{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:YLRIJ2GF4LKC6AYRV74MIGMG7A","short_pith_number":"pith:YLRIJ2GF","canonical_record":{"source":{"id":"2602.06104","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T18:42:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"64a27953ff5471d9de09c80a06a4dd6ea5ac19740c15b9fd5f8258611342336d","abstract_canon_sha256":"7ad8a22a1f32efff27d98e8f9932b53c461fff740581965c10ef9aa3268bd6d7"},"schema_version":"1.0"},"canonical_sha256":"c2e284e8c5e2d42f0311aff8c41986f80ca491c85921cf063e0d7c4f48958d27","source":{"kind":"arxiv","id":"2602.06104","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06104","created_at":"2026-05-18T03:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06104v2","created_at":"2026-05-18T03:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06104","created_at":"2026-05-18T03:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"YLRIJ2GF4LKC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YLRIJ2GF4LKC6AYR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YLRIJ2GF","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:YLRIJ2GF4LKC6AYRV74MIGMG7A","target":"record","payload":{"canonical_record":{"source":{"id":"2602.06104","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T18:42:29Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"64a27953ff5471d9de09c80a06a4dd6ea5ac19740c15b9fd5f8258611342336d","abstract_canon_sha256":"7ad8a22a1f32efff27d98e8f9932b53c461fff740581965c10ef9aa3268bd6d7"},"schema_version":"1.0"},"canonical_sha256":"c2e284e8c5e2d42f0311aff8c41986f80ca491c85921cf063e0d7c4f48958d27","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:10:03.593403Z","signature_b64":"qxtlEdFrZYefDbw/OYlv8r1824ATBa2aSiQTk3M8miF+BhPJ++3NYG5j8DpWB2XHJHJ1IbwmnpgW8ox3KWWJDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2e284e8c5e2d42f0311aff8c41986f80ca491c85921cf063e0d7c4f48958d27","last_reissued_at":"2026-05-18T03:10:03.592835Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:10:03.592835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.06104","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TzLSAleVdIjkQkplGwBdXGDN1gdZLD+WeasXBqyfx3wqI/kTEmLCtMTdi4gH2dsikRSvUtky5C9UR1Ul9nLGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:40:01.329661Z"},"content_sha256":"f3b9d2813e424c087ea6239edd936882d7d022160779cfa96584414f3b0d77c8","schema_version":"1.0","event_id":"sha256:f3b9d2813e424c087ea6239edd936882d7d022160779cfa96584414f3b0d77c8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:YLRIJ2GF4LKC6AYRV74MIGMG7A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Pragmatic Curiosity trades information gain on latent symbols against expected regret to unify hybrid learning and optimization.","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Anjali Parashar, Chuchu Fan, Enlu Zhou, Yingke Li","submitted_at":"2026-02-05T18:42:29Z","abstract_excerpt":"Many engineering and scientific workflows rely on expensive black-box evaluations, requiring sequential decisions that must both improve task performance and reduce uncertainty. Bayesian optimization (BO) and Bayesian experimental design (BED) provide powerful but largely separate treatments of goal-directed optimization and information-seeking experimentation, leaving limited guidance for hybrid settings in which learning and optimization are intrinsically coupled. We propose Pragmatic Curiosity (PraC), a unified framework for hybrid learning and optimization via active inference. PraC evalua"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We propose Pragmatic Curiosity (PraC), a unified framework for hybrid learning and optimization via active inference. PraC evaluates candidate queries by trading information gain about a task-relevant latent symbol against an expected regret-based potential over outcomes.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the three operational design choices (latent quantity, regret encoding, and information-regret exchange strength) can be specified without task-specific staging rules while still producing reliable downstream risk reduction across regimes.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"PraC unifies hybrid learning and optimization by trading information gain on task-relevant latents against regret-based value within active inference.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Pragmatic Curiosity trades information gain on latent symbols against expected regret to unify hybrid learning and optimization.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"fbb2797a0f9f76d518c7a8f1b9063fb2b9129231852bf1942188c9cf4664f57b"},"source":{"id":"2602.06104","kind":"arxiv","version":2},"verdict":{"id":"e471d367-9732-48ac-9437-b7c2425b6952","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-16T06:39:47.741624Z","strongest_claim":"We propose Pragmatic Curiosity (PraC), a unified framework for hybrid learning and optimization via active inference. PraC evaluates candidate queries by trading information gain about a task-relevant latent symbol against an expected regret-based potential over outcomes.","one_line_summary":"PraC unifies hybrid learning and optimization by trading information gain on task-relevant latents against regret-based value within active inference.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the three operational design choices (latent quantity, regret encoding, and information-regret exchange strength) can be specified without task-specific staging rules while still producing reliable downstream risk reduction across regimes.","pith_extraction_headline":"Pragmatic Curiosity trades information gain on latent symbols against expected regret to unify hybrid learning and optimization."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f5f8f04176c6904b3e24a088234d0b3bbe260f46cf2102a802c49067c31a1d5c"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"e471d367-9732-48ac-9437-b7c2425b6952"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T03:10:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"chS23GPTx61B9nGIpXWv9mgvhTSuijsPwGJvPJsFDmw+YnTdcP9wQqhqJlHJFcoN+FJvvVtYYThFhObxfZP9Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T12:40:01.330410Z"},"content_sha256":"39167d2e2f28c49e139f5bc81582fefa4d3604ec42a1e19ffe0dbd417f5eab4c","schema_version":"1.0","event_id":"sha256:39167d2e2f28c49e139f5bc81582fefa4d3604ec42a1e19ffe0dbd417f5eab4c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YLRIJ2GF4LKC6AYRV74MIGMG7A/bundle.json","state_url":"https://pith.science/pith/YLRIJ2GF4LKC6AYRV74MIGMG7A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YLRIJ2GF4LKC6AYRV74MIGMG7A/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":"2026-05-26T12:40:01Z","links":{"resolver":"https://pith.science/pith/YLRIJ2GF4LKC6AYRV74MIGMG7A","bundle":"https://pith.science/pith/YLRIJ2GF4LKC6AYRV74MIGMG7A/bundle.json","state":"https://pith.science/pith/YLRIJ2GF4LKC6AYRV74MIGMG7A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YLRIJ2GF4LKC6AYRV74MIGMG7A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:YLRIJ2GF4LKC6AYRV74MIGMG7A","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":"7ad8a22a1f32efff27d98e8f9932b53c461fff740581965c10ef9aa3268bd6d7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T18:42:29Z","title_canon_sha256":"64a27953ff5471d9de09c80a06a4dd6ea5ac19740c15b9fd5f8258611342336d"},"schema_version":"1.0","source":{"id":"2602.06104","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.06104","created_at":"2026-05-18T03:10:03Z"},{"alias_kind":"arxiv_version","alias_value":"2602.06104v2","created_at":"2026-05-18T03:10:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.06104","created_at":"2026-05-18T03:10:03Z"},{"alias_kind":"pith_short_12","alias_value":"YLRIJ2GF4LKC","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"YLRIJ2GF4LKC6AYR","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"YLRIJ2GF","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:39167d2e2f28c49e139f5bc81582fefa4d3604ec42a1e19ffe0dbd417f5eab4c","target":"graph","created_at":"2026-05-18T03:10:03Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"We propose Pragmatic Curiosity (PraC), a unified framework for hybrid learning and optimization via active inference. PraC evaluates candidate queries by trading information gain about a task-relevant latent symbol against an expected regret-based potential over outcomes."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the three operational design choices (latent quantity, regret encoding, and information-regret exchange strength) can be specified without task-specific staging rules while still producing reliable downstream risk reduction across regimes."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"PraC unifies hybrid learning and optimization by trading information gain on task-relevant latents against regret-based value within active inference."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Pragmatic Curiosity trades information gain on latent symbols against expected regret to unify hybrid learning and optimization."}],"snapshot_sha256":"fbb2797a0f9f76d518c7a8f1b9063fb2b9129231852bf1942188c9cf4664f57b"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f5f8f04176c6904b3e24a088234d0b3bbe260f46cf2102a802c49067c31a1d5c"},"paper":{"abstract_excerpt":"Many engineering and scientific workflows rely on expensive black-box evaluations, requiring sequential decisions that must both improve task performance and reduce uncertainty. Bayesian optimization (BO) and Bayesian experimental design (BED) provide powerful but largely separate treatments of goal-directed optimization and information-seeking experimentation, leaving limited guidance for hybrid settings in which learning and optimization are intrinsically coupled. We propose Pragmatic Curiosity (PraC), a unified framework for hybrid learning and optimization via active inference. PraC evalua","authors_text":"Anjali Parashar, Chuchu Fan, Enlu Zhou, Yingke Li","cross_cats":["stat.ML"],"headline":"Pragmatic Curiosity trades information gain on latent symbols against expected regret to unify hybrid learning and optimization.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T18:42:29Z","title":"Pragmatic Curiosity: A Unified Framework for Hybrid Learning and Optimization via Active Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.06104","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-16T06:39:47.741624Z","id":"e471d367-9732-48ac-9437-b7c2425b6952","model_set":{"reader":"grok-4.3"},"one_line_summary":"PraC unifies hybrid learning and optimization by trading information gain on task-relevant latents against regret-based value within active inference.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Pragmatic Curiosity trades information gain on latent symbols against expected regret to unify hybrid learning and optimization.","strongest_claim":"We propose Pragmatic Curiosity (PraC), a unified framework for hybrid learning and optimization via active inference. PraC evaluates candidate queries by trading information gain about a task-relevant latent symbol against an expected regret-based potential over outcomes.","weakest_assumption":"That the three operational design choices (latent quantity, regret encoding, and information-regret exchange strength) can be specified without task-specific staging rules while still producing reliable downstream risk reduction across regimes."}},"verdict_id":"e471d367-9732-48ac-9437-b7c2425b6952"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f3b9d2813e424c087ea6239edd936882d7d022160779cfa96584414f3b0d77c8","target":"record","created_at":"2026-05-18T03:10:03Z","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":"7ad8a22a1f32efff27d98e8f9932b53c461fff740581965c10ef9aa3268bd6d7","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-02-05T18:42:29Z","title_canon_sha256":"64a27953ff5471d9de09c80a06a4dd6ea5ac19740c15b9fd5f8258611342336d"},"schema_version":"1.0","source":{"id":"2602.06104","kind":"arxiv","version":2}},"canonical_sha256":"c2e284e8c5e2d42f0311aff8c41986f80ca491c85921cf063e0d7c4f48958d27","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c2e284e8c5e2d42f0311aff8c41986f80ca491c85921cf063e0d7c4f48958d27","first_computed_at":"2026-05-18T03:10:03.592835Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:10:03.592835Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qxtlEdFrZYefDbw/OYlv8r1824ATBa2aSiQTk3M8miF+BhPJ++3NYG5j8DpWB2XHJHJ1IbwmnpgW8ox3KWWJDw==","signature_status":"signed_v1","signed_at":"2026-05-18T03:10:03.593403Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.06104","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f3b9d2813e424c087ea6239edd936882d7d022160779cfa96584414f3b0d77c8","sha256:39167d2e2f28c49e139f5bc81582fefa4d3604ec42a1e19ffe0dbd417f5eab4c"],"state_sha256":"056e42fc92737c7f4d6759dfb1062878308c02de18b5b9e2540d04d96ee082b0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tz/hp3pRi6264j+DsTivE33e/M20P0pGT8FL2Vh9a5M2flOTPeWSc+c/pfmpc4Ro20vCz+WtaKiZjxfDqVtNAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T12:40:01.334272Z","bundle_sha256":"29155266be7544399b02f058bf3721e37de730ee05a6d68153867d5b938bc7dd"}}