{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LAXPVFJXSXOLUFJY7ZARK5O7QD","short_pith_number":"pith:LAXPVFJX","canonical_record":{"source":{"id":"2303.02135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T18:29:47Z","cross_cats_sorted":["cs.AI","cs.LO","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"25a9e084a8f0b3e6cf5cf020b234b7a7a3fb2db2631a500072efb4e8bbe9105f","abstract_canon_sha256":"b5c88754836afbfc7ca4ba8bec3d74efb6e209b00cdf58a216c64b61c718af68"},"schema_version":"1.0"},"canonical_sha256":"582efa953795dcba1538fe411575df80fe372b2d22d6949a68f8767f76cbec02","source":{"kind":"arxiv","id":"2303.02135","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02135","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02135v1","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02135","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"LAXPVFJXSXOL","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"LAXPVFJXSXOLUFJY","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"LAXPVFJX","created_at":"2026-07-05T05:47:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LAXPVFJXSXOLUFJY7ZARK5O7QD","target":"record","payload":{"canonical_record":{"source":{"id":"2303.02135","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T18:29:47Z","cross_cats_sorted":["cs.AI","cs.LO","cs.RO","cs.SY","eess.SY"],"title_canon_sha256":"25a9e084a8f0b3e6cf5cf020b234b7a7a3fb2db2631a500072efb4e8bbe9105f","abstract_canon_sha256":"b5c88754836afbfc7ca4ba8bec3d74efb6e209b00cdf58a216c64b61c718af68"},"schema_version":"1.0"},"canonical_sha256":"582efa953795dcba1538fe411575df80fe372b2d22d6949a68f8767f76cbec02","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:47:52.954671Z","signature_b64":"TX8q0PQBqhnD67fRYfcf2ubk8lkF21UA85/Hlvf7q54QzoYCGT4IeYcYcOuUQJQw0S5ksZQcQssopR4y68sRAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"582efa953795dcba1538fe411575df80fe372b2d22d6949a68f8767f76cbec02","last_reissued_at":"2026-07-05T05:47:52.954173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:47:52.954173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2303.02135","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":"2026-07-05T05:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"79RNs/YhB1V4RBa5tzYf3VMGQAIOU2DfwxEb8C2+dXU9m94dDAL7pkNt2ZWKbYiPW7wBLZ7X5z5ZEcv8oYj7AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:01:47.696657Z"},"content_sha256":"b4c5ee1ec8a0b6a5488d60a37fc234f0cef474f269480926a064455ef68a4fb1","schema_version":"1.0","event_id":"sha256:b4c5ee1ec8a0b6a5488d60a37fc234f0cef474f269480926a064455ef68a4fb1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LAXPVFJXSXOLUFJY7ZARK5O7QD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LO","cs.RO","cs.SY","eess.SY"],"primary_cat":"cs.LG","authors_text":"Abhinav Verma, Cameron Voloshin, Yisong Yue","submitted_at":"2023-03-03T18:29:47Z","abstract_excerpt":"Linear temporal logic (LTL) offers a simplified way of specifying tasks for policy optimization that may otherwise be difficult to describe with scalar reward functions. However, the standard RL framework can be too myopic to find maximally LTL satisfying policies. This paper makes two contributions. First, we develop a new value-function based proxy, using a technique we call eventual discounting, under which one can find policies that satisfy the LTL specification with highest achievable probability. Second, we develop a new experience replay method for generating off-policy data from on-pol"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02135","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/2303.02135/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":"2026-07-05T05:47:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e3fddhV89kaFJqqWntGFdYZJzj+v2ZIti5ufbTJp+Q2QFncQyjPSDfsyfJ+cvkf2rim5JUxGhXYEShtbOY+NBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:01:47.697578Z"},"content_sha256":"2ecf82b627dea208115a994f67352ba526b84d38db0c37efbd58389762d64dc9","schema_version":"1.0","event_id":"sha256:2ecf82b627dea208115a994f67352ba526b84d38db0c37efbd58389762d64dc9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LAXPVFJXSXOLUFJY7ZARK5O7QD/bundle.json","state_url":"https://pith.science/pith/LAXPVFJXSXOLUFJY7ZARK5O7QD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LAXPVFJXSXOLUFJY7ZARK5O7QD/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":"2026-08-18T11:01:47Z","links":{"resolver":"https://pith.science/pith/LAXPVFJXSXOLUFJY7ZARK5O7QD","bundle":"https://pith.science/pith/LAXPVFJXSXOLUFJY7ZARK5O7QD/bundle.json","state":"https://pith.science/pith/LAXPVFJXSXOLUFJY7ZARK5O7QD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LAXPVFJXSXOLUFJY7ZARK5O7QD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LAXPVFJXSXOLUFJY7ZARK5O7QD","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":"b5c88754836afbfc7ca4ba8bec3d74efb6e209b00cdf58a216c64b61c718af68","cross_cats_sorted":["cs.AI","cs.LO","cs.RO","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T18:29:47Z","title_canon_sha256":"25a9e084a8f0b3e6cf5cf020b234b7a7a3fb2db2631a500072efb4e8bbe9105f"},"schema_version":"1.0","source":{"id":"2303.02135","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.02135","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"arxiv_version","alias_value":"2303.02135v1","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.02135","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"pith_short_12","alias_value":"LAXPVFJXSXOL","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"pith_short_16","alias_value":"LAXPVFJXSXOLUFJY","created_at":"2026-07-05T05:47:52Z"},{"alias_kind":"pith_short_8","alias_value":"LAXPVFJX","created_at":"2026-07-05T05:47:52Z"}],"graph_snapshots":[{"event_id":"sha256:2ecf82b627dea208115a994f67352ba526b84d38db0c37efbd58389762d64dc9","target":"graph","created_at":"2026-07-05T05:47:52Z","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/2303.02135/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Linear temporal logic (LTL) offers a simplified way of specifying tasks for policy optimization that may otherwise be difficult to describe with scalar reward functions. However, the standard RL framework can be too myopic to find maximally LTL satisfying policies. This paper makes two contributions. First, we develop a new value-function based proxy, using a technique we call eventual discounting, under which one can find policies that satisfy the LTL specification with highest achievable probability. Second, we develop a new experience replay method for generating off-policy data from on-pol","authors_text":"Abhinav Verma, Cameron Voloshin, Yisong Yue","cross_cats":["cs.AI","cs.LO","cs.RO","cs.SY","eess.SY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T18:29:47Z","title":"Eventual Discounting Temporal Logic Counterfactual Experience Replay"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.02135","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:b4c5ee1ec8a0b6a5488d60a37fc234f0cef474f269480926a064455ef68a4fb1","target":"record","created_at":"2026-07-05T05:47:52Z","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":"b5c88754836afbfc7ca4ba8bec3d74efb6e209b00cdf58a216c64b61c718af68","cross_cats_sorted":["cs.AI","cs.LO","cs.RO","cs.SY","eess.SY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-03-03T18:29:47Z","title_canon_sha256":"25a9e084a8f0b3e6cf5cf020b234b7a7a3fb2db2631a500072efb4e8bbe9105f"},"schema_version":"1.0","source":{"id":"2303.02135","kind":"arxiv","version":1}},"canonical_sha256":"582efa953795dcba1538fe411575df80fe372b2d22d6949a68f8767f76cbec02","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"582efa953795dcba1538fe411575df80fe372b2d22d6949a68f8767f76cbec02","first_computed_at":"2026-07-05T05:47:52.954173Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:47:52.954173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TX8q0PQBqhnD67fRYfcf2ubk8lkF21UA85/Hlvf7q54QzoYCGT4IeYcYcOuUQJQw0S5ksZQcQssopR4y68sRAA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:47:52.954671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.02135","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b4c5ee1ec8a0b6a5488d60a37fc234f0cef474f269480926a064455ef68a4fb1","sha256:2ecf82b627dea208115a994f67352ba526b84d38db0c37efbd58389762d64dc9"],"state_sha256":"72f57365a95a542ec2aa3c7dcd30d71dd1d175d9541aade2b96c34aa88aa624d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XDG7yDdk0XpyJWA6mCeK9kl8xeDpCqrjWROOa/nG7cOGKcbEwRP+ox4MglTA5m4bD2Pu3OZns7igVU0zHc2SCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:01:47.765476Z","bundle_sha256":"bf3c3b13ea027287cfb661acc5d9c40f222c7fbe6d8aa5a58de251f056c7d1b3"}}