{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:JKVZYLLEPDDQCTX2YM5OXVBMM2","short_pith_number":"pith:JKVZYLLE","canonical_record":{"source":{"id":"2507.05477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T21:09:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41bbfabad174b831974cbb53270a4a71613110b3a7dc71d3ddb5582ba01d55ea","abstract_canon_sha256":"5f44d4a3142ecba0cc190164c4bedc855757e60e541903bd833ee035b49a331f"},"schema_version":"1.0"},"canonical_sha256":"4aab9c2d6478c7014efac33aebd42c668a6a97fb1f5f9e88db2bd94b7bee43f5","source":{"kind":"arxiv","id":"2507.05477","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05477","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05477v1","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05477","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_12","alias_value":"JKVZYLLEPDDQ","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_16","alias_value":"JKVZYLLEPDDQCTX2","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_8","alias_value":"JKVZYLLE","created_at":"2026-07-05T11:33:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:JKVZYLLEPDDQCTX2YM5OXVBMM2","target":"record","payload":{"canonical_record":{"source":{"id":"2507.05477","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T21:09:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"41bbfabad174b831974cbb53270a4a71613110b3a7dc71d3ddb5582ba01d55ea","abstract_canon_sha256":"5f44d4a3142ecba0cc190164c4bedc855757e60e541903bd833ee035b49a331f"},"schema_version":"1.0"},"canonical_sha256":"4aab9c2d6478c7014efac33aebd42c668a6a97fb1f5f9e88db2bd94b7bee43f5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:33:31.132594Z","signature_b64":"u5JQszov6imOfTPYIrIiXWBPRaxcOPCuQ73f8158oT0j0WqWbojNNpxTFlRs3KP247DzUW49uBbHlHabV1pCCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4aab9c2d6478c7014efac33aebd42c668a6a97fb1f5f9e88db2bd94b7bee43f5","last_reissued_at":"2026-07-05T11:33:31.132215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:33:31.132215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.05477","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":"2026-07-05T11:33:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r3W/YHSG2Zl3VAMlp41UiU46OftfJGGNdXuT15E3e3+hgAGwg/b1+CBhWSS7NUp3DiQzSUH/BcNsqbaquXTzAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:32:36.671113Z"},"content_sha256":"8b996ad4cc44795fb672183fa18c4142ee3392af631be897c0df3f2e95e388dc","schema_version":"1.0","event_id":"sha256:8b996ad4cc44795fb672183fa18c4142ee3392af631be897c0df3f2e95e388dc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:JKVZYLLEPDDQCTX2YM5OXVBMM2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Epistemically-guided forward-backward exploration","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Georg Martius, Marin Vlastelica, N\\'uria Armengol Urp\\'i, Stelian Coros","submitted_at":"2025-07-07T21:09:16Z","abstract_excerpt":"Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations (FB) have emerged as a promising method for learning optimal policies in absence of rewards via a factorization of the policy occupancy measure. However, up until now, FB and many similar zero-shot reinforcement learning algorithms have been decoupled from the exploration problem, generally relying on other exploration algorithms for data collection. We argue that FB representations should fundamentally be "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05477","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/2507.05477/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":"2026-07-05T11:33:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6IsjxbhPWi4wZ2WuhggoZy1vWpAVq1HafAXq75M1PZt6QRiNOz2DxaoyAlETrYT3mHxy0WEl+S5Xv6MAbFvFCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T02:32:36.671685Z"},"content_sha256":"9b46578fb79149ccd17599d82ea17860cde73dcd46153cfc6f4d46a3b9b3cc6b","schema_version":"1.0","event_id":"sha256:9b46578fb79149ccd17599d82ea17860cde73dcd46153cfc6f4d46a3b9b3cc6b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/JKVZYLLEPDDQCTX2YM5OXVBMM2/bundle.json","state_url":"https://pith.science/pith/JKVZYLLEPDDQCTX2YM5OXVBMM2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/JKVZYLLEPDDQCTX2YM5OXVBMM2/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":"2026-08-06T02:32:36Z","links":{"resolver":"https://pith.science/pith/JKVZYLLEPDDQCTX2YM5OXVBMM2","bundle":"https://pith.science/pith/JKVZYLLEPDDQCTX2YM5OXVBMM2/bundle.json","state":"https://pith.science/pith/JKVZYLLEPDDQCTX2YM5OXVBMM2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/JKVZYLLEPDDQCTX2YM5OXVBMM2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:JKVZYLLEPDDQCTX2YM5OXVBMM2","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":"5f44d4a3142ecba0cc190164c4bedc855757e60e541903bd833ee035b49a331f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T21:09:16Z","title_canon_sha256":"41bbfabad174b831974cbb53270a4a71613110b3a7dc71d3ddb5582ba01d55ea"},"schema_version":"1.0","source":{"id":"2507.05477","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05477","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05477v1","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05477","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_12","alias_value":"JKVZYLLEPDDQ","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_16","alias_value":"JKVZYLLEPDDQCTX2","created_at":"2026-07-05T11:33:31Z"},{"alias_kind":"pith_short_8","alias_value":"JKVZYLLE","created_at":"2026-07-05T11:33:31Z"}],"graph_snapshots":[{"event_id":"sha256:9b46578fb79149ccd17599d82ea17860cde73dcd46153cfc6f4d46a3b9b3cc6b","target":"graph","created_at":"2026-07-05T11:33:31Z","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/2507.05477/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Zero-shot reinforcement learning is necessary for extracting optimal policies in absence of concrete rewards for fast adaptation to future problem settings. Forward-backward representations (FB) have emerged as a promising method for learning optimal policies in absence of rewards via a factorization of the policy occupancy measure. However, up until now, FB and many similar zero-shot reinforcement learning algorithms have been decoupled from the exploration problem, generally relying on other exploration algorithms for data collection. We argue that FB representations should fundamentally be ","authors_text":"Georg Martius, Marin Vlastelica, N\\'uria Armengol Urp\\'i, Stelian Coros","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T21:09:16Z","title":"Epistemically-guided forward-backward exploration"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05477","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":"sha256:8b996ad4cc44795fb672183fa18c4142ee3392af631be897c0df3f2e95e388dc","target":"record","created_at":"2026-07-05T11:33:31Z","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":"5f44d4a3142ecba0cc190164c4bedc855757e60e541903bd833ee035b49a331f","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-07T21:09:16Z","title_canon_sha256":"41bbfabad174b831974cbb53270a4a71613110b3a7dc71d3ddb5582ba01d55ea"},"schema_version":"1.0","source":{"id":"2507.05477","kind":"arxiv","version":1}},"canonical_sha256":"4aab9c2d6478c7014efac33aebd42c668a6a97fb1f5f9e88db2bd94b7bee43f5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4aab9c2d6478c7014efac33aebd42c668a6a97fb1f5f9e88db2bd94b7bee43f5","first_computed_at":"2026-07-05T11:33:31.132215Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:31.132215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u5JQszov6imOfTPYIrIiXWBPRaxcOPCuQ73f8158oT0j0WqWbojNNpxTFlRs3KP247DzUW49uBbHlHabV1pCCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:31.132594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05477","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b996ad4cc44795fb672183fa18c4142ee3392af631be897c0df3f2e95e388dc","sha256:9b46578fb79149ccd17599d82ea17860cde73dcd46153cfc6f4d46a3b9b3cc6b"],"state_sha256":"cb1e696cbf7cc9534eae65b7748d23870b5a6d55da3568c7a5eaeb3958654496"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U9X4JGIcF3gQbkhZCyJ+ZuXRvGf2U8WwrZ8YvIeJLBuMzIaOU6qwqpCVLL+4gRuZ8FYKlaLIFtJGzgnhJsdNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T02:32:36.677421Z","bundle_sha256":"8251dc6a7107e402c5e45f4c67411a0542e6af83219d4b3c6c489ea2ee8a3cb8"}}