{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:3XG3XTBRWCWS3ZEFPEX7R5QPFI","short_pith_number":"pith:3XG3XTBR","canonical_record":{"source":{"id":"2406.18033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T03:02:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1085cdf768fe38ccb71ff45e32c18fe53a3d12ce6f346b230088f23f2f52e0f2","abstract_canon_sha256":"7ed33647d0c24c6eb7904645df6d358e6887f34a5ca4cd77e87f7a319eee7e14"},"schema_version":"1.0"},"canonical_sha256":"ddcdbbcc31b0ad2de485792ff8f60f2a2d1430e0379899319a66aa99cb800b9b","source":{"kind":"arxiv","id":"2406.18033","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18033","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18033v1","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18033","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"pith_short_12","alias_value":"3XG3XTBRWCWS","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"pith_short_16","alias_value":"3XG3XTBRWCWS3ZEF","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"pith_short_8","alias_value":"3XG3XTBR","created_at":"2026-07-05T08:36:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:3XG3XTBRWCWS3ZEFPEX7R5QPFI","target":"record","payload":{"canonical_record":{"source":{"id":"2406.18033","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T03:02:22Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"1085cdf768fe38ccb71ff45e32c18fe53a3d12ce6f346b230088f23f2f52e0f2","abstract_canon_sha256":"7ed33647d0c24c6eb7904645df6d358e6887f34a5ca4cd77e87f7a319eee7e14"},"schema_version":"1.0"},"canonical_sha256":"ddcdbbcc31b0ad2de485792ff8f60f2a2d1430e0379899319a66aa99cb800b9b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:36:53.969771Z","signature_b64":"bN7ezu/pRFjYDvN3m4bGJYAAsQcPUO7aYVvU9TFnCfffGDuprteueMpqt7uqyU8X5mg29YM5r6nFW2hCqvYKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ddcdbbcc31b0ad2de485792ff8f60f2a2d1430e0379899319a66aa99cb800b9b","last_reissued_at":"2026-07-05T08:36:53.969386Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:36:53.969386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.18033","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":"2026-07-05T08:36:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8geyJuQ3MPA9czehaBvcTq2S5+TBV2Yw4Xec4EpXSQu0jifPXnP2uq3cSyvcYHYozBLEn0CXExujetGtzk9+Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:37:51.418541Z"},"content_sha256":"ab00e3119b3b9232042a7d6dc7aabe9f7dcf7ffc3ca02d5365b4c196e4b53182","schema_version":"1.0","event_id":"sha256:ab00e3119b3b9232042a7d6dc7aabe9f7dcf7ffc3ca02d5365b4c196e4b53182"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:3XG3XTBRWCWS3ZEFPEX7R5QPFI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Boosting Soft Q-Learning by Bounding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Jacob Adamczyk, Rahul V. Kulkarni, Stas Tiomkin, Volodymyr Makarenko","submitted_at":"2024-06-26T03:02:22Z","abstract_excerpt":"An agent's ability to leverage past experience is critical for efficiently solving new tasks. Prior work has focused on using value function estimates to obtain zero-shot approximations for solutions to a new task. In soft Q-learning, we show how any value function estimate can also be used to derive double-sided bounds on the optimal value function. The derived bounds lead to new approaches for boosting training performance which we validate experimentally. Notably, we find that the proposed framework suggests an alternative method for updating the Q-function, leading to boosted performance."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18033","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/2406.18033/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":"2026-07-05T08:36:53Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mTL+NHuRYtbH2NstQGoSOZIFdH3iGevEdsxWCpk3gj93XV1ta/HHdjhfu5g8Q8yiZOpM8AXnwBEJbxjw6J6gBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:37:51.419071Z"},"content_sha256":"036dd7151871904a0d28435e592b887c042c6b89675acc521fe12cf3d50497f8","schema_version":"1.0","event_id":"sha256:036dd7151871904a0d28435e592b887c042c6b89675acc521fe12cf3d50497f8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3XG3XTBRWCWS3ZEFPEX7R5QPFI/bundle.json","state_url":"https://pith.science/pith/3XG3XTBRWCWS3ZEFPEX7R5QPFI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3XG3XTBRWCWS3ZEFPEX7R5QPFI/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":"2026-08-08T03:37:51Z","links":{"resolver":"https://pith.science/pith/3XG3XTBRWCWS3ZEFPEX7R5QPFI","bundle":"https://pith.science/pith/3XG3XTBRWCWS3ZEFPEX7R5QPFI/bundle.json","state":"https://pith.science/pith/3XG3XTBRWCWS3ZEFPEX7R5QPFI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3XG3XTBRWCWS3ZEFPEX7R5QPFI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3XG3XTBRWCWS3ZEFPEX7R5QPFI","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":"7ed33647d0c24c6eb7904645df6d358e6887f34a5ca4cd77e87f7a319eee7e14","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T03:02:22Z","title_canon_sha256":"1085cdf768fe38ccb71ff45e32c18fe53a3d12ce6f346b230088f23f2f52e0f2"},"schema_version":"1.0","source":{"id":"2406.18033","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.18033","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"arxiv_version","alias_value":"2406.18033v1","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.18033","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"pith_short_12","alias_value":"3XG3XTBRWCWS","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"pith_short_16","alias_value":"3XG3XTBRWCWS3ZEF","created_at":"2026-07-05T08:36:53Z"},{"alias_kind":"pith_short_8","alias_value":"3XG3XTBR","created_at":"2026-07-05T08:36:53Z"}],"graph_snapshots":[{"event_id":"sha256:036dd7151871904a0d28435e592b887c042c6b89675acc521fe12cf3d50497f8","target":"graph","created_at":"2026-07-05T08:36:53Z","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/2406.18033/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"An agent's ability to leverage past experience is critical for efficiently solving new tasks. Prior work has focused on using value function estimates to obtain zero-shot approximations for solutions to a new task. In soft Q-learning, we show how any value function estimate can also be used to derive double-sided bounds on the optimal value function. The derived bounds lead to new approaches for boosting training performance which we validate experimentally. Notably, we find that the proposed framework suggests an alternative method for updating the Q-function, leading to boosted performance.","authors_text":"Jacob Adamczyk, Rahul V. Kulkarni, Stas Tiomkin, Volodymyr Makarenko","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T03:02:22Z","title":"Boosting Soft Q-Learning by Bounding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.18033","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:ab00e3119b3b9232042a7d6dc7aabe9f7dcf7ffc3ca02d5365b4c196e4b53182","target":"record","created_at":"2026-07-05T08:36:53Z","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":"7ed33647d0c24c6eb7904645df6d358e6887f34a5ca4cd77e87f7a319eee7e14","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T03:02:22Z","title_canon_sha256":"1085cdf768fe38ccb71ff45e32c18fe53a3d12ce6f346b230088f23f2f52e0f2"},"schema_version":"1.0","source":{"id":"2406.18033","kind":"arxiv","version":1}},"canonical_sha256":"ddcdbbcc31b0ad2de485792ff8f60f2a2d1430e0379899319a66aa99cb800b9b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ddcdbbcc31b0ad2de485792ff8f60f2a2d1430e0379899319a66aa99cb800b9b","first_computed_at":"2026-07-05T08:36:53.969386Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:36:53.969386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bN7ezu/pRFjYDvN3m4bGJYAAsQcPUO7aYVvU9TFnCfffGDuprteueMpqt7uqyU8X5mg29YM5r6nFW2hCqvYKDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:36:53.969771Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.18033","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ab00e3119b3b9232042a7d6dc7aabe9f7dcf7ffc3ca02d5365b4c196e4b53182","sha256:036dd7151871904a0d28435e592b887c042c6b89675acc521fe12cf3d50497f8"],"state_sha256":"28bdc3fe9bc22ade1ae2a3194ea0c0b518fcf112014c39b4c35758aecff9c22a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oWgSUuRBJ7lckIKjYx/uEaLcbloU8ArS2WNxvMbnz0adKKcck0StfLMKerQSyZq/SKb58V1NfusUGNSYmki0Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:37:51.422940Z","bundle_sha256":"26947e03976556d7cf24c6ecc780e63e056cbc7a92bb268e55211ffb810de8f9"}}