{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:R3E62LRSRETUO44BDFIF2IGJEZ","short_pith_number":"pith:R3E62LRS","canonical_record":{"source":{"id":"2006.07217","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:19:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"82f959c29832b00083b8e8b0156b055bc188c43a2f5165fe5afdcf38ec03ca35","abstract_canon_sha256":"0e78302da6d051ed73fa15066cf0ffc81d8346797208d1ce7e123d45659c2329"},"schema_version":"1.0"},"canonical_sha256":"8ec9ed2e32892747738119505d20c92652d0617d4f2ed9c0d8cf89b2b4a622cf","source":{"kind":"arxiv","id":"2006.07217","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07217","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07217v3","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07217","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_12","alias_value":"R3E62LRSRETU","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_16","alias_value":"R3E62LRSRETUO44B","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_8","alias_value":"R3E62LRS","created_at":"2026-07-05T01:51:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:R3E62LRSRETUO44BDFIF2IGJEZ","target":"record","payload":{"canonical_record":{"source":{"id":"2006.07217","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:19:46Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"82f959c29832b00083b8e8b0156b055bc188c43a2f5165fe5afdcf38ec03ca35","abstract_canon_sha256":"0e78302da6d051ed73fa15066cf0ffc81d8346797208d1ce7e123d45659c2329"},"schema_version":"1.0"},"canonical_sha256":"8ec9ed2e32892747738119505d20c92652d0617d4f2ed9c0d8cf89b2b4a622cf","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:51:42.583876Z","signature_b64":"gy7bnJ3H6Nr8SoqMg0rXFa8bYLWtHEESRw9HiTPMTcPrezs9LuKaWFp2fvlZrK+nxskoUXBduuEPAywSp2SRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ec9ed2e32892747738119505d20c92652d0617d4f2ed9c0d8cf89b2b4a622cf","last_reissued_at":"2026-07-05T01:51:42.583377Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:51:42.583377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2006.07217","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":"2026-07-05T01:51:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G4nBIU+aj4TkpJU2TnPknRhp2NO5RBujbEp+090lJGCIQGZyC3GrDF3kmWyDZXhCfMjOvM81UsgRNOOJTj3lAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:16:26.940001Z"},"content_sha256":"213b6573c9026d4c81c1b054a26599a2322cfa4d3f0cdad5fd15585588381da1","schema_version":"1.0","event_id":"sha256:213b6573c9026d4c81c1b054a26599a2322cfa4d3f0cdad5fd15585588381da1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:R3E62LRSRETUO44BDFIF2IGJEZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Deep Reinforcement and InfoMax Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Bogdan Mazoure, Philip Bachman, R Devon Hjelm, Remi Tachet des Combes, Thang Doan","submitted_at":"2020-06-12T14:19:46Z","abstract_excerpt":"We begin with the hypothesis that a model-free agent whose representations are predictive of properties of future states (beyond expected rewards) will be more capable of solving and adapting to new RL problems. To test that hypothesis, we introduce an objective based on Deep InfoMax (DIM) which trains the agent to predict the future by maximizing the mutual information between its internal representation of successive timesteps. We test our approach in several synthetic settings, where it successfully learns representations that are predictive of the future. Finally, we augment C51, a strong "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07217","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/2006.07217/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":"2026-07-05T01:51:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6ooaiFIASfFjQTOwIjwOPDHmxQUjQ9DU6NNtziMSD+tgjVwK3AFU9c2ORyZMj28g9wDafK2+Ce6PwWuli+KIAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:16:26.940629Z"},"content_sha256":"a1272aa0f6bb9ff2566cb90dc793d0dab05281b3ab6c13e46fddb61433f7b6f8","schema_version":"1.0","event_id":"sha256:a1272aa0f6bb9ff2566cb90dc793d0dab05281b3ab6c13e46fddb61433f7b6f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R3E62LRSRETUO44BDFIF2IGJEZ/bundle.json","state_url":"https://pith.science/pith/R3E62LRSRETUO44BDFIF2IGJEZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R3E62LRSRETUO44BDFIF2IGJEZ/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":"2026-08-06T14:16:26Z","links":{"resolver":"https://pith.science/pith/R3E62LRSRETUO44BDFIF2IGJEZ","bundle":"https://pith.science/pith/R3E62LRSRETUO44BDFIF2IGJEZ/bundle.json","state":"https://pith.science/pith/R3E62LRSRETUO44BDFIF2IGJEZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R3E62LRSRETUO44BDFIF2IGJEZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:R3E62LRSRETUO44BDFIF2IGJEZ","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":"0e78302da6d051ed73fa15066cf0ffc81d8346797208d1ce7e123d45659c2329","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:19:46Z","title_canon_sha256":"82f959c29832b00083b8e8b0156b055bc188c43a2f5165fe5afdcf38ec03ca35"},"schema_version":"1.0","source":{"id":"2006.07217","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.07217","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"arxiv_version","alias_value":"2006.07217v3","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.07217","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_12","alias_value":"R3E62LRSRETU","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_16","alias_value":"R3E62LRSRETUO44B","created_at":"2026-07-05T01:51:42Z"},{"alias_kind":"pith_short_8","alias_value":"R3E62LRS","created_at":"2026-07-05T01:51:42Z"}],"graph_snapshots":[{"event_id":"sha256:a1272aa0f6bb9ff2566cb90dc793d0dab05281b3ab6c13e46fddb61433f7b6f8","target":"graph","created_at":"2026-07-05T01:51:42Z","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/2006.07217/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We begin with the hypothesis that a model-free agent whose representations are predictive of properties of future states (beyond expected rewards) will be more capable of solving and adapting to new RL problems. To test that hypothesis, we introduce an objective based on Deep InfoMax (DIM) which trains the agent to predict the future by maximizing the mutual information between its internal representation of successive timesteps. We test our approach in several synthetic settings, where it successfully learns representations that are predictive of the future. Finally, we augment C51, a strong ","authors_text":"Bogdan Mazoure, Philip Bachman, R Devon Hjelm, Remi Tachet des Combes, Thang Doan","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:19:46Z","title":"Deep Reinforcement and InfoMax Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.07217","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":"sha256:213b6573c9026d4c81c1b054a26599a2322cfa4d3f0cdad5fd15585588381da1","target":"record","created_at":"2026-07-05T01:51:42Z","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":"0e78302da6d051ed73fa15066cf0ffc81d8346797208d1ce7e123d45659c2329","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-06-12T14:19:46Z","title_canon_sha256":"82f959c29832b00083b8e8b0156b055bc188c43a2f5165fe5afdcf38ec03ca35"},"schema_version":"1.0","source":{"id":"2006.07217","kind":"arxiv","version":3}},"canonical_sha256":"8ec9ed2e32892747738119505d20c92652d0617d4f2ed9c0d8cf89b2b4a622cf","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ec9ed2e32892747738119505d20c92652d0617d4f2ed9c0d8cf89b2b4a622cf","first_computed_at":"2026-07-05T01:51:42.583377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:51:42.583377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gy7bnJ3H6Nr8SoqMg0rXFa8bYLWtHEESRw9HiTPMTcPrezs9LuKaWFp2fvlZrK+nxskoUXBduuEPAywSp2SRBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:51:42.583876Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.07217","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:213b6573c9026d4c81c1b054a26599a2322cfa4d3f0cdad5fd15585588381da1","sha256:a1272aa0f6bb9ff2566cb90dc793d0dab05281b3ab6c13e46fddb61433f7b6f8"],"state_sha256":"f134129a3f158a6fbba8abf384cd3efe0015f6ddb8e765cf2f439098bd9e2e36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CrgbTjcD/v9JOBLvSDVdcHNQWOoNyg7l61oYfWdH4xoJhyTndtEHFUplb806cSF50It9F3DXafdW8eYQYm8ZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:16:26.944027Z","bundle_sha256":"0ac3252a2e00e7918f6f062e9429d8a437784d9911fc4bdc29f83d33d522105c"}}