{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:NYEQ26H4K7ATM7WVHUZESHLPGA","short_pith_number":"pith:NYEQ26H4","canonical_record":{"source":{"id":"2311.16298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-27T20:19:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"663ce316dde1aa448725a9eb33a88289581999b710cd0dd4fc353516e5e99356","abstract_canon_sha256":"f172feb76bb8fd532437a980790b4e4f0276c39184c675e20c541e232da8ad8e"},"schema_version":"1.0"},"canonical_sha256":"6e090d78fc57c1367ed53d32491d6f301d11ac958c10d07e0b796b4616d70f97","source":{"kind":"arxiv","id":"2311.16298","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16298","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16298v1","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16298","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"NYEQ26H4K7AT","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"pith_short_16","alias_value":"NYEQ26H4K7ATM7WV","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"pith_short_8","alias_value":"NYEQ26H4","created_at":"2026-07-05T07:17:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:NYEQ26H4K7ATM7WVHUZESHLPGA","target":"record","payload":{"canonical_record":{"source":{"id":"2311.16298","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-27T20:19:22Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"663ce316dde1aa448725a9eb33a88289581999b710cd0dd4fc353516e5e99356","abstract_canon_sha256":"f172feb76bb8fd532437a980790b4e4f0276c39184c675e20c541e232da8ad8e"},"schema_version":"1.0"},"canonical_sha256":"6e090d78fc57c1367ed53d32491d6f301d11ac958c10d07e0b796b4616d70f97","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:17:38.979448Z","signature_b64":"MCISwZ1zSjiSHV2BKnr6PQ50SOyB9JG6lzOUqJXkvcTAuMOxiE9EaeQM2mfZXNq7Xh9Mxn5sXnh8tBKw5Vi8AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e090d78fc57c1367ed53d32491d6f301d11ac958c10d07e0b796b4616d70f97","last_reissued_at":"2026-07-05T07:17:38.979040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:17:38.979040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2311.16298","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":"2026-07-05T07:17:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jJNSQMpwoOOwxZ+V+zduDsez+xAbn1YyRSJDAOPL+SpThe9LiSu3XCq7Cd/qTJfNWe/l5N7RF3NKdr7Q5OVRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T06:57:47.713205Z"},"content_sha256":"c50fc2db9d961fe43aeca545bf59de4a0786618d0caa46b3cb78d99699415a74","schema_version":"1.0","event_id":"sha256:c50fc2db9d961fe43aeca545bf59de4a0786618d0caa46b3cb78d99699415a74"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:NYEQ26H4K7ATM7WVHUZESHLPGA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Influence Scores at Scale for Efficient Language Data Sampling","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Joshua Tan, Maria Minakova, Nikhil Anand","submitted_at":"2023-11-27T20:19:22Z","abstract_excerpt":"Modern ML systems ingest data aggregated from diverse sources, such as synthetic, human-annotated, and live customer traffic. Understanding \\textit{which} examples are important to the performance of a learning algorithm is crucial for efficient model training. Recently, a growing body of literature has given rise to various \"influence scores,\" which use training artifacts such as model confidence or checkpointed gradients to identify important subsets of data. However, these methods have primarily been developed in computer vision settings, and it remains unclear how well they generalize to l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16298","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/2311.16298/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":"2026-07-05T07:17:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sn4tBiGGgRF4YcyAbscPUWD4MXCChfL6C9pk3zkshL/SBk9f0TUCfCB1iSN1YaCTESlpxLML5wega5A0IfA7DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T06:57:47.714014Z"},"content_sha256":"23515ea6a83e27061c4c7e68fe019e8c24fa55cdd8342038ea2af6fbec14b328","schema_version":"1.0","event_id":"sha256:23515ea6a83e27061c4c7e68fe019e8c24fa55cdd8342038ea2af6fbec14b328"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NYEQ26H4K7ATM7WVHUZESHLPGA/bundle.json","state_url":"https://pith.science/pith/NYEQ26H4K7ATM7WVHUZESHLPGA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NYEQ26H4K7ATM7WVHUZESHLPGA/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":"2026-08-22T06:57:47Z","links":{"resolver":"https://pith.science/pith/NYEQ26H4K7ATM7WVHUZESHLPGA","bundle":"https://pith.science/pith/NYEQ26H4K7ATM7WVHUZESHLPGA/bundle.json","state":"https://pith.science/pith/NYEQ26H4K7ATM7WVHUZESHLPGA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NYEQ26H4K7ATM7WVHUZESHLPGA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:NYEQ26H4K7ATM7WVHUZESHLPGA","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":"f172feb76bb8fd532437a980790b4e4f0276c39184c675e20c541e232da8ad8e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-27T20:19:22Z","title_canon_sha256":"663ce316dde1aa448725a9eb33a88289581999b710cd0dd4fc353516e5e99356"},"schema_version":"1.0","source":{"id":"2311.16298","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2311.16298","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"arxiv_version","alias_value":"2311.16298v1","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.16298","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"pith_short_12","alias_value":"NYEQ26H4K7AT","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"pith_short_16","alias_value":"NYEQ26H4K7ATM7WV","created_at":"2026-07-05T07:17:38Z"},{"alias_kind":"pith_short_8","alias_value":"NYEQ26H4","created_at":"2026-07-05T07:17:38Z"}],"graph_snapshots":[{"event_id":"sha256:23515ea6a83e27061c4c7e68fe019e8c24fa55cdd8342038ea2af6fbec14b328","target":"graph","created_at":"2026-07-05T07:17:38Z","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/2311.16298/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Modern ML systems ingest data aggregated from diverse sources, such as synthetic, human-annotated, and live customer traffic. Understanding \\textit{which} examples are important to the performance of a learning algorithm is crucial for efficient model training. Recently, a growing body of literature has given rise to various \"influence scores,\" which use training artifacts such as model confidence or checkpointed gradients to identify important subsets of data. However, these methods have primarily been developed in computer vision settings, and it remains unclear how well they generalize to l","authors_text":"Joshua Tan, Maria Minakova, Nikhil Anand","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-27T20:19:22Z","title":"Influence Scores at Scale for Efficient Language Data Sampling"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.16298","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:c50fc2db9d961fe43aeca545bf59de4a0786618d0caa46b3cb78d99699415a74","target":"record","created_at":"2026-07-05T07:17:38Z","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":"f172feb76bb8fd532437a980790b4e4f0276c39184c675e20c541e232da8ad8e","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-11-27T20:19:22Z","title_canon_sha256":"663ce316dde1aa448725a9eb33a88289581999b710cd0dd4fc353516e5e99356"},"schema_version":"1.0","source":{"id":"2311.16298","kind":"arxiv","version":1}},"canonical_sha256":"6e090d78fc57c1367ed53d32491d6f301d11ac958c10d07e0b796b4616d70f97","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6e090d78fc57c1367ed53d32491d6f301d11ac958c10d07e0b796b4616d70f97","first_computed_at":"2026-07-05T07:17:38.979040Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:17:38.979040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MCISwZ1zSjiSHV2BKnr6PQ50SOyB9JG6lzOUqJXkvcTAuMOxiE9EaeQM2mfZXNq7Xh9Mxn5sXnh8tBKw5Vi8AA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:17:38.979448Z","signed_message":"canonical_sha256_bytes"},"source_id":"2311.16298","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c50fc2db9d961fe43aeca545bf59de4a0786618d0caa46b3cb78d99699415a74","sha256:23515ea6a83e27061c4c7e68fe019e8c24fa55cdd8342038ea2af6fbec14b328"],"state_sha256":"d92fad48ad4294af76154ff25408d9ea7eb563db716c27ad0539069bd99dc05f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I9cFpSOAU2G3gEZmR3ou6NPkERO6UZFyIR7KtjgCbyU4rCdlvy/soYlDD8cKfvuPCIcF+B1F+7sx6TDKA4eIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T06:57:47.719121Z","bundle_sha256":"4a0cf9fbf58fe7159f20070af460ea588c8f29655fd43ecdf6e3618dcce30744"}}