{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:XH5PU5CNJGUZVN5SGIXORRSM2I","short_pith_number":"pith:XH5PU5CN","canonical_record":{"source":{"id":"1902.09996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-26T15:26:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4be6db0902984f47d00af60c7d299b079588260c8c3f6a42f2790fd25a607a02","abstract_canon_sha256":"2b8f3f6afa4dfd04d893777b4a82d03bca75741665dde1a69f7737fac70a865d"},"schema_version":"1.0"},"canonical_sha256":"b9fafa744d49a99ab7b2322ee8c64cd205254ee3d07297a44c6b60c4e2f83c7a","source":{"kind":"arxiv","id":"1902.09996","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09996","created_at":"2026-05-17T23:52:34Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09996v1","created_at":"2026-05-17T23:52:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09996","created_at":"2026-05-17T23:52:34Z"},{"alias_kind":"pith_short_12","alias_value":"XH5PU5CNJGUZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XH5PU5CNJGUZVN5S","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XH5PU5CN","created_at":"2026-05-18T12:33:33Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:XH5PU5CNJGUZVN5SGIXORRSM2I","target":"record","payload":{"canonical_record":{"source":{"id":"1902.09996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-26T15:26:10Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"4be6db0902984f47d00af60c7d299b079588260c8c3f6a42f2790fd25a607a02","abstract_canon_sha256":"2b8f3f6afa4dfd04d893777b4a82d03bca75741665dde1a69f7737fac70a865d"},"schema_version":"1.0"},"canonical_sha256":"b9fafa744d49a99ab7b2322ee8c64cd205254ee3d07297a44c6b60c4e2f83c7a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:52:34.894870Z","signature_b64":"r5MpispJHBZvDmHrxsP/mDvSVCr/rgD1sPW5FZkjRHbp3NY1PPVZ4G/fL+SEdhzzz7q5Fd6pGpskjEmPbSrvCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b9fafa744d49a99ab7b2322ee8c64cd205254ee3d07297a44c6b60c4e2f83c7a","last_reissued_at":"2026-05-17T23:52:34.894496Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:52:34.894496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1902.09996","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":"2026-05-17T23:52:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AysTdtKLS5VsMOb8LLb2Yb8IhdrnLTgjKZuwTrQJn/SMAPUPoLJ34HGgbiQ6pS/tEZx+OmbgqDwhqxT9gbB8CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T13:12:03.921779Z"},"content_sha256":"dd2c4a2b698d492f400d72de0c8bc6f852b7e779a8d541aba4112b597cc3e82d","schema_version":"1.0","event_id":"sha256:dd2c4a2b698d492f400d72de0c8bc6f852b7e779a8d541aba4112b597cc3e82d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:XH5PU5CNJGUZVN5SGIXORRSM2I","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Termination Critic","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.AI","authors_text":"Anna Harutyunyan, Diana Borsa, Doina Precup, Nicolas Heess, Remi Munos, Will Dabney","submitted_at":"2019-02-26T15:26:10Z","abstract_excerpt":"In this work, we consider the problem of autonomously discovering behavioral abstractions, or options, for reinforcement learning agents. We propose an algorithm that focuses on the termination condition, as opposed to -- as is common -- the policy. The termination condition is usually trained to optimize a control objective: an option ought to terminate if another has better value. We offer a different, information-theoretic perspective, and propose that terminations should focus instead on the compressibility of the option's encoding -- arguably a key reason for using abstractions. To achiev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09996","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":""},"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":"2026-05-17T23:52:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mebY5AoTG//5z/qPw/qudbvDO8Nh11Xz6ej+TLxYjIdRgmPcWXKPc7txJgSdtwSq4cn/wlXrt6s+uG2T0BrEBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-22T13:12:03.922456Z"},"content_sha256":"3debd3eeae5b656e87e4436eef20025108e1237efede4fd372d0473c5ec139d5","schema_version":"1.0","event_id":"sha256:3debd3eeae5b656e87e4436eef20025108e1237efede4fd372d0473c5ec139d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/XH5PU5CNJGUZVN5SGIXORRSM2I/bundle.json","state_url":"https://pith.science/pith/XH5PU5CNJGUZVN5SGIXORRSM2I/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/XH5PU5CNJGUZVN5SGIXORRSM2I/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":"2026-05-22T13:12:03Z","links":{"resolver":"https://pith.science/pith/XH5PU5CNJGUZVN5SGIXORRSM2I","bundle":"https://pith.science/pith/XH5PU5CNJGUZVN5SGIXORRSM2I/bundle.json","state":"https://pith.science/pith/XH5PU5CNJGUZVN5SGIXORRSM2I/state.json","well_known_bundle":"https://pith.science/.well-known/pith/XH5PU5CNJGUZVN5SGIXORRSM2I/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:XH5PU5CNJGUZVN5SGIXORRSM2I","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":"2b8f3f6afa4dfd04d893777b4a82d03bca75741665dde1a69f7737fac70a865d","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-26T15:26:10Z","title_canon_sha256":"4be6db0902984f47d00af60c7d299b079588260c8c3f6a42f2790fd25a607a02"},"schema_version":"1.0","source":{"id":"1902.09996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1902.09996","created_at":"2026-05-17T23:52:34Z"},{"alias_kind":"arxiv_version","alias_value":"1902.09996v1","created_at":"2026-05-17T23:52:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1902.09996","created_at":"2026-05-17T23:52:34Z"},{"alias_kind":"pith_short_12","alias_value":"XH5PU5CNJGUZ","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_16","alias_value":"XH5PU5CNJGUZVN5S","created_at":"2026-05-18T12:33:33Z"},{"alias_kind":"pith_short_8","alias_value":"XH5PU5CN","created_at":"2026-05-18T12:33:33Z"}],"graph_snapshots":[{"event_id":"sha256:3debd3eeae5b656e87e4436eef20025108e1237efede4fd372d0473c5ec139d5","target":"graph","created_at":"2026-05-17T23:52:34Z","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"},"paper":{"abstract_excerpt":"In this work, we consider the problem of autonomously discovering behavioral abstractions, or options, for reinforcement learning agents. We propose an algorithm that focuses on the termination condition, as opposed to -- as is common -- the policy. The termination condition is usually trained to optimize a control objective: an option ought to terminate if another has better value. We offer a different, information-theoretic perspective, and propose that terminations should focus instead on the compressibility of the option's encoding -- arguably a key reason for using abstractions. To achiev","authors_text":"Anna Harutyunyan, Diana Borsa, Doina Precup, Nicolas Heess, Remi Munos, Will Dabney","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-26T15:26:10Z","title":"The Termination Critic"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1902.09996","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:dd2c4a2b698d492f400d72de0c8bc6f852b7e779a8d541aba4112b597cc3e82d","target":"record","created_at":"2026-05-17T23:52:34Z","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":"2b8f3f6afa4dfd04d893777b4a82d03bca75741665dde1a69f7737fac70a865d","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2019-02-26T15:26:10Z","title_canon_sha256":"4be6db0902984f47d00af60c7d299b079588260c8c3f6a42f2790fd25a607a02"},"schema_version":"1.0","source":{"id":"1902.09996","kind":"arxiv","version":1}},"canonical_sha256":"b9fafa744d49a99ab7b2322ee8c64cd205254ee3d07297a44c6b60c4e2f83c7a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b9fafa744d49a99ab7b2322ee8c64cd205254ee3d07297a44c6b60c4e2f83c7a","first_computed_at":"2026-05-17T23:52:34.894496Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:52:34.894496Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"r5MpispJHBZvDmHrxsP/mDvSVCr/rgD1sPW5FZkjRHbp3NY1PPVZ4G/fL+SEdhzzz7q5Fd6pGpskjEmPbSrvCw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:52:34.894870Z","signed_message":"canonical_sha256_bytes"},"source_id":"1902.09996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd2c4a2b698d492f400d72de0c8bc6f852b7e779a8d541aba4112b597cc3e82d","sha256:3debd3eeae5b656e87e4436eef20025108e1237efede4fd372d0473c5ec139d5"],"state_sha256":"fba2cfa26965d80af39adda40a72269e194a6b05cc6669271dd25067832fe132"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0IZw2HuwrQAo6aBIg0pSCvbzz/0sQB0aS0yS6O5RC3Yz1I5WtAjNfxiEPfuGJbk2n8DIh5ntb9LSzBIUbNTIBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-22T13:12:03.926121Z","bundle_sha256":"fdb048d345952ed87b37a60d19f4d7cb8e2e560fa1a5d9f45d9b08f34555f44d"}}