{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:T7AAUEZM25MNPMURX7VG3S5QV6","short_pith_number":"pith:T7AAUEZM","canonical_record":{"source":{"id":"2203.06404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-12T10:50:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d1993e044c0484430b39f844b484c996d6e66881a6297877f54713e735c75d01","abstract_canon_sha256":"1c5fd55930d5183f8c637f992d084b36cadeed7ad3576cedee92f9a79053a3e3"},"schema_version":"1.0"},"canonical_sha256":"9fc00a132cd758d7b291bfea6dcbb0af9f60e86ca7ea7b8fb37d0201b6e5aef6","source":{"kind":"arxiv","id":"2203.06404","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06404","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06404v1","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06404","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"T7AAUEZM25MN","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"T7AAUEZM25MNPMUR","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"T7AAUEZM","created_at":"2026-07-05T04:04:50Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:T7AAUEZM25MNPMURX7VG3S5QV6","target":"record","payload":{"canonical_record":{"source":{"id":"2203.06404","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-12T10:50:13Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d1993e044c0484430b39f844b484c996d6e66881a6297877f54713e735c75d01","abstract_canon_sha256":"1c5fd55930d5183f8c637f992d084b36cadeed7ad3576cedee92f9a79053a3e3"},"schema_version":"1.0"},"canonical_sha256":"9fc00a132cd758d7b291bfea6dcbb0af9f60e86ca7ea7b8fb37d0201b6e5aef6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:50.351897Z","signature_b64":"y9TxmK5cMcYTRE9okVaDqVeNuGVs63rreM6EwCr93H9vqNztcNLLr6kj3WfMhhtwh/TwXdaYEhFFNqIL84X/Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fc00a132cd758d7b291bfea6dcbb0af9f60e86ca7ea7b8fb37d0201b6e5aef6","last_reissued_at":"2026-07-05T04:04:50.351476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:50.351476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.06404","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":"2026-07-05T04:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BaoPvuq6XIsAG9M6M+KJ83/AddwgTFkPxn56rTw9Ji+7zUDl52u4yS9ET8EfoTjP0XEG2QTNaZb2/V+8Y0KnDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:16:13.033024Z"},"content_sha256":"aa760a6af4d51c8a189046452297acfa7ad96da065632d21d060ee15d8469c38","schema_version":"1.0","event_id":"sha256:aa760a6af4d51c8a189046452297acfa7ad96da065632d21d060ee15d8469c38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:T7AAUEZM25MNPMURX7VG3S5QV6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Proposal to Study \"Is High Quality Data All We Need?\"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Anjana Arunkumar, Swaroop Mishra","submitted_at":"2022-03-12T10:50:13Z","abstract_excerpt":"Even though deep neural models have achieved superhuman performance on many popular benchmarks, they have failed to generalize to OOD or adversarial datasets. Conventional approaches aimed at increasing robustness include developing increasingly large models and augmentation with large scale datasets. However, orthogonal to these trends, we hypothesize that a smaller, high quality dataset is what we need. Our hypothesis is based on the fact that deep neural networks are data driven models, and data is what leads/misleads models. In this work, we propose an empirical study that examines how to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06404","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/2203.06404/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":"2026-07-05T04:04:50Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gr7Ht+XrqWxgmVQF5fopybL6HOnt8d8aG95u72jC78UltaljpU8kW4/yhCe0i8inXX/89ZAxZMswHqo1m6YNBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T13:16:13.033872Z"},"content_sha256":"6eb513f1a9d462fd7e5b18efff6dae58eadc01b6785b262fdbef915b05d51407","schema_version":"1.0","event_id":"sha256:6eb513f1a9d462fd7e5b18efff6dae58eadc01b6785b262fdbef915b05d51407"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6/bundle.json","state_url":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7AAUEZM25MNPMURX7VG3S5QV6/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":"2026-08-08T13:16:13Z","links":{"resolver":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6","bundle":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6/bundle.json","state":"https://pith.science/pith/T7AAUEZM25MNPMURX7VG3S5QV6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7AAUEZM25MNPMURX7VG3S5QV6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:T7AAUEZM25MNPMURX7VG3S5QV6","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":"1c5fd55930d5183f8c637f992d084b36cadeed7ad3576cedee92f9a79053a3e3","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-12T10:50:13Z","title_canon_sha256":"d1993e044c0484430b39f844b484c996d6e66881a6297877f54713e735c75d01"},"schema_version":"1.0","source":{"id":"2203.06404","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06404","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06404v1","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06404","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"pith_short_12","alias_value":"T7AAUEZM25MN","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"pith_short_16","alias_value":"T7AAUEZM25MNPMUR","created_at":"2026-07-05T04:04:50Z"},{"alias_kind":"pith_short_8","alias_value":"T7AAUEZM","created_at":"2026-07-05T04:04:50Z"}],"graph_snapshots":[{"event_id":"sha256:6eb513f1a9d462fd7e5b18efff6dae58eadc01b6785b262fdbef915b05d51407","target":"graph","created_at":"2026-07-05T04:04:50Z","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/2203.06404/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Even though deep neural models have achieved superhuman performance on many popular benchmarks, they have failed to generalize to OOD or adversarial datasets. Conventional approaches aimed at increasing robustness include developing increasingly large models and augmentation with large scale datasets. However, orthogonal to these trends, we hypothesize that a smaller, high quality dataset is what we need. Our hypothesis is based on the fact that deep neural networks are data driven models, and data is what leads/misleads models. In this work, we propose an empirical study that examines how to ","authors_text":"Anjana Arunkumar, Swaroop Mishra","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-12T10:50:13Z","title":"A Proposal to Study \"Is High Quality Data All We Need?\""},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06404","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:aa760a6af4d51c8a189046452297acfa7ad96da065632d21d060ee15d8469c38","target":"record","created_at":"2026-07-05T04:04:50Z","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":"1c5fd55930d5183f8c637f992d084b36cadeed7ad3576cedee92f9a79053a3e3","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2022-03-12T10:50:13Z","title_canon_sha256":"d1993e044c0484430b39f844b484c996d6e66881a6297877f54713e735c75d01"},"schema_version":"1.0","source":{"id":"2203.06404","kind":"arxiv","version":1}},"canonical_sha256":"9fc00a132cd758d7b291bfea6dcbb0af9f60e86ca7ea7b8fb37d0201b6e5aef6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fc00a132cd758d7b291bfea6dcbb0af9f60e86ca7ea7b8fb37d0201b6e5aef6","first_computed_at":"2026-07-05T04:04:50.351476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:50.351476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"y9TxmK5cMcYTRE9okVaDqVeNuGVs63rreM6EwCr93H9vqNztcNLLr6kj3WfMhhtwh/TwXdaYEhFFNqIL84X/Dg==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:50.351897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.06404","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa760a6af4d51c8a189046452297acfa7ad96da065632d21d060ee15d8469c38","sha256:6eb513f1a9d462fd7e5b18efff6dae58eadc01b6785b262fdbef915b05d51407"],"state_sha256":"2f10e89634ab7f5683a53dfe5a5cee72eec7cb4cbe51b1467370ef48d5b63f2b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"txRC5liRe14zZL2Xh6kH2MDkmftIPkhvfpyJoW89/Cur6D05EuIinxYCnaUXCM0WAcn3m2leNZCp0/04esI+Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T13:16:13.039670Z","bundle_sha256":"7200612dd8bb1efbdf962902e1cf589d507393ac6af83a351b03f4c1d3b6a2ce"}}