{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:O7FOYONHJMZ6B4U5RJOUHLDHV7","short_pith_number":"pith:O7FOYONH","canonical_record":{"source":{"id":"2504.16277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T21:25:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb8b3155799a098ee3aff723cf73d1c32948bfb2bff3d200a02959c214406fc2","abstract_canon_sha256":"fce02d19c849f681cb98006b3f170ba357da6feef9ea61debb58009c31dbb3fb"},"schema_version":"1.0"},"canonical_sha256":"77caec39a74b33e0f29d8a5d43ac67afeeca29b27707ac9bd9ee9f9f8b1cee38","source":{"kind":"arxiv","id":"2504.16277","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16277","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16277v1","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16277","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"pith_short_12","alias_value":"O7FOYONHJMZ6","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"pith_short_16","alias_value":"O7FOYONHJMZ6B4U5","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"pith_short_8","alias_value":"O7FOYONH","created_at":"2026-07-05T10:52:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:O7FOYONHJMZ6B4U5RJOUHLDHV7","target":"record","payload":{"canonical_record":{"source":{"id":"2504.16277","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T21:25:14Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"bb8b3155799a098ee3aff723cf73d1c32948bfb2bff3d200a02959c214406fc2","abstract_canon_sha256":"fce02d19c849f681cb98006b3f170ba357da6feef9ea61debb58009c31dbb3fb"},"schema_version":"1.0"},"canonical_sha256":"77caec39a74b33e0f29d8a5d43ac67afeeca29b27707ac9bd9ee9f9f8b1cee38","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:52:44.124863Z","signature_b64":"ldI/E3HQQwbdR413LTOb17zJi7hGIqhwtv0XF53+r9dFfjSOMFx0h5PtCEJ8vpoar+GCU5DLAHVjLztKDIi7DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"77caec39a74b33e0f29d8a5d43ac67afeeca29b27707ac9bd9ee9f9f8b1cee38","last_reissued_at":"2026-07-05T10:52:44.124387Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:52:44.124387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2504.16277","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":"2026-07-05T10:52:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kjlKn326eFwL4DGlaHjhmlWoG0mXQt2TnDQPBDhNrLRH6GS0Gx31lmUWWgpb72gfw8Gney+M8YPCMnxV+d3UCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:44:45.269724Z"},"content_sha256":"0b38918b64cf2e4c1b9a6492f8c4f06e1e333f7be2d06b045eca4688994471dd","schema_version":"1.0","event_id":"sha256:0b38918b64cf2e4c1b9a6492f8c4f06e1e333f7be2d06b045eca4688994471dd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:O7FOYONHJMZ6B4U5RJOUHLDHV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DataS^3: Dataset Subset Selection for Specialization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Abigail O'Neil, Alaa Maalouf, Daniela Rus, Daniel Yang, Gabriel Tseng, Hannah Kerner, Irene Chen, Judy Hansen Shen, Ken Goldberg, Levi Cai, Mike Walmsley, Neha Hulkund, Sandeep Mukherjee, Sara Beery, Timm Haucke, Tsun-Hsuan Wang, Vikram Ramaswamy, Yogesh Girdhar","submitted_at":"2025-04-22T21:25:14Z","abstract_excerpt":"In many real-world machine learning (ML) applications (e.g. detecting broken bones in x-ray images, detecting species in camera traps), in practice models need to perform well on specific deployments (e.g. a specific hospital, a specific national park) rather than the domain broadly. However, deployments often have imbalanced, unique data distributions. Discrepancy between the training distribution and the deployment distribution can lead to suboptimal performance, highlighting the need to select deployment-specialized subsets from the available training data. We formalize dataset subset selec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16277","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/2504.16277/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":"2026-07-05T10:52:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"53AxpC+8mdnAlyKgvJgs8eFoqecPZSxK8YzYFPQLBOju5gxH7hzFo/pYz6ott/NvSUEC3Y5o2G0v5vDXGNMyDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T13:44:45.270296Z"},"content_sha256":"981b378f1b11afc2f34ffa8d1826f8297234f67b148d2bb432d44c7a476fd756","schema_version":"1.0","event_id":"sha256:981b378f1b11afc2f34ffa8d1826f8297234f67b148d2bb432d44c7a476fd756"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/O7FOYONHJMZ6B4U5RJOUHLDHV7/bundle.json","state_url":"https://pith.science/pith/O7FOYONHJMZ6B4U5RJOUHLDHV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/O7FOYONHJMZ6B4U5RJOUHLDHV7/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":"2026-07-07T13:44:45Z","links":{"resolver":"https://pith.science/pith/O7FOYONHJMZ6B4U5RJOUHLDHV7","bundle":"https://pith.science/pith/O7FOYONHJMZ6B4U5RJOUHLDHV7/bundle.json","state":"https://pith.science/pith/O7FOYONHJMZ6B4U5RJOUHLDHV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/O7FOYONHJMZ6B4U5RJOUHLDHV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:O7FOYONHJMZ6B4U5RJOUHLDHV7","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":"fce02d19c849f681cb98006b3f170ba357da6feef9ea61debb58009c31dbb3fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T21:25:14Z","title_canon_sha256":"bb8b3155799a098ee3aff723cf73d1c32948bfb2bff3d200a02959c214406fc2"},"schema_version":"1.0","source":{"id":"2504.16277","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.16277","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"arxiv_version","alias_value":"2504.16277v1","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.16277","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"pith_short_12","alias_value":"O7FOYONHJMZ6","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"pith_short_16","alias_value":"O7FOYONHJMZ6B4U5","created_at":"2026-07-05T10:52:44Z"},{"alias_kind":"pith_short_8","alias_value":"O7FOYONH","created_at":"2026-07-05T10:52:44Z"}],"graph_snapshots":[{"event_id":"sha256:981b378f1b11afc2f34ffa8d1826f8297234f67b148d2bb432d44c7a476fd756","target":"graph","created_at":"2026-07-05T10:52:44Z","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/2504.16277/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In many real-world machine learning (ML) applications (e.g. detecting broken bones in x-ray images, detecting species in camera traps), in practice models need to perform well on specific deployments (e.g. a specific hospital, a specific national park) rather than the domain broadly. However, deployments often have imbalanced, unique data distributions. Discrepancy between the training distribution and the deployment distribution can lead to suboptimal performance, highlighting the need to select deployment-specialized subsets from the available training data. We formalize dataset subset selec","authors_text":"Abigail O'Neil, Alaa Maalouf, Daniela Rus, Daniel Yang, Gabriel Tseng, Hannah Kerner, Irene Chen, Judy Hansen Shen, Ken Goldberg, Levi Cai, Mike Walmsley, Neha Hulkund, Sandeep Mukherjee, Sara Beery, Timm Haucke, Tsun-Hsuan Wang, Vikram Ramaswamy, Yogesh Girdhar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T21:25:14Z","title":"DataS^3: Dataset Subset Selection for Specialization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.16277","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":"sha256:0b38918b64cf2e4c1b9a6492f8c4f06e1e333f7be2d06b045eca4688994471dd","target":"record","created_at":"2026-07-05T10:52:44Z","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":"fce02d19c849f681cb98006b3f170ba357da6feef9ea61debb58009c31dbb3fb","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-04-22T21:25:14Z","title_canon_sha256":"bb8b3155799a098ee3aff723cf73d1c32948bfb2bff3d200a02959c214406fc2"},"schema_version":"1.0","source":{"id":"2504.16277","kind":"arxiv","version":1}},"canonical_sha256":"77caec39a74b33e0f29d8a5d43ac67afeeca29b27707ac9bd9ee9f9f8b1cee38","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"77caec39a74b33e0f29d8a5d43ac67afeeca29b27707ac9bd9ee9f9f8b1cee38","first_computed_at":"2026-07-05T10:52:44.124387Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:52:44.124387Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ldI/E3HQQwbdR413LTOb17zJi7hGIqhwtv0XF53+r9dFfjSOMFx0h5PtCEJ8vpoar+GCU5DLAHVjLztKDIi7DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:52:44.124863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.16277","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b38918b64cf2e4c1b9a6492f8c4f06e1e333f7be2d06b045eca4688994471dd","sha256:981b378f1b11afc2f34ffa8d1826f8297234f67b148d2bb432d44c7a476fd756"],"state_sha256":"c4f2240c8c8b6eb6b75334aaba26e45fbb6292c7b85c3cb9b11df6a8eb4c4614"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ceS1zfAp/8F7IRI+TYw2ptn5BNxJEGc5dBycYDmgFa2j21HUfddA3sEbMBneniZTm1/H6eAffCphdUsMGH9ICA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T13:44:45.272252Z","bundle_sha256":"039e5acc70f918326107e86a5d052e736cb3f8fc0875c7478b71ec80dbe609e6"}}