{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CHY7RR5FMX2PSZ25A2NWRFHEDA","short_pith_number":"pith:CHY7RR5F","schema_version":"1.0","canonical_sha256":"11f1f8c7a565f4f9675d069b6894e418252dc656474915b95a16c5069edc509d","source":{"kind":"arxiv","id":"2605.30218","version":1},"attestation_state":"computed","paper":{"title":"MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Kexin Chu, Wei Zhang, Yang Zhou","submitted_at":"2026-05-28T16:50:19Z","abstract_excerpt":"Temperature-zero BF16 LLM inference is often treated as reproducible, yet the same request can emit different tokens when decoded alone or inside a larger batch. Existing fixes use batch-invariant operators or LLM-42's per-token verification, incurring cost even when most steps are stable. We ask whether verification can be applied exclusively to flipped tokens. Across five models, batch-induced token flips are sparse on the flip-rate benchmarks: on MATH500, Llama-3.1-8B flips on $0.48\\%$ of synchronous decode steps, and all tested models stay within the 0.3-1.3% range on MATH500, GSM8K, and H"},"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":"2605.30218","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-28T16:50:19Z","cross_cats_sorted":["cs.PF"],"title_canon_sha256":"5ae65c875edafb05372f7899d9fef5ee37e1b333d24d90c79fa18f4d630f2978","abstract_canon_sha256":"18f507fdb8bb7b9e99bf3147f89e7bb9a06f1ed39b4b8ed567f03deaec3fd2a8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:13.184333Z","signature_b64":"zQEpm7oZ4ktA7azkNg9layxlRVCkPFPMUrQgAG6foZsrDe1azJfY5Yk5sQKLiF1L0T7g9XY0ywWzhz1Ut4UhAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"11f1f8c7a565f4f9675d069b6894e418252dc656474915b95a16c5069edc509d","last_reissued_at":"2026-05-29T02:06:13.183929Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:13.183929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MarginGate: Sparse Margin-Triggered Verification for Batch-Invariant LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.PF"],"primary_cat":"cs.LG","authors_text":"Kexin Chu, Wei Zhang, Yang Zhou","submitted_at":"2026-05-28T16:50:19Z","abstract_excerpt":"Temperature-zero BF16 LLM inference is often treated as reproducible, yet the same request can emit different tokens when decoded alone or inside a larger batch. Existing fixes use batch-invariant operators or LLM-42's per-token verification, incurring cost even when most steps are stable. We ask whether verification can be applied exclusively to flipped tokens. Across five models, batch-induced token flips are sparse on the flip-rate benchmarks: on MATH500, Llama-3.1-8B flips on $0.48\\%$ of synchronous decode steps, and all tested models stay within the 0.3-1.3% range on MATH500, GSM8K, and H"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30218","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/2605.30218/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":"2605.30218","created_at":"2026-05-29T02:06:13.183991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.30218v1","created_at":"2026-05-29T02:06:13.183991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30218","created_at":"2026-05-29T02:06:13.183991+00:00"},{"alias_kind":"pith_short_12","alias_value":"CHY7RR5FMX2P","created_at":"2026-05-29T02:06:13.183991+00:00"},{"alias_kind":"pith_short_16","alias_value":"CHY7RR5FMX2PSZ25","created_at":"2026-05-29T02:06:13.183991+00:00"},{"alias_kind":"pith_short_8","alias_value":"CHY7RR5F","created_at":"2026-05-29T02:06:13.183991+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/CHY7RR5FMX2PSZ25A2NWRFHEDA","json":"https://pith.science/pith/CHY7RR5FMX2PSZ25A2NWRFHEDA.json","graph_json":"https://pith.science/api/pith-number/CHY7RR5FMX2PSZ25A2NWRFHEDA/graph.json","events_json":"https://pith.science/api/pith-number/CHY7RR5FMX2PSZ25A2NWRFHEDA/events.json","paper":"https://pith.science/paper/CHY7RR5F"},"agent_actions":{"view_html":"https://pith.science/pith/CHY7RR5FMX2PSZ25A2NWRFHEDA","download_json":"https://pith.science/pith/CHY7RR5FMX2PSZ25A2NWRFHEDA.json","view_paper":"https://pith.science/paper/CHY7RR5F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.30218&json=true","fetch_graph":"https://pith.science/api/pith-number/CHY7RR5FMX2PSZ25A2NWRFHEDA/graph.json","fetch_events":"https://pith.science/api/pith-number/CHY7RR5FMX2PSZ25A2NWRFHEDA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CHY7RR5FMX2PSZ25A2NWRFHEDA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CHY7RR5FMX2PSZ25A2NWRFHEDA/action/storage_attestation","attest_author":"https://pith.science/pith/CHY7RR5FMX2PSZ25A2NWRFHEDA/action/author_attestation","sign_citation":"https://pith.science/pith/CHY7RR5FMX2PSZ25A2NWRFHEDA/action/citation_signature","submit_replication":"https://pith.science/pith/CHY7RR5FMX2PSZ25A2NWRFHEDA/action/replication_record"}},"created_at":"2026-05-29T02:06:13.183991+00:00","updated_at":"2026-05-29T02:06:13.183991+00:00"}