{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CIDESPC5QRVD4ADJB3NJX5EVVV","short_pith_number":"pith:CIDESPC5","schema_version":"1.0","canonical_sha256":"1206493c5d846a3e00690eda9bf495ad792a3ea5cf772ba9d87f9ef325ca5b76","source":{"kind":"arxiv","id":"2506.16043","version":1},"attestation_state":"computed","paper":{"title":"DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fei Wang, Jiefeng Chen, Ruoxi Sun, Sercan \\\"O. Ar{\\i}k, Xingchen Wan","submitted_at":"2025-06-19T05:40:54Z","abstract_excerpt":"Inference-time scaling has proven effective in boosting large language model (LLM) performance through increased test-time computation. Yet, its practical application is often hindered by reliance on external verifiers or a lack of optimization for realistic computational constraints. We propose DynScaling, which addresses these limitations through two primary innovations: an integrated parallel-sequential sampling strategy and a bandit-based dynamic budget allocation framework. The integrated sampling strategy unifies parallel and sequential sampling by constructing synthetic sequential reaso"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2506.16043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T05:40:54Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"1f8c965a489213c94d1117afd4a72b90efc8cab6eb6a4279cfe5436cd7086f12","abstract_canon_sha256":"0d6a88565abeb0891a3428c3015a7df165aba79d1da89aa56c9d4583ac77948d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:29.189691Z","signature_b64":"PvnVnYBfWtxOJL37ogBNSZc39GxPSuVL5jJ6/gUMAeKvRBu0RfUi3a54Xdk9RzL3wHxjlPBD/OzeK2Z5wvYSBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1206493c5d846a3e00690eda9bf495ad792a3ea5cf772ba9d87f9ef325ca5b76","last_reissued_at":"2026-07-05T11:24:29.189162Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:29.189162Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DynScaling: Efficient Verifier-free Inference Scaling via Dynamic and Integrated Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Fei Wang, Jiefeng Chen, Ruoxi Sun, Sercan \\\"O. Ar{\\i}k, Xingchen Wan","submitted_at":"2025-06-19T05:40:54Z","abstract_excerpt":"Inference-time scaling has proven effective in boosting large language model (LLM) performance through increased test-time computation. Yet, its practical application is often hindered by reliance on external verifiers or a lack of optimization for realistic computational constraints. We propose DynScaling, which addresses these limitations through two primary innovations: an integrated parallel-sequential sampling strategy and a bandit-based dynamic budget allocation framework. The integrated sampling strategy unifies parallel and sequential sampling by constructing synthetic sequential reaso"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16043","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/2506.16043/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2506.16043","created_at":"2026-07-05T11:24:29.189225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.16043v1","created_at":"2026-07-05T11:24:29.189225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16043","created_at":"2026-07-05T11:24:29.189225+00:00"},{"alias_kind":"pith_short_12","alias_value":"CIDESPC5QRVD","created_at":"2026-07-05T11:24:29.189225+00:00"},{"alias_kind":"pith_short_16","alias_value":"CIDESPC5QRVD4ADJ","created_at":"2026-07-05T11:24:29.189225+00:00"},{"alias_kind":"pith_short_8","alias_value":"CIDESPC5","created_at":"2026-07-05T11:24:29.189225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CIDESPC5QRVD4ADJB3NJX5EVVV","json":"https://pith.science/pith/CIDESPC5QRVD4ADJB3NJX5EVVV.json","graph_json":"https://pith.science/api/pith-number/CIDESPC5QRVD4ADJB3NJX5EVVV/graph.json","events_json":"https://pith.science/api/pith-number/CIDESPC5QRVD4ADJB3NJX5EVVV/events.json","paper":"https://pith.science/paper/CIDESPC5"},"agent_actions":{"view_html":"https://pith.science/pith/CIDESPC5QRVD4ADJB3NJX5EVVV","download_json":"https://pith.science/pith/CIDESPC5QRVD4ADJB3NJX5EVVV.json","view_paper":"https://pith.science/paper/CIDESPC5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.16043&json=true","fetch_graph":"https://pith.science/api/pith-number/CIDESPC5QRVD4ADJB3NJX5EVVV/graph.json","fetch_events":"https://pith.science/api/pith-number/CIDESPC5QRVD4ADJB3NJX5EVVV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CIDESPC5QRVD4ADJB3NJX5EVVV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CIDESPC5QRVD4ADJB3NJX5EVVV/action/storage_attestation","attest_author":"https://pith.science/pith/CIDESPC5QRVD4ADJB3NJX5EVVV/action/author_attestation","sign_citation":"https://pith.science/pith/CIDESPC5QRVD4ADJB3NJX5EVVV/action/citation_signature","submit_replication":"https://pith.science/pith/CIDESPC5QRVD4ADJB3NJX5EVVV/action/replication_record"}},"created_at":"2026-07-05T11:24:29.189225+00:00","updated_at":"2026-07-05T11:24:29.189225+00:00"}