{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:D3LN57UI4JCZ54NB4KM65LVIV7","short_pith_number":"pith:D3LN57UI","canonical_record":{"source":{"id":"2402.07019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T18:36:42Z","cross_cats_sorted":[],"title_canon_sha256":"9ae1e4cc4f7b81c69e43df85ce9ee5b962ce7b67f2afa6d3dab1ee621b94424c","abstract_canon_sha256":"d1122443e9f8743d50cc49b542903c5189e180dcd3dd362aa7d87fa6632ba59d"},"schema_version":"1.0"},"canonical_sha256":"1ed6defe88e2459ef1a1e299eeaea8afe31c4816c08f858171cb3690460c5485","source":{"kind":"arxiv","id":"2402.07019","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07019","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07019v1","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07019","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"D3LN57UI4JCZ","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"pith_short_16","alias_value":"D3LN57UI4JCZ54NB","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"pith_short_8","alias_value":"D3LN57UI","created_at":"2026-07-05T07:43:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:D3LN57UI4JCZ54NB4KM65LVIV7","target":"record","payload":{"canonical_record":{"source":{"id":"2402.07019","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T18:36:42Z","cross_cats_sorted":[],"title_canon_sha256":"9ae1e4cc4f7b81c69e43df85ce9ee5b962ce7b67f2afa6d3dab1ee621b94424c","abstract_canon_sha256":"d1122443e9f8743d50cc49b542903c5189e180dcd3dd362aa7d87fa6632ba59d"},"schema_version":"1.0"},"canonical_sha256":"1ed6defe88e2459ef1a1e299eeaea8afe31c4816c08f858171cb3690460c5485","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:43:42.594421Z","signature_b64":"Qz12ulCzfeIrGGOPQq8bwqvnokwzN0KMgDEBE14YfViFOAvuUfzBeP53Nj2hyAUbbnjkZeI89zREX2cbuMYlBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1ed6defe88e2459ef1a1e299eeaea8afe31c4816c08f858171cb3690460c5485","last_reissued_at":"2026-07-05T07:43:42.594021Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:43:42.594021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.07019","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":"2026-07-05T07:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3MfqJMaKONPiT0F/En92OzRzkcoWks0Yd9oyUc2VQcUgi+N2o+XMen3Fa32Zzk74rPEsSTSL0jqYsLuBg5J2DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:16:12.140993Z"},"content_sha256":"19348e6efc7a55d7dcaf988a6be544883dc90ee5c9bda0c90ae69d13a04880f8","schema_version":"1.0","event_id":"sha256:19348e6efc7a55d7dcaf988a6be544883dc90ee5c9bda0c90ae69d13a04880f8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:D3LN57UI4JCZ54NB4KM65LVIV7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Informativeness of Reward Functions in Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Adish Singla, Parameswaran Kamalaruban, Rati Devidze","submitted_at":"2024-02-10T18:36:42Z","abstract_excerpt":"Reward functions are central in specifying the task we want a reinforcement learning agent to perform. Given a task and desired optimal behavior, we study the problem of designing informative reward functions so that the designed rewards speed up the agent's convergence. In particular, we consider expert-driven reward design settings where an expert or teacher seeks to provide informative and interpretable rewards to a learning agent. Existing works have considered several different reward design formulations; however, the key challenge is formulating a reward informativeness criterion that ad"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07019","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/2402.07019/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":"2026-07-05T07:43:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3N3PrpXGKWrLJQoiOHioNtTQOsEoQK31Dg+dQ0RSPaq6GYEqE8l5FqsrLS0z/bQ3vQc1W+fqFjZI/pbWRh3tAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T00:16:12.141580Z"},"content_sha256":"3f529bcb3869392cc6195e2ef37295a417d03bc51ac8004a3e423ea311732348","schema_version":"1.0","event_id":"sha256:3f529bcb3869392cc6195e2ef37295a417d03bc51ac8004a3e423ea311732348"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7/bundle.json","state_url":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D3LN57UI4JCZ54NB4KM65LVIV7/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":"2026-08-06T00:16:12Z","links":{"resolver":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7","bundle":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7/bundle.json","state":"https://pith.science/pith/D3LN57UI4JCZ54NB4KM65LVIV7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D3LN57UI4JCZ54NB4KM65LVIV7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:D3LN57UI4JCZ54NB4KM65LVIV7","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":"d1122443e9f8743d50cc49b542903c5189e180dcd3dd362aa7d87fa6632ba59d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T18:36:42Z","title_canon_sha256":"9ae1e4cc4f7b81c69e43df85ce9ee5b962ce7b67f2afa6d3dab1ee621b94424c"},"schema_version":"1.0","source":{"id":"2402.07019","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.07019","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"arxiv_version","alias_value":"2402.07019v1","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.07019","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"pith_short_12","alias_value":"D3LN57UI4JCZ","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"pith_short_16","alias_value":"D3LN57UI4JCZ54NB","created_at":"2026-07-05T07:43:42Z"},{"alias_kind":"pith_short_8","alias_value":"D3LN57UI","created_at":"2026-07-05T07:43:42Z"}],"graph_snapshots":[{"event_id":"sha256:3f529bcb3869392cc6195e2ef37295a417d03bc51ac8004a3e423ea311732348","target":"graph","created_at":"2026-07-05T07:43:42Z","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/2402.07019/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Reward functions are central in specifying the task we want a reinforcement learning agent to perform. Given a task and desired optimal behavior, we study the problem of designing informative reward functions so that the designed rewards speed up the agent's convergence. In particular, we consider expert-driven reward design settings where an expert or teacher seeks to provide informative and interpretable rewards to a learning agent. Existing works have considered several different reward design formulations; however, the key challenge is formulating a reward informativeness criterion that ad","authors_text":"Adish Singla, Parameswaran Kamalaruban, Rati Devidze","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T18:36:42Z","title":"Informativeness of Reward Functions in Reinforcement Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.07019","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":"sha256:19348e6efc7a55d7dcaf988a6be544883dc90ee5c9bda0c90ae69d13a04880f8","target":"record","created_at":"2026-07-05T07:43:42Z","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":"d1122443e9f8743d50cc49b542903c5189e180dcd3dd362aa7d87fa6632ba59d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-10T18:36:42Z","title_canon_sha256":"9ae1e4cc4f7b81c69e43df85ce9ee5b962ce7b67f2afa6d3dab1ee621b94424c"},"schema_version":"1.0","source":{"id":"2402.07019","kind":"arxiv","version":1}},"canonical_sha256":"1ed6defe88e2459ef1a1e299eeaea8afe31c4816c08f858171cb3690460c5485","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1ed6defe88e2459ef1a1e299eeaea8afe31c4816c08f858171cb3690460c5485","first_computed_at":"2026-07-05T07:43:42.594021Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:43:42.594021Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Qz12ulCzfeIrGGOPQq8bwqvnokwzN0KMgDEBE14YfViFOAvuUfzBeP53Nj2hyAUbbnjkZeI89zREX2cbuMYlBw==","signature_status":"signed_v1","signed_at":"2026-07-05T07:43:42.594421Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.07019","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:19348e6efc7a55d7dcaf988a6be544883dc90ee5c9bda0c90ae69d13a04880f8","sha256:3f529bcb3869392cc6195e2ef37295a417d03bc51ac8004a3e423ea311732348"],"state_sha256":"50eb8e4b49aa06401e31bfc4f08ad3caff63ea25c24f11e9f353a2b74e9ef7b9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ATyZhp3FSvLpLlSGG3fKuefSS6af1yb0vP/qCtniwJEUY2l4CVPpZUKCdlY+cOiEX3G9eaxwR4kakLZ4FzAYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T00:16:12.146740Z","bundle_sha256":"cb5c8462b45c11374fdb3a082cc6520847521416f6e33a2a6ef01671b03320d0"}}