{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:54KQJ2ZCKFZLOVZ7UTMNCF4EC7","short_pith_number":"pith:54KQJ2ZC","canonical_record":{"source":{"id":"2208.10483","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T17:55:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a76d692dd607eaf326a0aead7ce36225ddfb467c4e3d29e53328187c554b6e0a","abstract_canon_sha256":"4b9eae634c11cf5b3c33cba31e8ac56fe39959282a057e10d99dce3eb4825717"},"schema_version":"1.0"},"canonical_sha256":"ef1504eb225172b7573fa4d8d1178417d608ab5ccf812b787aae1eb83961790b","source":{"kind":"arxiv","id":"2208.10483","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10483","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10483v3","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10483","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"pith_short_12","alias_value":"54KQJ2ZCKFZL","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"pith_short_16","alias_value":"54KQJ2ZCKFZLOVZ7","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"pith_short_8","alias_value":"54KQJ2ZC","created_at":"2026-07-05T07:07:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:54KQJ2ZCKFZLOVZ7UTMNCF4EC7","target":"record","payload":{"canonical_record":{"source":{"id":"2208.10483","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T17:55:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a76d692dd607eaf326a0aead7ce36225ddfb467c4e3d29e53328187c554b6e0a","abstract_canon_sha256":"4b9eae634c11cf5b3c33cba31e8ac56fe39959282a057e10d99dce3eb4825717"},"schema_version":"1.0"},"canonical_sha256":"ef1504eb225172b7573fa4d8d1178417d608ab5ccf812b787aae1eb83961790b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:07:51.573236Z","signature_b64":"7bxpsU71jNCB3Gp2Ox0DSCKacfHSAEa/modtAALaA2Sl9Ua/tLAa0znKcWznQkBivmgz8fTmBSG71nHMa5S0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef1504eb225172b7573fa4d8d1178417d608ab5ccf812b787aae1eb83961790b","last_reissued_at":"2026-07-05T07:07:51.572823Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:07:51.572823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2208.10483","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:07:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xmZobQ1ERlnV4qHH+DHcC8JAoe/2jsL/V2oaQ1KlLF8w5nh1PEKLm62VofGOpyQ803NhrXvzOp1onmfDedy6Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:23:46.841264Z"},"content_sha256":"e716eba75faeeb66cbed59033b24ee2e66c6db2905249de1af9be055b06efa73","schema_version":"1.0","event_id":"sha256:e716eba75faeeb66cbed59033b24ee2e66c6db2905249de1af9be055b06efa73"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:54KQJ2ZCKFZLOVZ7UTMNCF4EC7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Prioritizing Samples in Reinforcement Learning with Reducible Loss","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Pedro H. M. Braga, Samira Ebrahimi Kahou, Shivakanth Sujit, Somjit Nath","submitted_at":"2022-08-22T17:55:43Z","abstract_excerpt":"Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed in the past. Not all samples carry the same amount of significance and simply assigning equal importance to each of the samples is a na\\\"ive strategy. In this paper, we propose a method to prioritize samples based on how much we can learn from a sample. We define the learn-ability of a sample as the steady decrease of the training loss associated with this sample over time. We develop an algorithm to prioritize samples with high learn-ability, while assigni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10483","kind":"arxiv","version":3},"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/2208.10483/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":"2026-07-05T07:07:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lW92WO+IhUCiDsCNAZgQXSx/7O5MreVllBGIU7/hdR3vxmcWYgB0cppRAyp4DeayQYLOt7jLIUTSias35lXrCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T16:23:46.841662Z"},"content_sha256":"106dfa0b02b351f51e21264a4924927a11911a33f13d2154a71902f4d00e2a3c","schema_version":"1.0","event_id":"sha256:106dfa0b02b351f51e21264a4924927a11911a33f13d2154a71902f4d00e2a3c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/54KQJ2ZCKFZLOVZ7UTMNCF4EC7/bundle.json","state_url":"https://pith.science/pith/54KQJ2ZCKFZLOVZ7UTMNCF4EC7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/54KQJ2ZCKFZLOVZ7UTMNCF4EC7/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":"2026-07-06T16:23:46Z","links":{"resolver":"https://pith.science/pith/54KQJ2ZCKFZLOVZ7UTMNCF4EC7","bundle":"https://pith.science/pith/54KQJ2ZCKFZLOVZ7UTMNCF4EC7/bundle.json","state":"https://pith.science/pith/54KQJ2ZCKFZLOVZ7UTMNCF4EC7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/54KQJ2ZCKFZLOVZ7UTMNCF4EC7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:54KQJ2ZCKFZLOVZ7UTMNCF4EC7","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":"4b9eae634c11cf5b3c33cba31e8ac56fe39959282a057e10d99dce3eb4825717","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T17:55:43Z","title_canon_sha256":"a76d692dd607eaf326a0aead7ce36225ddfb467c4e3d29e53328187c554b6e0a"},"schema_version":"1.0","source":{"id":"2208.10483","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2208.10483","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"arxiv_version","alias_value":"2208.10483v3","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2208.10483","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"pith_short_12","alias_value":"54KQJ2ZCKFZL","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"pith_short_16","alias_value":"54KQJ2ZCKFZLOVZ7","created_at":"2026-07-05T07:07:51Z"},{"alias_kind":"pith_short_8","alias_value":"54KQJ2ZC","created_at":"2026-07-05T07:07:51Z"}],"graph_snapshots":[{"event_id":"sha256:106dfa0b02b351f51e21264a4924927a11911a33f13d2154a71902f4d00e2a3c","target":"graph","created_at":"2026-07-05T07:07:51Z","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/2208.10483/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most reinforcement learning algorithms take advantage of an experience replay buffer to repeatedly train on samples the agent has observed in the past. Not all samples carry the same amount of significance and simply assigning equal importance to each of the samples is a na\\\"ive strategy. In this paper, we propose a method to prioritize samples based on how much we can learn from a sample. We define the learn-ability of a sample as the steady decrease of the training loss associated with this sample over time. We develop an algorithm to prioritize samples with high learn-ability, while assigni","authors_text":"Pedro H. M. Braga, Samira Ebrahimi Kahou, Shivakanth Sujit, Somjit Nath","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T17:55:43Z","title":"Prioritizing Samples in Reinforcement Learning with Reducible Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2208.10483","kind":"arxiv","version":3},"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:e716eba75faeeb66cbed59033b24ee2e66c6db2905249de1af9be055b06efa73","target":"record","created_at":"2026-07-05T07:07:51Z","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":"4b9eae634c11cf5b3c33cba31e8ac56fe39959282a057e10d99dce3eb4825717","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-08-22T17:55:43Z","title_canon_sha256":"a76d692dd607eaf326a0aead7ce36225ddfb467c4e3d29e53328187c554b6e0a"},"schema_version":"1.0","source":{"id":"2208.10483","kind":"arxiv","version":3}},"canonical_sha256":"ef1504eb225172b7573fa4d8d1178417d608ab5ccf812b787aae1eb83961790b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ef1504eb225172b7573fa4d8d1178417d608ab5ccf812b787aae1eb83961790b","first_computed_at":"2026-07-05T07:07:51.572823Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:07:51.572823Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7bxpsU71jNCB3Gp2Ox0DSCKacfHSAEa/modtAALaA2Sl9Ua/tLAa0znKcWznQkBivmgz8fTmBSG71nHMa5S0DA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:07:51.573236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2208.10483","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e716eba75faeeb66cbed59033b24ee2e66c6db2905249de1af9be055b06efa73","sha256:106dfa0b02b351f51e21264a4924927a11911a33f13d2154a71902f4d00e2a3c"],"state_sha256":"68f394b9965b884f00c4789718e2d33b8c6b0ff2a65bff4d9dc4b716644c3164"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2hzn0ZrO1g49bdh1x6/mFK8I2SMhrbcea/ML+g63VTqz7k9rUHc2WQJPSvzhJNxzF2IsoMfin8tqwpYDpFykCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T16:23:46.843601Z","bundle_sha256":"a52fe19d77b026eaeba3b8a1c29a879ce12aa6c6ade53443f858f71f32acac67"}}