{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:EDKOIZGIK6RWAMGSU3QYXHHMFG","short_pith_number":"pith:EDKOIZGI","canonical_record":{"source":{"id":"2606.06892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T04:17:50Z","cross_cats_sorted":[],"title_canon_sha256":"11d83384a791703442aca86f068cf551050ea560899c25be527f19d6e737d1e1","abstract_canon_sha256":"ff20f03a13c8572b4debed25ca439ae5693bb354940b333773d57f16f11a5764"},"schema_version":"1.0"},"canonical_sha256":"20d4e464c857a36030d2a6e18b9cec29a062180526ca8e4592f7c763c35ea317","source":{"kind":"arxiv","id":"2606.06892","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06892","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06892v1","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06892","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"EDKOIZGIK6RW","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"EDKOIZGIK6RWAMGS","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"EDKOIZGI","created_at":"2026-06-08T01:04:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:EDKOIZGIK6RWAMGSU3QYXHHMFG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.06892","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T04:17:50Z","cross_cats_sorted":[],"title_canon_sha256":"11d83384a791703442aca86f068cf551050ea560899c25be527f19d6e737d1e1","abstract_canon_sha256":"ff20f03a13c8572b4debed25ca439ae5693bb354940b333773d57f16f11a5764"},"schema_version":"1.0"},"canonical_sha256":"20d4e464c857a36030d2a6e18b9cec29a062180526ca8e4592f7c763c35ea317","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-08T01:04:34.303842Z","signature_b64":"UPKTX/nxLhtuZ1j39qMexdc6eyu5OXp0qBrFODFV+hcq02m6WV5lL9RXr0VjGtB5tAYJplL+uOU6hJj3PkMtAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"20d4e464c857a36030d2a6e18b9cec29a062180526ca8e4592f7c763c35ea317","last_reissued_at":"2026-06-08T01:04:34.303007Z","signature_status":"signed_v1","first_computed_at":"2026-06-08T01:04:34.303007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.06892","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-08T01:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gBNP4mqLKvp6e4VeRnREbWIeZqzFV5kNX8D/508DK/gEKTHX7BfSi1v6hU8AsBDb6ac4P00SgRBxqTsMLi4ZDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T08:19:27.408682Z"},"content_sha256":"5457314643741cd0e3675cfd3eb887cb9cd6b23340176ba3828271061ff5ec18","schema_version":"1.0","event_id":"sha256:5457314643741cd0e3675cfd3eb887cb9cd6b23340176ba3828271061ff5ec18"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:EDKOIZGIK6RWAMGSU3QYXHHMFG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Ruining Chen, Yue Min, Yujun Li","submitted_at":"2026-06-05T04:17:50Z","abstract_excerpt":"Scalable data attribution methods typically assign isolated utility scores to individual training examples. This prevalent additive assumption fundamentally fails to capture critical subset dynamics, including data redundancy and complementary coverage. In this work, we reframe attribution as subset-level counterfactual utility prediction and introduce GRASP, an interaction-aware surrogate. Grounded in a theoretical smoothness lower bound, GRASP explicitly models subset interactions through a quadratic geometric penalty. To achieve pretraining-scale efficiency without relying on hidden oracle "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06892","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/2606.06892/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":"2026-06-08T01:04:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EIkFATsGk8IdoAWY9p6MhmBFMr1XPpH9q7MFEp0g1+2A3YXpXnt4O/dceTV6RiGeSq++5MLjpy9xYtOGIlIGAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-12T08:19:27.409064Z"},"content_sha256":"0be25ca4788486c1bf0a8ba91814035239c98c28b129973ed17d40cfa828e733","schema_version":"1.0","event_id":"sha256:0be25ca4788486c1bf0a8ba91814035239c98c28b129973ed17d40cfa828e733"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EDKOIZGIK6RWAMGSU3QYXHHMFG/bundle.json","state_url":"https://pith.science/pith/EDKOIZGIK6RWAMGSU3QYXHHMFG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EDKOIZGIK6RWAMGSU3QYXHHMFG/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":"2026-06-12T08:19:27Z","links":{"resolver":"https://pith.science/pith/EDKOIZGIK6RWAMGSU3QYXHHMFG","bundle":"https://pith.science/pith/EDKOIZGIK6RWAMGSU3QYXHHMFG/bundle.json","state":"https://pith.science/pith/EDKOIZGIK6RWAMGSU3QYXHHMFG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EDKOIZGIK6RWAMGSU3QYXHHMFG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:EDKOIZGIK6RWAMGSU3QYXHHMFG","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":"ff20f03a13c8572b4debed25ca439ae5693bb354940b333773d57f16f11a5764","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T04:17:50Z","title_canon_sha256":"11d83384a791703442aca86f068cf551050ea560899c25be527f19d6e737d1e1"},"schema_version":"1.0","source":{"id":"2606.06892","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.06892","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2606.06892v1","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.06892","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"EDKOIZGIK6RW","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"EDKOIZGIK6RWAMGS","created_at":"2026-06-08T01:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"EDKOIZGI","created_at":"2026-06-08T01:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:0be25ca4788486c1bf0a8ba91814035239c98c28b129973ed17d40cfa828e733","target":"graph","created_at":"2026-06-08T01:04:34Z","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/2606.06892/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Scalable data attribution methods typically assign isolated utility scores to individual training examples. This prevalent additive assumption fundamentally fails to capture critical subset dynamics, including data redundancy and complementary coverage. In this work, we reframe attribution as subset-level counterfactual utility prediction and introduce GRASP, an interaction-aware surrogate. Grounded in a theoretical smoothness lower bound, GRASP explicitly models subset interactions through a quadratic geometric penalty. To achieve pretraining-scale efficiency without relying on hidden oracle ","authors_text":"Ruining Chen, Yue Min, Yujun Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T04:17:50Z","title":"GRASP: Geometry-aware Residual Alignment for Scalable Pretraining Data Attribution"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.06892","kind":"arxiv","version":1},"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":"sha256:5457314643741cd0e3675cfd3eb887cb9cd6b23340176ba3828271061ff5ec18","target":"record","created_at":"2026-06-08T01:04:34Z","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":"ff20f03a13c8572b4debed25ca439ae5693bb354940b333773d57f16f11a5764","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-05T04:17:50Z","title_canon_sha256":"11d83384a791703442aca86f068cf551050ea560899c25be527f19d6e737d1e1"},"schema_version":"1.0","source":{"id":"2606.06892","kind":"arxiv","version":1}},"canonical_sha256":"20d4e464c857a36030d2a6e18b9cec29a062180526ca8e4592f7c763c35ea317","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"20d4e464c857a36030d2a6e18b9cec29a062180526ca8e4592f7c763c35ea317","first_computed_at":"2026-06-08T01:04:34.303007Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-08T01:04:34.303007Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UPKTX/nxLhtuZ1j39qMexdc6eyu5OXp0qBrFODFV+hcq02m6WV5lL9RXr0VjGtB5tAYJplL+uOU6hJj3PkMtAA==","signature_status":"signed_v1","signed_at":"2026-06-08T01:04:34.303842Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.06892","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5457314643741cd0e3675cfd3eb887cb9cd6b23340176ba3828271061ff5ec18","sha256:0be25ca4788486c1bf0a8ba91814035239c98c28b129973ed17d40cfa828e733"],"state_sha256":"bdcd9e737382313faa703b2dbc35b29ae6d06b97f834755fd6980e02ac3a12ef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"M2fh/JFcdB3nXKkDC3Bz97HsG9IFOPkcV0ti4kcmAni+XpXjpVfIgK3iwrHFtqe8X0mGXUaIfO2EVm5iJCCiAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-12T08:19:27.411270Z","bundle_sha256":"26375873ce115c75f358a9ce8754246aabaf5f25da124e9e22df9f667c448df8"}}