{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:EQOMP7HK6KYGJTGNK2XYJQWH4V","short_pith_number":"pith:EQOMP7HK","canonical_record":{"source":{"id":"2210.16956","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-30T21:28:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"555f4e120029dc2a05a2d41afa74e67b487ece407e8432827fde4ab17d5fab2d","abstract_canon_sha256":"2c623525a3637fe612e4f57025a4b01a9d9fd1b5cda602b4d1a3088896b60c57"},"schema_version":"1.0"},"canonical_sha256":"241cc7fceaf2b064cccd56af84c2c7e566be8a3911f22c468f6700fff5b308b0","source":{"kind":"arxiv","id":"2210.16956","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16956","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16956v1","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16956","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"EQOMP7HK6KYG","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"EQOMP7HK6KYGJTGN","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"EQOMP7HK","created_at":"2026-07-05T05:11:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:EQOMP7HK6KYGJTGNK2XYJQWH4V","target":"record","payload":{"canonical_record":{"source":{"id":"2210.16956","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-30T21:28:22Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"555f4e120029dc2a05a2d41afa74e67b487ece407e8432827fde4ab17d5fab2d","abstract_canon_sha256":"2c623525a3637fe612e4f57025a4b01a9d9fd1b5cda602b4d1a3088896b60c57"},"schema_version":"1.0"},"canonical_sha256":"241cc7fceaf2b064cccd56af84c2c7e566be8a3911f22c468f6700fff5b308b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:11:52.972660Z","signature_b64":"XBxgrbqDxgBjpn8SM8oTTKiDK8QMhAW8JithLrBsG6oqRma9ektlgEqZ/v1a0zp6bY+S68x2PjlT0+wFYaz8Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"241cc7fceaf2b064cccd56af84c2c7e566be8a3911f22c468f6700fff5b308b0","last_reissued_at":"2026-07-05T05:11:52.972199Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:11:52.972199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.16956","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":"2026-07-05T05:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+j1waCHieVH8VLRJIzbjIEZT94knJwKPHp3h95FgPA9NJipQ+twdFORxJ2UO4gQYthrInv20TuZgFiwiwmkCBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:21:56.128692Z"},"content_sha256":"8a3cdf1f7dfc10cd0628c6653d04744d788f1b2d9a81928cc3685ed6404c2bf2","schema_version":"1.0","event_id":"sha256:8a3cdf1f7dfc10cd0628c6653d04744d788f1b2d9a81928cc3685ed6404c2bf2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:EQOMP7HK6KYGJTGNK2XYJQWH4V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Reward Shaping Using Convolutional Neural Network","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Azzam Mourad, Ernesto Damiani, Hadi Otrok, Hani Sami, Jamal Bentahar","submitted_at":"2022-10-30T21:28:22Z","abstract_excerpt":"In this paper, we propose Value Iteration Network for Reward Shaping (VIN-RS), a potential-based reward shaping mechanism using Convolutional Neural Network (CNN). The proposed VIN-RS embeds a CNN trained on computed labels using the message passing mechanism of the Hidden Markov Model. The CNN processes images or graphs of the environment to predict the shaping values. Recent work on reward shaping still has limitations towards training on a representation of the Markov Decision Process (MDP) and building an estimate of the transition matrix. The advantage of VIN-RS is to construct an effecti"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16956","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/2210.16956/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":"2026-07-05T05:11:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YfTmiJNjFxd8Q8/NxwW/PEVc4Elek/eJgSSUPurgzc1MUoEHq5h6ip97Djrw+HMIV74NGXyi68AAUTrIya1qAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T07:21:56.129038Z"},"content_sha256":"e1680bb6f1d44d772d4c10c25efd369896af7f141a385a40aedc20a9e0d0e10c","schema_version":"1.0","event_id":"sha256:e1680bb6f1d44d772d4c10c25efd369896af7f141a385a40aedc20a9e0d0e10c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/EQOMP7HK6KYGJTGNK2XYJQWH4V/bundle.json","state_url":"https://pith.science/pith/EQOMP7HK6KYGJTGNK2XYJQWH4V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/EQOMP7HK6KYGJTGNK2XYJQWH4V/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":"2026-08-20T07:21:56Z","links":{"resolver":"https://pith.science/pith/EQOMP7HK6KYGJTGNK2XYJQWH4V","bundle":"https://pith.science/pith/EQOMP7HK6KYGJTGNK2XYJQWH4V/bundle.json","state":"https://pith.science/pith/EQOMP7HK6KYGJTGNK2XYJQWH4V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/EQOMP7HK6KYGJTGNK2XYJQWH4V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:EQOMP7HK6KYGJTGNK2XYJQWH4V","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":"2c623525a3637fe612e4f57025a4b01a9d9fd1b5cda602b4d1a3088896b60c57","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-30T21:28:22Z","title_canon_sha256":"555f4e120029dc2a05a2d41afa74e67b487ece407e8432827fde4ab17d5fab2d"},"schema_version":"1.0","source":{"id":"2210.16956","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.16956","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"arxiv_version","alias_value":"2210.16956v1","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.16956","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_12","alias_value":"EQOMP7HK6KYG","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_16","alias_value":"EQOMP7HK6KYGJTGN","created_at":"2026-07-05T05:11:52Z"},{"alias_kind":"pith_short_8","alias_value":"EQOMP7HK","created_at":"2026-07-05T05:11:52Z"}],"graph_snapshots":[{"event_id":"sha256:e1680bb6f1d44d772d4c10c25efd369896af7f141a385a40aedc20a9e0d0e10c","target":"graph","created_at":"2026-07-05T05:11:52Z","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/2210.16956/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose Value Iteration Network for Reward Shaping (VIN-RS), a potential-based reward shaping mechanism using Convolutional Neural Network (CNN). The proposed VIN-RS embeds a CNN trained on computed labels using the message passing mechanism of the Hidden Markov Model. The CNN processes images or graphs of the environment to predict the shaping values. Recent work on reward shaping still has limitations towards training on a representation of the Markov Decision Process (MDP) and building an estimate of the transition matrix. The advantage of VIN-RS is to construct an effecti","authors_text":"Azzam Mourad, Ernesto Damiani, Hadi Otrok, Hani Sami, Jamal Bentahar","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-30T21:28:22Z","title":"Reward Shaping Using Convolutional Neural Network"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.16956","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":"sha256:8a3cdf1f7dfc10cd0628c6653d04744d788f1b2d9a81928cc3685ed6404c2bf2","target":"record","created_at":"2026-07-05T05:11:52Z","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":"2c623525a3637fe612e4f57025a4b01a9d9fd1b5cda602b4d1a3088896b60c57","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-30T21:28:22Z","title_canon_sha256":"555f4e120029dc2a05a2d41afa74e67b487ece407e8432827fde4ab17d5fab2d"},"schema_version":"1.0","source":{"id":"2210.16956","kind":"arxiv","version":1}},"canonical_sha256":"241cc7fceaf2b064cccd56af84c2c7e566be8a3911f22c468f6700fff5b308b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"241cc7fceaf2b064cccd56af84c2c7e566be8a3911f22c468f6700fff5b308b0","first_computed_at":"2026-07-05T05:11:52.972199Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:11:52.972199Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"XBxgrbqDxgBjpn8SM8oTTKiDK8QMhAW8JithLrBsG6oqRma9ektlgEqZ/v1a0zp6bY+S68x2PjlT0+wFYaz8Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T05:11:52.972660Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.16956","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8a3cdf1f7dfc10cd0628c6653d04744d788f1b2d9a81928cc3685ed6404c2bf2","sha256:e1680bb6f1d44d772d4c10c25efd369896af7f141a385a40aedc20a9e0d0e10c"],"state_sha256":"1275495c02a763bf0339b8b942871dc6ecec711aa3d3aaaf4d52d8e7de5c820a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"J9gG4iBmqXGiNYmBW9mqZPOoMLVO0+/QOekWw0AEK8Tv6ynGxJuui50eNBLkxaMuT8ybTUgCf43hNcg3QKpiAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T07:21:56.132116Z","bundle_sha256":"b149df8ba4d5ddf587e622b97c7de671fe4b2e07568cf384027dee759a3c52db"}}