{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:J34VM3Y3NZVFTJN6T4WXDVVORN","short_pith_number":"pith:J34VM3Y3","canonical_record":{"source":{"id":"2509.22992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T23:08:03Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"0a4ff88a2bf2923f41d0f5bd25bfc6c742160478c80807bb2e66c040d2abea5e","abstract_canon_sha256":"94020e70ddb496a7f47779229e5be15a4864378c7ae64a81dabf97c5d76521bb"},"schema_version":"1.0"},"canonical_sha256":"4ef9566f1b6e6a59a5be9f2d71d6ae8b7be0202fa28657b2be1e7e5d75c93de9","source":{"kind":"arxiv","id":"2509.22992","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.22992","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2509.22992v2","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.22992","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"J34VM3Y3NZVF","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"J34VM3Y3NZVFTJN6","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"J34VM3Y3","created_at":"2026-08-04T01:57:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:J34VM3Y3NZVFTJN6T4WXDVVORN","target":"record","payload":{"canonical_record":{"source":{"id":"2509.22992","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T23:08:03Z","cross_cats_sorted":["cs.GT"],"title_canon_sha256":"0a4ff88a2bf2923f41d0f5bd25bfc6c742160478c80807bb2e66c040d2abea5e","abstract_canon_sha256":"94020e70ddb496a7f47779229e5be15a4864378c7ae64a81dabf97c5d76521bb"},"schema_version":"1.0"},"canonical_sha256":"4ef9566f1b6e6a59a5be9f2d71d6ae8b7be0202fa28657b2be1e7e5d75c93de9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T01:57:55.131092Z","signature_b64":"NMJXLvGuMPV+OOjgJ1TBBLnL7mV6joflsPKd3+5akki4Bz9FJQoqkOKI/NvHT735N/sCP5mt6+yzqvgp9m6xCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ef9566f1b6e6a59a5be9f2d71d6ae8b7be0202fa28657b2be1e7e5d75c93de9","last_reissued_at":"2026-08-04T01:57:55.129492Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T01:57:55.129492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.22992","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":"2026-08-04T01:57:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wTCRjzwbSJctBDC7HhGyM+F2MJefxkbK7SmxEXQDmIpHFG81kDLOChK9eQDTGNXVRXx05zj9U7Kny2mBcZ6sCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:28:37.933542Z"},"content_sha256":"ec1f6af252313e969d942c3383b152acfb87fcafab6b004d0a35e0f437483864","schema_version":"1.0","event_id":"sha256:ec1f6af252313e969d942c3383b152acfb87fcafab6b004d0a35e0f437483864"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:J34VM3Y3NZVFTJN6T4WXDVVORN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"T-TAMER: Provably Taming Trade-offs in ML Serving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.GT"],"primary_cat":"cs.LG","authors_text":"Haifeng Xu, Jamie Morgenstern, Ruimin Zhang, Yuanyuan Yang","submitted_at":"2025-09-26T23:08:03Z","abstract_excerpt":"As machine learning models continue to grow in size and complexity, efficient serving faces increasingly broad trade-offs spanning accuracy, latency, resource usage, and other objectives. Multi-model serving further complicates these trade-offs; for example, in cascaded models, each early-exit decision balances latency reduction against potential accuracy loss. Despite the pervasiveness and importance of such trade-offs, current strategies remain largely heuristic and case-specific, limiting both their theoretical guarantees and general applicability.\n  We present a general framework, T-Tamer,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.22992","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/2509.22992/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":"2026-08-04T01:57:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"veNrBsV12IKqkIy4ikgKZBCtGwC2uT+6UmNTNiRt8MvWgMngtXvBugeESBJ6f5aWOoESTABDJ5/5iY7jO8Y8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T06:28:37.934085Z"},"content_sha256":"e8595884240641b37f5b74d34bb9fb49a31f3f7a2fae144b5a870bcdbd2f97ba","schema_version":"1.0","event_id":"sha256:e8595884240641b37f5b74d34bb9fb49a31f3f7a2fae144b5a870bcdbd2f97ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/J34VM3Y3NZVFTJN6T4WXDVVORN/bundle.json","state_url":"https://pith.science/pith/J34VM3Y3NZVFTJN6T4WXDVVORN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/J34VM3Y3NZVFTJN6T4WXDVVORN/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":"2026-08-06T06:28:37Z","links":{"resolver":"https://pith.science/pith/J34VM3Y3NZVFTJN6T4WXDVVORN","bundle":"https://pith.science/pith/J34VM3Y3NZVFTJN6T4WXDVVORN/bundle.json","state":"https://pith.science/pith/J34VM3Y3NZVFTJN6T4WXDVVORN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/J34VM3Y3NZVFTJN6T4WXDVVORN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:J34VM3Y3NZVFTJN6T4WXDVVORN","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":"94020e70ddb496a7f47779229e5be15a4864378c7ae64a81dabf97c5d76521bb","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T23:08:03Z","title_canon_sha256":"0a4ff88a2bf2923f41d0f5bd25bfc6c742160478c80807bb2e66c040d2abea5e"},"schema_version":"1.0","source":{"id":"2509.22992","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.22992","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"arxiv_version","alias_value":"2509.22992v2","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.22992","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"pith_short_12","alias_value":"J34VM3Y3NZVF","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"pith_short_16","alias_value":"J34VM3Y3NZVFTJN6","created_at":"2026-08-04T01:57:55Z"},{"alias_kind":"pith_short_8","alias_value":"J34VM3Y3","created_at":"2026-08-04T01:57:55Z"}],"graph_snapshots":[{"event_id":"sha256:e8595884240641b37f5b74d34bb9fb49a31f3f7a2fae144b5a870bcdbd2f97ba","target":"graph","created_at":"2026-08-04T01:57:55Z","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/2509.22992/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As machine learning models continue to grow in size and complexity, efficient serving faces increasingly broad trade-offs spanning accuracy, latency, resource usage, and other objectives. Multi-model serving further complicates these trade-offs; for example, in cascaded models, each early-exit decision balances latency reduction against potential accuracy loss. Despite the pervasiveness and importance of such trade-offs, current strategies remain largely heuristic and case-specific, limiting both their theoretical guarantees and general applicability.\n  We present a general framework, T-Tamer,","authors_text":"Haifeng Xu, Jamie Morgenstern, Ruimin Zhang, Yuanyuan Yang","cross_cats":["cs.GT"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T23:08:03Z","title":"T-TAMER: Provably Taming Trade-offs in ML Serving"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.22992","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:ec1f6af252313e969d942c3383b152acfb87fcafab6b004d0a35e0f437483864","target":"record","created_at":"2026-08-04T01:57:55Z","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":"94020e70ddb496a7f47779229e5be15a4864378c7ae64a81dabf97c5d76521bb","cross_cats_sorted":["cs.GT"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T23:08:03Z","title_canon_sha256":"0a4ff88a2bf2923f41d0f5bd25bfc6c742160478c80807bb2e66c040d2abea5e"},"schema_version":"1.0","source":{"id":"2509.22992","kind":"arxiv","version":2}},"canonical_sha256":"4ef9566f1b6e6a59a5be9f2d71d6ae8b7be0202fa28657b2be1e7e5d75c93de9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4ef9566f1b6e6a59a5be9f2d71d6ae8b7be0202fa28657b2be1e7e5d75c93de9","first_computed_at":"2026-08-04T01:57:55.129492Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-04T01:57:55.129492Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NMJXLvGuMPV+OOjgJ1TBBLnL7mV6joflsPKd3+5akki4Bz9FJQoqkOKI/NvHT735N/sCP5mt6+yzqvgp9m6xCQ==","signature_status":"signed_v1","signed_at":"2026-08-04T01:57:55.131092Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.22992","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ec1f6af252313e969d942c3383b152acfb87fcafab6b004d0a35e0f437483864","sha256:e8595884240641b37f5b74d34bb9fb49a31f3f7a2fae144b5a870bcdbd2f97ba"],"state_sha256":"98a45ca6d82c5be418344c76280951726cb7b84fcf5937acf9ba2c4e5aef675f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mq5gtzk4pTkr97sxTyT+M3VOAsdqHjTi4wRmfua7Reje1uPJ9zYyC6cF7E7Moa3Es43vOi+MjaswEwuxCld7AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T06:28:37.938539Z","bundle_sha256":"e4e452f7ddc4c8fe05f26cc49b5ae63d6b425d2340543bafad190c53a51f9361"}}