{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:I2HO6GNYYXHKWICMLMNTSFRZ22","short_pith_number":"pith:I2HO6GNY","canonical_record":{"source":{"id":"2507.07848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:27:44Z","cross_cats_sorted":[],"title_canon_sha256":"3f2fc7243f25d285cc5d48b47a40ecd09341851b171d707ec97915d5cbbb1333","abstract_canon_sha256":"dc7e0065590fe1e59dc8b9d3d46180f04741942e6b1eccfdf5c6e3012155c75d"},"schema_version":"1.0"},"canonical_sha256":"468eef19b8c5ceab204c5b1b391639d688315fa0d8c2a6b665d220fa29b7ccd4","source":{"kind":"arxiv","id":"2507.07848","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07848","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07848v2","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07848","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"I2HO6GNYYXHK","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"I2HO6GNYYXHKWICM","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"I2HO6GNY","created_at":"2026-07-05T11:44:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:I2HO6GNYYXHKWICMLMNTSFRZ22","target":"record","payload":{"canonical_record":{"source":{"id":"2507.07848","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:27:44Z","cross_cats_sorted":[],"title_canon_sha256":"3f2fc7243f25d285cc5d48b47a40ecd09341851b171d707ec97915d5cbbb1333","abstract_canon_sha256":"dc7e0065590fe1e59dc8b9d3d46180f04741942e6b1eccfdf5c6e3012155c75d"},"schema_version":"1.0"},"canonical_sha256":"468eef19b8c5ceab204c5b1b391639d688315fa0d8c2a6b665d220fa29b7ccd4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:44:51.033229Z","signature_b64":"vNEjXGIRYW0lOE6+6+/a0qfV5lZUqfIlLKYB+Lf75E3t/7fU81lc+l4UAnGvHvx5by/2BwbZbiIt53OZkAK8Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"468eef19b8c5ceab204c5b1b391639d688315fa0d8c2a6b665d220fa29b7ccd4","last_reissued_at":"2026-07-05T11:44:51.032686Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:44:51.032686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.07848","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:44:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vhqbFuxwuF4ByOzziVhxe3m2SNS/yP42k7Pk+Wev29B1BeWtRrf9VxKeS3+TP1gd4LDRPn0IL+TTFBRNqdXWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:06:45.388024Z"},"content_sha256":"e65cd4a3129d6e87a44b0c3b1f9c85af59be77eafae97714c712ea1539fe0d0e","schema_version":"1.0","event_id":"sha256:e65cd4a3129d6e87a44b0c3b1f9c85af59be77eafae97714c712ea1539fe0d0e"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:I2HO6GNYYXHKWICMLMNTSFRZ22","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\"So, Tell Me About Your Policy...\": Distillation of interpretable policies from Deep Reinforcement Learning agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Giovanni Dispoto, Marcello Restelli, Paolo Bonetti","submitted_at":"2025-07-10T15:27:44Z","abstract_excerpt":"Recent advances in Reinforcement Learning (RL) largely benefit from the inclusion of Deep Neural Networks, boosting the number of novel approaches proposed in the field of Deep Reinforcement Learning (DRL). These techniques demonstrate the ability to tackle complex games such as Atari, Go, and other real-world applications, including financial trading. Nevertheless, a significant challenge emerges from the lack of interpretability, particularly when attempting to comprehend the underlying patterns learned, the relative importance of the state features, and how they are integrated to generate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07848","kind":"arxiv","version":2},"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/2507.07848/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":"2026-07-05T11:44:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Nye7qA1TQtYOT2mLkj4xrot2tIjglw5tGykJez3OJauXK73FMSi7WFYeRO3VwjuMnLIaI7NEVGioWXfYrzCAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T05:06:45.388522Z"},"content_sha256":"54f3d6b5381cfcabd97cb6ba003c019ef2513d3652a160d50e862a5a1320ac2e","schema_version":"1.0","event_id":"sha256:54f3d6b5381cfcabd97cb6ba003c019ef2513d3652a160d50e862a5a1320ac2e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/bundle.json","state_url":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/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":"2026-08-07T05:06:45Z","links":{"resolver":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22","bundle":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/bundle.json","state":"https://pith.science/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/state.json","well_known_bundle":"https://pith.science/.well-known/pith/I2HO6GNYYXHKWICMLMNTSFRZ22/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:I2HO6GNYYXHKWICMLMNTSFRZ22","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":"dc7e0065590fe1e59dc8b9d3d46180f04741942e6b1eccfdf5c6e3012155c75d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:27:44Z","title_canon_sha256":"3f2fc7243f25d285cc5d48b47a40ecd09341851b171d707ec97915d5cbbb1333"},"schema_version":"1.0","source":{"id":"2507.07848","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07848","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07848v2","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07848","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"pith_short_12","alias_value":"I2HO6GNYYXHK","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"pith_short_16","alias_value":"I2HO6GNYYXHKWICM","created_at":"2026-07-05T11:44:51Z"},{"alias_kind":"pith_short_8","alias_value":"I2HO6GNY","created_at":"2026-07-05T11:44:51Z"}],"graph_snapshots":[{"event_id":"sha256:54f3d6b5381cfcabd97cb6ba003c019ef2513d3652a160d50e862a5a1320ac2e","target":"graph","created_at":"2026-07-05T11:44:51Z","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/2507.07848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in Reinforcement Learning (RL) largely benefit from the inclusion of Deep Neural Networks, boosting the number of novel approaches proposed in the field of Deep Reinforcement Learning (DRL). These techniques demonstrate the ability to tackle complex games such as Atari, Go, and other real-world applications, including financial trading. Nevertheless, a significant challenge emerges from the lack of interpretability, particularly when attempting to comprehend the underlying patterns learned, the relative importance of the state features, and how they are integrated to generate t","authors_text":"Giovanni Dispoto, Marcello Restelli, Paolo Bonetti","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:27:44Z","title":"\"So, Tell Me About Your Policy...\": Distillation of interpretable policies from Deep Reinforcement Learning agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07848","kind":"arxiv","version":2},"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:e65cd4a3129d6e87a44b0c3b1f9c85af59be77eafae97714c712ea1539fe0d0e","target":"record","created_at":"2026-07-05T11:44:51Z","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":"dc7e0065590fe1e59dc8b9d3d46180f04741942e6b1eccfdf5c6e3012155c75d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:27:44Z","title_canon_sha256":"3f2fc7243f25d285cc5d48b47a40ecd09341851b171d707ec97915d5cbbb1333"},"schema_version":"1.0","source":{"id":"2507.07848","kind":"arxiv","version":2}},"canonical_sha256":"468eef19b8c5ceab204c5b1b391639d688315fa0d8c2a6b665d220fa29b7ccd4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"468eef19b8c5ceab204c5b1b391639d688315fa0d8c2a6b665d220fa29b7ccd4","first_computed_at":"2026-07-05T11:44:51.032686Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:44:51.032686Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vNEjXGIRYW0lOE6+6+/a0qfV5lZUqfIlLKYB+Lf75E3t/7fU81lc+l4UAnGvHvx5by/2BwbZbiIt53OZkAK8Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:44:51.033229Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07848","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e65cd4a3129d6e87a44b0c3b1f9c85af59be77eafae97714c712ea1539fe0d0e","sha256:54f3d6b5381cfcabd97cb6ba003c019ef2513d3652a160d50e862a5a1320ac2e"],"state_sha256":"5ed2be43dafaf6d43a9a5b26dc83d9a8ecfd9b92463eebc4eb6a29f188e47e71"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Rt50uSfbYaALAwQ7Myh0PBGh3hdupZpZx92bZzFla0IQztTJ1VgjTJb5STLZXjx8zny2fEz60KgabZ9UHMV2BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T05:06:45.391948Z","bundle_sha256":"0815eb18b459bfc983856f2f61cce0e9dc04c809c4eb1036946542c9a126dab6"}}