{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:DRISY7N7HDA5E2C4AAUQJYR4RX","short_pith_number":"pith:DRISY7N7","canonical_record":{"source":{"id":"2109.03216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-07T17:30:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e9d423a0b4134600108dfc958a4010d75d12bf7b651661e25275dab6f6800b69","abstract_canon_sha256":"c80b4061cf5b015ac4e6d6c1858cfa09ac0bb182e46fb6a9b7e4f00b47fe9f0c"},"schema_version":"1.0"},"canonical_sha256":"1c512c7dbf38c1d2685c002904e23c8defe9f0c74b70467ef4a50217b8d16f69","source":{"kind":"arxiv","id":"2109.03216","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.03216","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"2109.03216v1","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03216","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"DRISY7N7HDA5","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"pith_short_16","alias_value":"DRISY7N7HDA5E2C4","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"pith_short_8","alias_value":"DRISY7N7","created_at":"2026-07-05T03:12:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:DRISY7N7HDA5E2C4AAUQJYR4RX","target":"record","payload":{"canonical_record":{"source":{"id":"2109.03216","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-07T17:30:56Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"e9d423a0b4134600108dfc958a4010d75d12bf7b651661e25275dab6f6800b69","abstract_canon_sha256":"c80b4061cf5b015ac4e6d6c1858cfa09ac0bb182e46fb6a9b7e4f00b47fe9f0c"},"schema_version":"1.0"},"canonical_sha256":"1c512c7dbf38c1d2685c002904e23c8defe9f0c74b70467ef4a50217b8d16f69","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:12:24.874237Z","signature_b64":"67Q60OjIYfcpVvC1H6EWkQeiiT6p5w+C0SytgDSastiKqUP6Xh6MLXy66Dbk5xPYVfORPd8Bxpu6wKNhY8ZhCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c512c7dbf38c1d2685c002904e23c8defe9f0c74b70467ef4a50217b8d16f69","last_reissued_at":"2026-07-05T03:12:24.873856Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:12:24.873856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2109.03216","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":"2026-07-05T03:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CzoXMjTlEuIfv6LXTKJMrTdI53GEVpgRlLzB6LcKTTk3RYEEmZO9ICBtSOz/unxBLk6tOARl0jMZbtgZDnieBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:23:51.494420Z"},"content_sha256":"3f19b9fca91ead72cbbad675db9e8897e4c458a3570e5675b32c068d6b509776","schema_version":"1.0","event_id":"sha256:3f19b9fca91ead72cbbad675db9e8897e4c458a3570e5675b32c068d6b509776"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:DRISY7N7HDA5E2C4AAUQJYR4RX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Fast Sample Re-weighting Without Reward Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Tomas Pfister, Zizhao Zhang","submitted_at":"2021-09-07T17:30:56Z","abstract_excerpt":"Training sample re-weighting is an effective approach for tackling data biases such as imbalanced and corrupted labels. Recent methods develop learning-based algorithms to learn sample re-weighting strategies jointly with model training based on the frameworks of reinforcement learning and meta learning. However, depending on additional unbiased reward data is limiting their general applicability. Furthermore, existing learning-based sample re-weighting methods require nested optimizations of models and weighting parameters, which requires expensive second-order computation. This paper address"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03216","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/2109.03216/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":"2026-07-05T03:12:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HRUglgur5OXLYzll7ZjOISgUCCqarS+eV/JE36JLZpc1o0dq8U3Zru6UpJuGwxVSJZASbwwd5MfU4iP406icAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T14:23:51.494802Z"},"content_sha256":"4066fd5d19651af60553366fe8aa7360540f3580f039bfc99ccb9023df3e2947","schema_version":"1.0","event_id":"sha256:4066fd5d19651af60553366fe8aa7360540f3580f039bfc99ccb9023df3e2947"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DRISY7N7HDA5E2C4AAUQJYR4RX/bundle.json","state_url":"https://pith.science/pith/DRISY7N7HDA5E2C4AAUQJYR4RX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DRISY7N7HDA5E2C4AAUQJYR4RX/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":"2026-07-07T14:23:51Z","links":{"resolver":"https://pith.science/pith/DRISY7N7HDA5E2C4AAUQJYR4RX","bundle":"https://pith.science/pith/DRISY7N7HDA5E2C4AAUQJYR4RX/bundle.json","state":"https://pith.science/pith/DRISY7N7HDA5E2C4AAUQJYR4RX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DRISY7N7HDA5E2C4AAUQJYR4RX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:DRISY7N7HDA5E2C4AAUQJYR4RX","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":"c80b4061cf5b015ac4e6d6c1858cfa09ac0bb182e46fb6a9b7e4f00b47fe9f0c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-07T17:30:56Z","title_canon_sha256":"e9d423a0b4134600108dfc958a4010d75d12bf7b651661e25275dab6f6800b69"},"schema_version":"1.0","source":{"id":"2109.03216","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.03216","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"arxiv_version","alias_value":"2109.03216v1","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.03216","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"pith_short_12","alias_value":"DRISY7N7HDA5","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"pith_short_16","alias_value":"DRISY7N7HDA5E2C4","created_at":"2026-07-05T03:12:24Z"},{"alias_kind":"pith_short_8","alias_value":"DRISY7N7","created_at":"2026-07-05T03:12:24Z"}],"graph_snapshots":[{"event_id":"sha256:4066fd5d19651af60553366fe8aa7360540f3580f039bfc99ccb9023df3e2947","target":"graph","created_at":"2026-07-05T03:12:24Z","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/2109.03216/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training sample re-weighting is an effective approach for tackling data biases such as imbalanced and corrupted labels. Recent methods develop learning-based algorithms to learn sample re-weighting strategies jointly with model training based on the frameworks of reinforcement learning and meta learning. However, depending on additional unbiased reward data is limiting their general applicability. Furthermore, existing learning-based sample re-weighting methods require nested optimizations of models and weighting parameters, which requires expensive second-order computation. This paper address","authors_text":"Tomas Pfister, Zizhao Zhang","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-07T17:30:56Z","title":"Learning Fast Sample Re-weighting Without Reward Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.03216","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":"sha256:3f19b9fca91ead72cbbad675db9e8897e4c458a3570e5675b32c068d6b509776","target":"record","created_at":"2026-07-05T03:12:24Z","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":"c80b4061cf5b015ac4e6d6c1858cfa09ac0bb182e46fb6a9b7e4f00b47fe9f0c","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-09-07T17:30:56Z","title_canon_sha256":"e9d423a0b4134600108dfc958a4010d75d12bf7b651661e25275dab6f6800b69"},"schema_version":"1.0","source":{"id":"2109.03216","kind":"arxiv","version":1}},"canonical_sha256":"1c512c7dbf38c1d2685c002904e23c8defe9f0c74b70467ef4a50217b8d16f69","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c512c7dbf38c1d2685c002904e23c8defe9f0c74b70467ef4a50217b8d16f69","first_computed_at":"2026-07-05T03:12:24.873856Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:12:24.873856Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"67Q60OjIYfcpVvC1H6EWkQeiiT6p5w+C0SytgDSastiKqUP6Xh6MLXy66Dbk5xPYVfORPd8Bxpu6wKNhY8ZhCw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:12:24.874237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.03216","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3f19b9fca91ead72cbbad675db9e8897e4c458a3570e5675b32c068d6b509776","sha256:4066fd5d19651af60553366fe8aa7360540f3580f039bfc99ccb9023df3e2947"],"state_sha256":"0e153bad0633d8eea69692893f5a01de6d5a88ebd130e619ef44d5e28584f011"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WOrH2uz8U6PshXYgVAnVNXlgm6HRaYH2kGCwlL3wGUAI+BwlvyXUz/hvfTAzaQAfk9yArKgSvoriBN+ooNYzCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T14:23:51.496792Z","bundle_sha256":"df47eaf1260d48b1e006c897fca7818feb1e3dc4e2fdc32ee3909e5e31537e37"}}