{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3WYKEHWNJAKVYZ7EYVRMWYT7XM","short_pith_number":"pith:3WYKEHWN","canonical_record":{"source":{"id":"2406.16838","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T17:45:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d3e1ae5d6b56becc18af63994321e7934f299af1dca9d3dcd4a725f15291b68","abstract_canon_sha256":"a487220e1494c4bdc6c0d5b32a11d82f1a9ea18669a7009d64f2cadf1e9b0678"},"schema_version":"1.0"},"canonical_sha256":"ddb0a21ecd48155c67e4c562cb627fbb03cec454b6ad3702ae99c7e73c40fd4e","source":{"kind":"arxiv","id":"2406.16838","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16838","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16838v2","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16838","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"3WYKEHWNJAKV","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"pith_short_16","alias_value":"3WYKEHWNJAKVYZ7E","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"pith_short_8","alias_value":"3WYKEHWN","created_at":"2026-07-05T09:38:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3WYKEHWNJAKVYZ7EYVRMWYT7XM","target":"record","payload":{"canonical_record":{"source":{"id":"2406.16838","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T17:45:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d3e1ae5d6b56becc18af63994321e7934f299af1dca9d3dcd4a725f15291b68","abstract_canon_sha256":"a487220e1494c4bdc6c0d5b32a11d82f1a9ea18669a7009d64f2cadf1e9b0678"},"schema_version":"1.0"},"canonical_sha256":"ddb0a21ecd48155c67e4c562cb627fbb03cec454b6ad3702ae99c7e73c40fd4e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:38:15.170306Z","signature_b64":"95oy2hxLdRuA6PVoUmVaRJmKqk47WGR6W4c5NbtWFsVfaTy3mAJ0sinSiojJIRVn9liypyWoJ/qgk2gziO+7Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddb0a21ecd48155c67e4c562cb627fbb03cec454b6ad3702ae99c7e73c40fd4e","last_reissued_at":"2026-07-05T09:38:15.169800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:38:15.169800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.16838","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":"2026-07-05T09:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HpIJ31kKybreteM7QTNqbxJ0XY0CObcAjbwI1PnjoyS6YFrTiQTBm6jZsGBUy5QmPbm5ZRg2yjPteRXMoiLeCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:16:18.536811Z"},"content_sha256":"52739ea55ae2441bfb636cad8b20b65de62dcc37acc2378f6dfe0d71d84d525c","schema_version":"1.0","event_id":"sha256:52739ea55ae2441bfb636cad8b20b65de62dcc37acc2378f6dfe0d71d84d525c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3WYKEHWNJAKVYZ7EYVRMWYT7XM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Alex Xie, Amanda Bertsch, Graham Neubig, Hailey Schoelkopf, Ilia Kulikov, Matthew Finlayson, Sean Welleck, Zaid Harchaoui","submitted_at":"2024-06-24T17:45:59Z","abstract_excerpt":"One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during inference. This survey focuses on these inference-time approaches. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms, and efficient generation. Token-level generation algorithms, often called decoding algorithms, operate by sampling a single token at a time or constructing a token-level sea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16838","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/2406.16838/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":"2026-07-05T09:38:15Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"a/JQCqnRVNczr4SAP7IUzcO8wpyO/YuxDLaB7Kn0m5WHUyYwY/SIrcrkVPby3yfY409Z8BVOZquCzhPkSxtlDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T12:16:18.537351Z"},"content_sha256":"f43f53a5e723f71232c331791ce5b52a3dc655f6fc01cc573a63a76aa61b1605","schema_version":"1.0","event_id":"sha256:f43f53a5e723f71232c331791ce5b52a3dc655f6fc01cc573a63a76aa61b1605"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3WYKEHWNJAKVYZ7EYVRMWYT7XM/bundle.json","state_url":"https://pith.science/pith/3WYKEHWNJAKVYZ7EYVRMWYT7XM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3WYKEHWNJAKVYZ7EYVRMWYT7XM/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":"2026-08-07T12:16:18Z","links":{"resolver":"https://pith.science/pith/3WYKEHWNJAKVYZ7EYVRMWYT7XM","bundle":"https://pith.science/pith/3WYKEHWNJAKVYZ7EYVRMWYT7XM/bundle.json","state":"https://pith.science/pith/3WYKEHWNJAKVYZ7EYVRMWYT7XM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3WYKEHWNJAKVYZ7EYVRMWYT7XM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3WYKEHWNJAKVYZ7EYVRMWYT7XM","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":"a487220e1494c4bdc6c0d5b32a11d82f1a9ea18669a7009d64f2cadf1e9b0678","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T17:45:59Z","title_canon_sha256":"9d3e1ae5d6b56becc18af63994321e7934f299af1dca9d3dcd4a725f15291b68"},"schema_version":"1.0","source":{"id":"2406.16838","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.16838","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"arxiv_version","alias_value":"2406.16838v2","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.16838","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"pith_short_12","alias_value":"3WYKEHWNJAKV","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"pith_short_16","alias_value":"3WYKEHWNJAKVYZ7E","created_at":"2026-07-05T09:38:15Z"},{"alias_kind":"pith_short_8","alias_value":"3WYKEHWN","created_at":"2026-07-05T09:38:15Z"}],"graph_snapshots":[{"event_id":"sha256:f43f53a5e723f71232c331791ce5b52a3dc655f6fc01cc573a63a76aa61b1605","target":"graph","created_at":"2026-07-05T09:38:15Z","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/2406.16838/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One of the most striking findings in modern research on large language models (LLMs) is that scaling up compute during training leads to better results. However, less attention has been given to the benefits of scaling compute during inference. This survey focuses on these inference-time approaches. We explore three areas under a unified mathematical formalism: token-level generation algorithms, meta-generation algorithms, and efficient generation. Token-level generation algorithms, often called decoding algorithms, operate by sampling a single token at a time or constructing a token-level sea","authors_text":"Alex Xie, Amanda Bertsch, Graham Neubig, Hailey Schoelkopf, Ilia Kulikov, Matthew Finlayson, Sean Welleck, Zaid Harchaoui","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T17:45:59Z","title":"From Decoding to Meta-Generation: Inference-time Algorithms for Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.16838","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":"sha256:52739ea55ae2441bfb636cad8b20b65de62dcc37acc2378f6dfe0d71d84d525c","target":"record","created_at":"2026-07-05T09:38:15Z","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":"a487220e1494c4bdc6c0d5b32a11d82f1a9ea18669a7009d64f2cadf1e9b0678","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-24T17:45:59Z","title_canon_sha256":"9d3e1ae5d6b56becc18af63994321e7934f299af1dca9d3dcd4a725f15291b68"},"schema_version":"1.0","source":{"id":"2406.16838","kind":"arxiv","version":2}},"canonical_sha256":"ddb0a21ecd48155c67e4c562cb627fbb03cec454b6ad3702ae99c7e73c40fd4e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddb0a21ecd48155c67e4c562cb627fbb03cec454b6ad3702ae99c7e73c40fd4e","first_computed_at":"2026-07-05T09:38:15.169800Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:38:15.169800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"95oy2hxLdRuA6PVoUmVaRJmKqk47WGR6W4c5NbtWFsVfaTy3mAJ0sinSiojJIRVn9liypyWoJ/qgk2gziO+7Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:38:15.170306Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.16838","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:52739ea55ae2441bfb636cad8b20b65de62dcc37acc2378f6dfe0d71d84d525c","sha256:f43f53a5e723f71232c331791ce5b52a3dc655f6fc01cc573a63a76aa61b1605"],"state_sha256":"6928f3a63c46fc6b926b809db68142665b5929e2496500707ea8132a14298816"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xHh3LzPGJe5eOBwoCV6gNiEX+YNmL6p/NjZCocRdZkAwPpqMITe2VTjhTLoE2WDWw36wb0ph9CBbstXHd7y0Bw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T12:16:18.544251Z","bundle_sha256":"6713f5befa9e31b1c11fe0ce2bba942d882422b230350fc56125a1377c39567a"}}