snapshots":[{"event_id":"sha256:58ec98ba58aa44975ea8320f68a2d7e2fee4e4defa803a468373482e2ea45a2a","target":"graph","created_at":"2026-07-05T09:28:17Z","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/2410.22480/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sampling is a basic operation in many inference-time algorithms of large language models (LLMs). To scale up inference efficiently with a limited compute, it is crucial to find an optimal allocation for sample compute budgets: Which sampling configurations (model, temperature, language, etc.) do we use? How many samples do we generate in each configuration? We formulate these choices as a learning problem and propose OSCA, an algorithm that Optimizes Sample Compute Allocation by finding an optimal mix of different inference configurations. Our experiments show that with our learned mixed alloc","authors_text":"Danqing Wang, Kexun Zhang, Lei Li, Shang Zhou, William Yang Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T19:17:55Z","title":"Scaling LLM Inference with Optimized Sample Compute Allocation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.22480","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":"sha256:724b6568110f6b81417900675a662a4fac5b7b59494b26b952e3fe30597b3cbc","target":"record","created_at":"2026-07-05T09:28:17Z","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":"3f844044c622ca130fdde53c5a26c64abf0f11f1fae4609d43ca425113b1bd59","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-10-29T19:17:55Z","title_canon_sha256":"14e0957ee3e4beb1b2280956ce37a5a1bbe92f9c238786a4a60eda331b40ec74"},"schema_version":"1.0","source":{"id":"2410.22480","kind":"arxiv","version":1}},"canonical_sha256":"846924c7aa27711e800f0e9fe68c16d63e9b2f28be0f340145c5cdf0acb2864b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"846924c7aa27711e800f0e9fe68c16d63e9b2f28be0f340145c5cdf0acb2864b","first_computed_at":"2026-07-05T09:28:17.259562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:17.259562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"im3vY3ovk62x5pZ/X6hWpWSl/1a18fVb8Zi16vNmTu6PijZewDPhphaDkSxAvnlwEtWB2x+7LK+yj8WNN93aCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:17.260011Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.22480","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:724b6568110f6b81417900675a662a4fac5b7b59494b26b952e3fe30597b3cbc","sha256:58ec98ba58aa44975ea8320f68a2d7e2fee4e4defa803a468373482e2ea45a2a"],"state_sha256":"3e9a62734be26b87fca340b16bd2175bd9a900c7390ba8a7613e7c9a3cde2004"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I1c54KuqNwm99BWInPEZAWtOUuh0ctVDFQDyjusoOZIfonZt8yS+m5MWgWOPbEz6eoG1ogvuBdNv/hxxs1O7BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T11:13:04.155502Z","bundle_sha256":"19c2f4a187895e0208c1d51e7cce3c59b0d67539827f0dff35eda6d0be352186"}}