{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:JPBADMBSCREE7VLKFBXWFJ736Q","short_pith_number":"pith:JPBADMBS","canonical_record":{"source":{"id":"2604.08438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-09T16:38:14Z","cross_cats_sorted":[],"title_canon_sha256":"b84431360dda8abe46294e537bf01c12b4deb3e91bf76002adeec910ea9cb143","abstract_canon_sha256":"d55164f24eae6d753b025f36cb17a061e020b092a82cd99f0d64b03cecc14476"},"schema_version":"1.0"},"canonical_sha256":"4bc201b03214484fd56a286f62a7fbf43c6e310c3a6194fbff6e11e4c2608144","source":{"kind":"arxiv","id":"2604.08438","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.08438","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"arxiv_version","alias_value":"2604.08438v2","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08438","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"pith_short_12","alias_value":"JPBADMBSCREE","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"pith_short_16","alias_value":"JPBADMBSCREE7VLK","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"pith_short_8","alias_value":"JPBADMBS","created_at":"2026-06-04T01:08:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:JPBADMBSCREE7VLKFBXWFJ736Q","target":"record","payload":{"canonical_record":{"source":{"id":"2604.08438","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-09T16:38:14Z","cross_cats_sorted":[],"title_canon_sha256":"b84431360dda8abe46294e537bf01c12b4deb3e91bf76002adeec910ea9cb143","abstract_canon_sha256":"d55164f24eae6d753b025f36cb17a061e020b092a82cd99f0d64b03cecc14476"},"schema_version":"1.0"},"canonical_sha256":"4bc201b03214484fd56a286f62a7fbf43c6e310c3a6194fbff6e11e4c2608144","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:08:49.704971Z","signature_b64":"BpbSxzflf92nuq1ecs6VZtrC6PlSl493OoVysl2JBqRgMEzR3aEYV490c3OfAtFy9WtQA4yg2TQnW7s3LXyJAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4bc201b03214484fd56a286f62a7fbf43c6e310c3a6194fbff6e11e4c2608144","last_reissued_at":"2026-06-04T01:08:49.704520Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:08:49.704520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.08438","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":"2026-06-04T01:08:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ePrAK+taVjX86INzv56/9jF8agrY8CRGg2KsNG34F8XaHwBEd7RWNtJN2y2G+8RbLbpoHso8awRJfGHZrdFuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:37:48.975525Z"},"content_sha256":"974d82e37676356c60c4f5f7ec9e15f7ac54a5ccc610fa8ef10220e69bec39f8","schema_version":"1.0","event_id":"sha256:974d82e37676356c60c4f5f7ec9e15f7ac54a5ccc610fa8ef10220e69bec39f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:JPBADMBSCREE7VLKFBXWFJ736Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A linear-space algorithm approximates Shapley values and semi-values with O(n/ε² log(1/δ)) queries while minimizing mean squared error for any utility.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bryan Kian Hsiang Low, Weida Li, Yaoliang Yu","submitted_at":"2026-04-09T16:38:14Z","abstract_excerpt":"The Shapley value, and its broader family of semi-values, has received much attention in various attribution problems. A fundamental and long-standing challenge is their efficient approximation, since exact computation generally requires an exponential number of utility queries in the number of players $n$. To meet the challenges of large-scale applications, we explore the limits of efficiently approximating semi-values under a $\\Theta(n)$ space constraint. Building upon a vector concentration inequality, we establish a theoretical framework that enables sharper query complexities for existing"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Our algorithm requires O(n/ε² log(1/δ)) utility queries to ensure P(‖φ̂ - φ‖₂ ≥ ε) ≤ δ for all commonly used semi-values... our algorithm allows explicit minimization of the mean square error for each specific utility function... the first adaptive, linear-time, linear-space randomized algorithm, Adalina, that theoretically achieves improved mean square error.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The framework relies on a vector concentration inequality to derive the query bounds under a Θ(n) space constraint; if this inequality does not apply tightly to the semi-value estimators, the claimed complexities may not hold.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Introduces Adalina, the first adaptive linear-time linear-space randomized algorithm for semi-value approximation with provable O(n/ε² log(1/δ)) query complexity and explicit MSE minimization.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A linear-space algorithm approximates Shapley values and semi-values with O(n/ε² log(1/δ)) queries while minimizing mean squared error for any utility.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9db8bb4ef4ad8cc365ada60f2b615f6e2a9d3fa5e417f4a809fdee9de7ed670b"},"source":{"id":"2604.08438","kind":"arxiv","version":2},"verdict":{"id":"31e2cd17-38a6-4b6f-adaf-f1867d94ab23","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T18:33:07.174134Z","strongest_claim":"Our algorithm requires O(n/ε² log(1/δ)) utility queries to ensure P(‖φ̂ - φ‖₂ ≥ ε) ≤ δ for all commonly used semi-values... our algorithm allows explicit minimization of the mean square error for each specific utility function... the first adaptive, linear-time, linear-space randomized algorithm, Adalina, that theoretically achieves improved mean square error.","one_line_summary":"Introduces Adalina, the first adaptive linear-time linear-space randomized algorithm for semi-value approximation with provable O(n/ε² log(1/δ)) query complexity and explicit MSE minimization.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The framework relies on a vector concentration inequality to derive the query bounds under a Θ(n) space constraint; if this inequality does not apply tightly to the semi-value estimators, the claimed complexities may not hold.","pith_extraction_headline":"A linear-space algorithm approximates Shapley values and semi-values with O(n/ε² log(1/δ)) queries while minimizing mean squared error for any utility."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.08438/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":2,"snapshot_sha256":"cd1c453c5550d309211a649a1a515afd899c700c0c8f7dd1bb3875a4c21fa07c"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"31e2cd17-38a6-4b6f-adaf-f1867d94ab23"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:08:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HZpGVkj0lxI28vEpzLYeFuDw9OG8HDUqyXVgL7cS3GrL+LCyGWLbxGImUF1YxjvEQ6N6l43C7eO5Gj1L9Ga0Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-09T09:37:48.976016Z"},"content_sha256":"255e07b02b5f5f7b7fd61843fbfab8d3fe87b5240c754c347203e98817126df3","schema_version":"1.0","event_id":"sha256:255e07b02b5f5f7b7fd61843fbfab8d3fe87b5240c754c347203e98817126df3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JPBADMBSCREE7VLKFBXWFJ736Q/bundle.json","state_url":"https://pith.science/pith/JPBADMBSCREE7VLKFBXWFJ736Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JPBADMBSCREE7VLKFBXWFJ736Q/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":"2026-06-09T09:37:48Z","links":{"resolver":"https://pith.science/pith/JPBADMBSCREE7VLKFBXWFJ736Q","bundle":"https://pith.science/pith/JPBADMBSCREE7VLKFBXWFJ736Q/bundle.json","state":"https://pith.science/pith/JPBADMBSCREE7VLKFBXWFJ736Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JPBADMBSCREE7VLKFBXWFJ736Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:JPBADMBSCREE7VLKFBXWFJ736Q","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":"d55164f24eae6d753b025f36cb17a061e020b092a82cd99f0d64b03cecc14476","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-09T16:38:14Z","title_canon_sha256":"b84431360dda8abe46294e537bf01c12b4deb3e91bf76002adeec910ea9cb143"},"schema_version":"1.0","source":{"id":"2604.08438","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.08438","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"arxiv_version","alias_value":"2604.08438v2","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08438","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"pith_short_12","alias_value":"JPBADMBSCREE","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"pith_short_16","alias_value":"JPBADMBSCREE7VLK","created_at":"2026-06-04T01:08:49Z"},{"alias_kind":"pith_short_8","alias_value":"JPBADMBS","created_at":"2026-06-04T01:08:49Z"}],"graph_snapshots":[{"event_id":"sha256:255e07b02b5f5f7b7fd61843fbfab8d3fe87b5240c754c347203e98817126df3","target":"graph","created_at":"2026-06-04T01:08:49Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Our algorithm requires O(n/ε² log(1/δ)) utility queries to ensure P(‖φ̂ - φ‖₂ ≥ ε) ≤ δ for all commonly used semi-values... our algorithm allows explicit minimization of the mean square error for each specific utility function... the first adaptive, linear-time, linear-space randomized algorithm, Adalina, that theoretically achieves improved mean square error."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The framework relies on a vector concentration inequality to derive the query bounds under a Θ(n) space constraint; if this inequality does not apply tightly to the semi-value estimators, the claimed complexities may not hold."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Introduces Adalina, the first adaptive linear-time linear-space randomized algorithm for semi-value approximation with provable O(n/ε² log(1/δ)) query complexity and explicit MSE minimization."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A linear-space algorithm approximates Shapley values and semi-values with O(n/ε² log(1/δ)) queries while minimizing mean squared error for any utility."}],"snapshot_sha256":"9db8bb4ef4ad8cc365ada60f2b615f6e2a9d3fa5e417f4a809fdee9de7ed670b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"cd1c453c5550d309211a649a1a515afd899c700c0c8f7dd1bb3875a4c21fa07c"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.08438/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Shapley value, and its broader family of semi-values, has received much attention in various attribution problems. A fundamental and long-standing challenge is their efficient approximation, since exact computation generally requires an exponential number of utility queries in the number of players $n$. To meet the challenges of large-scale applications, we explore the limits of efficiently approximating semi-values under a $\\Theta(n)$ space constraint. Building upon a vector concentration inequality, we establish a theoretical framework that enables sharper query complexities for existing","authors_text":"Bryan Kian Hsiang Low, Weida Li, Yaoliang Yu","cross_cats":[],"headline":"A linear-space algorithm approximates Shapley values and semi-values with O(n/ε² log(1/δ)) queries while minimizing mean squared error for any utility.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-09T16:38:14Z","title":"Adalina: Adaptive Linear Approximation for the Shapley Value and Beyond"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.08438","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T18:33:07.174134Z","id":"31e2cd17-38a6-4b6f-adaf-f1867d94ab23","model_set":{"reader":"grok-4.3"},"one_line_summary":"Introduces Adalina, the first adaptive linear-time linear-space randomized algorithm for semi-value approximation with provable O(n/ε² log(1/δ)) query complexity and explicit MSE minimization.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A linear-space algorithm approximates Shapley values and semi-values with O(n/ε² log(1/δ)) queries while minimizing mean squared error for any utility.","strongest_claim":"Our algorithm requires O(n/ε² log(1/δ)) utility queries to ensure P(‖φ̂ - φ‖₂ ≥ ε) ≤ δ for all commonly used semi-values... our algorithm allows explicit minimization of the mean square error for each specific utility function... the first adaptive, linear-time, linear-space randomized algorithm, Adalina, that theoretically achieves improved mean square error.","weakest_assumption":"The framework relies on a vector concentration inequality to derive the query bounds under a Θ(n) space constraint; if this inequality does not apply tightly to the semi-value estimators, the claimed complexities may not hold."}},"verdict_id":"31e2cd17-38a6-4b6f-adaf-f1867d94ab23"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:974d82e37676356c60c4f5f7ec9e15f7ac54a5ccc610fa8ef10220e69bec39f8","target":"record","created_at":"2026-06-04T01:08:49Z","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":"d55164f24eae6d753b025f36cb17a061e020b092a82cd99f0d64b03cecc14476","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-04-09T16:38:14Z","title_canon_sha256":"b84431360dda8abe46294e537bf01c12b4deb3e91bf76002adeec910ea9cb143"},"schema_version":"1.0","source":{"id":"2604.08438","kind":"arxiv","version":2}},"canonical_sha256":"4bc201b03214484fd56a286f62a7fbf43c6e310c3a6194fbff6e11e4c2608144","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4bc201b03214484fd56a286f62a7fbf43c6e310c3a6194fbff6e11e4c2608144","first_computed_at":"2026-06-04T01:08:49.704520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:08:49.704520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BpbSxzflf92nuq1ecs6VZtrC6PlSl493OoVysl2JBqRgMEzR3aEYV490c3OfAtFy9WtQA4yg2TQnW7s3LXyJAw==","signature_status":"signed_v1","signed_at":"2026-06-04T01:08:49.704971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.08438","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:974d82e37676356c60c4f5f7ec9e15f7ac54a5ccc610fa8ef10220e69bec39f8","sha256:255e07b02b5f5f7b7fd61843fbfab8d3fe87b5240c754c347203e98817126df3"],"state_sha256":"a368e6ca2ed67ce94a0c254f179747b0634587940f584ee26b720d6962f93be4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XKgDy/3KI3P8v6UzFEacAunwgZaFstVqsuMEJNE59Qrp+2LSYv8HuvPCx871sRJgpZdMP7dlDBcJjayv9sMMCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-09T09:37:48.978146Z","bundle_sha256":"4145279dfa1894e7fb6d539ce9aa8c2e813cc4ccdf1191539020c397cf755803"}}