{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QZPU63TMPPXJZQQTZZMQHDICUX","short_pith_number":"pith:QZPU63TM","canonical_record":{"source":{"id":"2607.24672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T17:14:42Z","cross_cats_sorted":[],"title_canon_sha256":"7d8fd4d399fb44c4f1a6fe4ddd1a2dd7cf1065ca457655ab6db3be2fae571069","abstract_canon_sha256":"7454325931273889a5f5f518ceb32b20b7aae69fa8c765a202d7615cae35c94c"},"schema_version":"1.0"},"canonical_sha256":"865f4f6e6c7bee9cc213ce59038d02a5e37db1ff423b7dd838263d0bbafc1470","source":{"kind":"arxiv","id":"2607.24672","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24672","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24672v1","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24672","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"pith_short_12","alias_value":"QZPU63TMPPXJ","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"pith_short_16","alias_value":"QZPU63TMPPXJZQQT","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"pith_short_8","alias_value":"QZPU63TM","created_at":"2026-07-28T02:24:21Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QZPU63TMPPXJZQQTZZMQHDICUX","target":"record","payload":{"canonical_record":{"source":{"id":"2607.24672","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T17:14:42Z","cross_cats_sorted":[],"title_canon_sha256":"7d8fd4d399fb44c4f1a6fe4ddd1a2dd7cf1065ca457655ab6db3be2fae571069","abstract_canon_sha256":"7454325931273889a5f5f518ceb32b20b7aae69fa8c765a202d7615cae35c94c"},"schema_version":"1.0"},"canonical_sha256":"865f4f6e6c7bee9cc213ce59038d02a5e37db1ff423b7dd838263d0bbafc1470","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T02:24:21.787967Z","signature_b64":"cZ/CHydXxA158wsvMBc2ueFDFOZrOyqEV8P4KReKHQvw/DORosBXmMXB++AdLNEpSGT/S8r5Z3q16lww5Cz3CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"865f4f6e6c7bee9cc213ce59038d02a5e37db1ff423b7dd838263d0bbafc1470","last_reissued_at":"2026-07-28T02:24:21.787152Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T02:24:21.787152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.24672","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":"2026-07-28T02:24:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2bwcTyT5wyax3DNF171ytnfX6Xhz7UZAS2v5vdCB2+PDPs791ipPfnJzWJ2umUrcxPANdtSopNAM2FTKkd0BAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:15:34.440601Z"},"content_sha256":"1b19af0e4298e6e37c3348d015fb39c496d866125ac62b132d47e364c59abc1b","schema_version":"1.0","event_id":"sha256:1b19af0e4298e6e37c3348d015fb39c496d866125ac62b132d47e364c59abc1b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QZPU63TMPPXJZQQTZZMQHDICUX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Explainable Reinforcement Learning via Physics-Aware Policy Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Shaker Al-Tamari, Waled Kadour","submitted_at":"2026-07-27T17:14:42Z","abstract_excerpt":"In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the black-box nature of deep neural networks. This lack of transparency poses significant challenges for regulatory compliance and human-agent trust. This paper presents an experimental study aimed at making high-performance continuous control DRL systems interpretable. A policy distillation framework is implemented using the classic Inverted Pendulum benchmark. A high-performance Twin Delayed DDPG (TD3) agent serves as an opaque, continuous teacher m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24672","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/2607.24672/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":"2026-07-28T02:24:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jpZVdD9qWK14Gv57lUUGmk/qL6uQwQ+13NDYZ/2gfpL9nO7P/FuCL3WGYqxXvNRXXPQxVG7rroKKLYfOvHDoAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:15:34.441523Z"},"content_sha256":"ba952c4046037b6716f3be5eb4ca1b8f79309e5c9f37bf28772c9b32b94f4767","schema_version":"1.0","event_id":"sha256:ba952c4046037b6716f3be5eb4ca1b8f79309e5c9f37bf28772c9b32b94f4767"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QZPU63TMPPXJZQQTZZMQHDICUX/bundle.json","state_url":"https://pith.science/pith/QZPU63TMPPXJZQQTZZMQHDICUX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QZPU63TMPPXJZQQTZZMQHDICUX/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":"2026-08-03T18:15:34Z","links":{"resolver":"https://pith.science/pith/QZPU63TMPPXJZQQTZZMQHDICUX","bundle":"https://pith.science/pith/QZPU63TMPPXJZQQTZZMQHDICUX/bundle.json","state":"https://pith.science/pith/QZPU63TMPPXJZQQTZZMQHDICUX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QZPU63TMPPXJZQQTZZMQHDICUX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QZPU63TMPPXJZQQTZZMQHDICUX","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":"7454325931273889a5f5f518ceb32b20b7aae69fa8c765a202d7615cae35c94c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T17:14:42Z","title_canon_sha256":"7d8fd4d399fb44c4f1a6fe4ddd1a2dd7cf1065ca457655ab6db3be2fae571069"},"schema_version":"1.0","source":{"id":"2607.24672","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.24672","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"arxiv_version","alias_value":"2607.24672v1","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.24672","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"pith_short_12","alias_value":"QZPU63TMPPXJ","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"pith_short_16","alias_value":"QZPU63TMPPXJZQQT","created_at":"2026-07-28T02:24:21Z"},{"alias_kind":"pith_short_8","alias_value":"QZPU63TM","created_at":"2026-07-28T02:24:21Z"}],"graph_snapshots":[{"event_id":"sha256:ba952c4046037b6716f3be5eb4ca1b8f79309e5c9f37bf28772c9b32b94f4767","target":"graph","created_at":"2026-07-28T02:24:21Z","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/2607.24672/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In safety-critical sectors such as robotics and automotive engineering, the deployment of Deep Reinforcement Learning (DRL) is often hindered by the black-box nature of deep neural networks. This lack of transparency poses significant challenges for regulatory compliance and human-agent trust. This paper presents an experimental study aimed at making high-performance continuous control DRL systems interpretable. A policy distillation framework is implemented using the classic Inverted Pendulum benchmark. A high-performance Twin Delayed DDPG (TD3) agent serves as an opaque, continuous teacher m","authors_text":"Shaker Al-Tamari, Waled Kadour","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T17:14:42Z","title":"Explainable Reinforcement Learning via Physics-Aware Policy Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.24672","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":"sha256:1b19af0e4298e6e37c3348d015fb39c496d866125ac62b132d47e364c59abc1b","target":"record","created_at":"2026-07-28T02:24:21Z","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":"7454325931273889a5f5f518ceb32b20b7aae69fa8c765a202d7615cae35c94c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-07-27T17:14:42Z","title_canon_sha256":"7d8fd4d399fb44c4f1a6fe4ddd1a2dd7cf1065ca457655ab6db3be2fae571069"},"schema_version":"1.0","source":{"id":"2607.24672","kind":"arxiv","version":1}},"canonical_sha256":"865f4f6e6c7bee9cc213ce59038d02a5e37db1ff423b7dd838263d0bbafc1470","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"865f4f6e6c7bee9cc213ce59038d02a5e37db1ff423b7dd838263d0bbafc1470","first_computed_at":"2026-07-28T02:24:21.787152Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T02:24:21.787152Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cZ/CHydXxA158wsvMBc2ueFDFOZrOyqEV8P4KReKHQvw/DORosBXmMXB++AdLNEpSGT/S8r5Z3q16lww5Cz3CQ==","signature_status":"signed_v1","signed_at":"2026-07-28T02:24:21.787967Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.24672","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1b19af0e4298e6e37c3348d015fb39c496d866125ac62b132d47e364c59abc1b","sha256:ba952c4046037b6716f3be5eb4ca1b8f79309e5c9f37bf28772c9b32b94f4767"],"state_sha256":"0600db6e117091ba53b9d18d4917d9d5b24b5960be91871485b4d5d451478ee9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JQHgvMk3xE08HAhrfW6EPeIqdWJM5IKXTPiwfVzC8J17PgDw6o1JJMqMjgjHuqgYXOUZeP7GYViO7lzvqi2yBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:15:34.447259Z","bundle_sha256":"6b795cd0d2f54b4871f675ecd1bf9f00daa6d0167c22fd8df84a23217a4a89bc"}}