{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:N46EIBTIZ6DGVUYGROGE35ZUEP","short_pith_number":"pith:N46EIBTI","schema_version":"1.0","canonical_sha256":"6f3c440668cf866ad3068b8c4df73423e63ab20d0f55a9c4eabb132f14b6db9e","source":{"kind":"arxiv","id":"2607.03333","version":1},"attestation_state":"computed","paper":{"title":"SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DC","authors_text":"Huajun Bai, Huichuan Zheng, Jiwu Shu, Weiwei Lv, Youyou Lu","submitted_at":"2026-07-03T13:51:32Z","abstract_excerpt":"LLM agents are becoming a common interface for research, coding, and question answering, yet their Thought-Action-Observation loop is often serial: the model reasons, emits a tool call, then idles the GPU until the result returns. This wait consumes 16-37% of wall time in our workloads and 35-61% in prior reports. Speculative tool execution can hide this wait, but existing systems need auxiliary predictors, historical traces, or static workflow graphs, leaving a gap for training-free, day-one deployment. We observe that the model can be its own predictor: a probe forked at the start of generat"},"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":"2607.03333","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2026-07-03T13:51:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"6181d9b6a55d4657c57d450c2ba56b0ae05717f5e0142aa2f90602e075fe4592","abstract_canon_sha256":"0daeca066f139512f145c0a3408602b71a79dcd5e9f89aa9094323f0b3d51199"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:17:37.838033Z","signature_b64":"WtoTc1ZA5EtElxsUby7oQntGH8OTYPZz6helXNRy+etQj/dxRnlvh3Tz87/z2KgTcs0L2dzDWYwMLpz4UCn6BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6f3c440668cf866ad3068b8c4df73423e63ab20d0f55a9c4eabb132f14b6db9e","last_reissued_at":"2026-07-07T02:17:37.837299Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:17:37.837299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SPORK: Self-Speculative Forking to Accelerate Agentic LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.DC","authors_text":"Huajun Bai, Huichuan Zheng, Jiwu Shu, Weiwei Lv, Youyou Lu","submitted_at":"2026-07-03T13:51:32Z","abstract_excerpt":"LLM agents are becoming a common interface for research, coding, and question answering, yet their Thought-Action-Observation loop is often serial: the model reasons, emits a tool call, then idles the GPU until the result returns. This wait consumes 16-37% of wall time in our workloads and 35-61% in prior reports. Speculative tool execution can hide this wait, but existing systems need auxiliary predictors, historical traces, or static workflow graphs, leaving a gap for training-free, day-one deployment. We observe that the model can be its own predictor: a probe forked at the start of generat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.03333","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/2607.03333/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":"2607.03333","created_at":"2026-07-07T02:17:37.837383+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.03333v1","created_at":"2026-07-07T02:17:37.837383+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.03333","created_at":"2026-07-07T02:17:37.837383+00:00"},{"alias_kind":"pith_short_12","alias_value":"N46EIBTIZ6DG","created_at":"2026-07-07T02:17:37.837383+00:00"},{"alias_kind":"pith_short_16","alias_value":"N46EIBTIZ6DGVUYG","created_at":"2026-07-07T02:17:37.837383+00:00"},{"alias_kind":"pith_short_8","alias_value":"N46EIBTI","created_at":"2026-07-07T02:17:37.837383+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/N46EIBTIZ6DGVUYGROGE35ZUEP","json":"https://pith.science/pith/N46EIBTIZ6DGVUYGROGE35ZUEP.json","graph_json":"https://pith.science/api/pith-number/N46EIBTIZ6DGVUYGROGE35ZUEP/graph.json","events_json":"https://pith.science/api/pith-number/N46EIBTIZ6DGVUYGROGE35ZUEP/events.json","paper":"https://pith.science/paper/N46EIBTI"},"agent_actions":{"view_html":"https://pith.science/pith/N46EIBTIZ6DGVUYGROGE35ZUEP","download_json":"https://pith.science/pith/N46EIBTIZ6DGVUYGROGE35ZUEP.json","view_paper":"https://pith.science/paper/N46EIBTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.03333&json=true","fetch_graph":"https://pith.science/api/pith-number/N46EIBTIZ6DGVUYGROGE35ZUEP/graph.json","fetch_events":"https://pith.science/api/pith-number/N46EIBTIZ6DGVUYGROGE35ZUEP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N46EIBTIZ6DGVUYGROGE35ZUEP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N46EIBTIZ6DGVUYGROGE35ZUEP/action/storage_attestation","attest_author":"https://pith.science/pith/N46EIBTIZ6DGVUYGROGE35ZUEP/action/author_attestation","sign_citation":"https://pith.science/pith/N46EIBTIZ6DGVUYGROGE35ZUEP/action/citation_signature","submit_replication":"https://pith.science/pith/N46EIBTIZ6DGVUYGROGE35ZUEP/action/replication_record"}},"created_at":"2026-07-07T02:17:37.837383+00:00","updated_at":"2026-07-07T02:17:37.837383+00:00"}