{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TUTTGIHHW32IK3UFN4SJ37KPPJ","short_pith_number":"pith:TUTTGIHH","canonical_record":{"source":{"id":"2105.00043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-30T18:53:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5afc3e8e473fe0769d14fcdd4cb62ab904f88bcbdbe5baf2251d49a8a45e2bb7","abstract_canon_sha256":"6633699924d1221f19fe48a692d8b17c809e6430eae51cd9285f5851a9eb808b"},"schema_version":"1.0"},"canonical_sha256":"9d273320e7b6f4856e856f249dfd4f7a708fb8b479f9db5decd5f2b704f5cc45","source":{"kind":"arxiv","id":"2105.00043","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.00043","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2105.00043v1","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00043","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"TUTTGIHHW32I","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"TUTTGIHHW32IK3UF","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"TUTTGIHH","created_at":"2026-07-05T02:36:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TUTTGIHHW32IK3UFN4SJ37KPPJ","target":"record","payload":{"canonical_record":{"source":{"id":"2105.00043","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-30T18:53:09Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"5afc3e8e473fe0769d14fcdd4cb62ab904f88bcbdbe5baf2251d49a8a45e2bb7","abstract_canon_sha256":"6633699924d1221f19fe48a692d8b17c809e6430eae51cd9285f5851a9eb808b"},"schema_version":"1.0"},"canonical_sha256":"9d273320e7b6f4856e856f249dfd4f7a708fb8b479f9db5decd5f2b704f5cc45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:36:33.203097Z","signature_b64":"+7CbbSEvHlmLfogBBUBzXgPgh7fSWtNkeFQ2IrLRKQ/91fdcn2Mfn/nLKYcZOJ008pa5NBCM4jQEIKZY6pJ9Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d273320e7b6f4856e856f249dfd4f7a708fb8b479f9db5decd5f2b704f5cc45","last_reissued_at":"2026-07-05T02:36:33.202647Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:36:33.202647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.00043","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":"2026-07-05T02:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKJUGWI7GfzhDWqi2oK19qPK7gMrDHoD+JHzXVRwinwH7d4Rj7PoCnSvdzcFOw9fG2hfcWUBn1RQwigral/PAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:34:06.848518Z"},"content_sha256":"d0e0984852e0ecb221d969ae44e727d3f5f4376b5e6eea5da0167a409ce14dca","schema_version":"1.0","event_id":"sha256:d0e0984852e0ecb221d969ae44e727d3f5f4376b5e6eea5da0167a409ce14dca"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TUTTGIHHW32IK3UFN4SJ37KPPJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Submodular Mutual Information for Targeted Data Subset Selection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Ganesh Ramakrishnan, Jeff Bilmes, Rishabh Iyer, Suraj Kothawade, Vishal Kaushal","submitted_at":"2021-04-30T18:53:09Z","abstract_excerpt":"With the rapid growth of data, it is becoming increasingly difficult to train or improve deep learning models with the right subset of data. We show that this problem can be effectively solved at an additional labeling cost by targeted data subset selection(TSS) where a subset of unlabeled data points similar to an auxiliary set are added to the training data. We do so by using a rich class of Submodular Mutual Information (SMI) functions and demonstrate its effectiveness for image classification on CIFAR-10 and MNIST datasets. Lastly, we compare the performance of SMI functions for TSS with o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00043","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/2105.00043/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":"2026-07-05T02:36:33Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bq59JcWNmynjASyNnVGwhiyStVsbNvTRQgCB2QcsW2Hb1Pk4FQjjLA20Wq3LR7MC5Jl0RHL80LD99YdPGp1DAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T05:34:06.849023Z"},"content_sha256":"55f6b636ca87afdc0964ea326ac7d03ba8dca08947567a80eb4f9000b5a9698d","schema_version":"1.0","event_id":"sha256:55f6b636ca87afdc0964ea326ac7d03ba8dca08947567a80eb4f9000b5a9698d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TUTTGIHHW32IK3UFN4SJ37KPPJ/bundle.json","state_url":"https://pith.science/pith/TUTTGIHHW32IK3UFN4SJ37KPPJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TUTTGIHHW32IK3UFN4SJ37KPPJ/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":"2026-08-12T05:34:06Z","links":{"resolver":"https://pith.science/pith/TUTTGIHHW32IK3UFN4SJ37KPPJ","bundle":"https://pith.science/pith/TUTTGIHHW32IK3UFN4SJ37KPPJ/bundle.json","state":"https://pith.science/pith/TUTTGIHHW32IK3UFN4SJ37KPPJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TUTTGIHHW32IK3UFN4SJ37KPPJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TUTTGIHHW32IK3UFN4SJ37KPPJ","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":"6633699924d1221f19fe48a692d8b17c809e6430eae51cd9285f5851a9eb808b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-30T18:53:09Z","title_canon_sha256":"5afc3e8e473fe0769d14fcdd4cb62ab904f88bcbdbe5baf2251d49a8a45e2bb7"},"schema_version":"1.0","source":{"id":"2105.00043","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.00043","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"arxiv_version","alias_value":"2105.00043v1","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.00043","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"pith_short_12","alias_value":"TUTTGIHHW32I","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"pith_short_16","alias_value":"TUTTGIHHW32IK3UF","created_at":"2026-07-05T02:36:33Z"},{"alias_kind":"pith_short_8","alias_value":"TUTTGIHH","created_at":"2026-07-05T02:36:33Z"}],"graph_snapshots":[{"event_id":"sha256:55f6b636ca87afdc0964ea326ac7d03ba8dca08947567a80eb4f9000b5a9698d","target":"graph","created_at":"2026-07-05T02:36:33Z","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/2105.00043/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the rapid growth of data, it is becoming increasingly difficult to train or improve deep learning models with the right subset of data. We show that this problem can be effectively solved at an additional labeling cost by targeted data subset selection(TSS) where a subset of unlabeled data points similar to an auxiliary set are added to the training data. We do so by using a rich class of Submodular Mutual Information (SMI) functions and demonstrate its effectiveness for image classification on CIFAR-10 and MNIST datasets. Lastly, we compare the performance of SMI functions for TSS with o","authors_text":"Ganesh Ramakrishnan, Jeff Bilmes, Rishabh Iyer, Suraj Kothawade, Vishal Kaushal","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-30T18:53:09Z","title":"Submodular Mutual Information for Targeted Data Subset Selection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.00043","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:d0e0984852e0ecb221d969ae44e727d3f5f4376b5e6eea5da0167a409ce14dca","target":"record","created_at":"2026-07-05T02:36:33Z","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":"6633699924d1221f19fe48a692d8b17c809e6430eae51cd9285f5851a9eb808b","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-04-30T18:53:09Z","title_canon_sha256":"5afc3e8e473fe0769d14fcdd4cb62ab904f88bcbdbe5baf2251d49a8a45e2bb7"},"schema_version":"1.0","source":{"id":"2105.00043","kind":"arxiv","version":1}},"canonical_sha256":"9d273320e7b6f4856e856f249dfd4f7a708fb8b479f9db5decd5f2b704f5cc45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9d273320e7b6f4856e856f249dfd4f7a708fb8b479f9db5decd5f2b704f5cc45","first_computed_at":"2026-07-05T02:36:33.202647Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:36:33.202647Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+7CbbSEvHlmLfogBBUBzXgPgh7fSWtNkeFQ2IrLRKQ/91fdcn2Mfn/nLKYcZOJ008pa5NBCM4jQEIKZY6pJ9Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T02:36:33.203097Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.00043","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d0e0984852e0ecb221d969ae44e727d3f5f4376b5e6eea5da0167a409ce14dca","sha256:55f6b636ca87afdc0964ea326ac7d03ba8dca08947567a80eb4f9000b5a9698d"],"state_sha256":"58dc8b8e3e2aa6f82ff429242c9cc5b72ffefdecc43c2eb8b05de1f5fe00cbbb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tvliwJiq+h3yl2pOYVf3/gocR/T50Rf0HUkwK6lFxc03QDaz9V81/TGKqMRAuirfyv+Hh2C6xDfjvcaujgefBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T05:34:06.853047Z","bundle_sha256":"042a7dd8384e378d16a9a31dc3911de888568bbb1fac11705c1b9b9e44d476fa"}}