{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:477BOH2AZO3TI3RZT5VZTVSUQL","short_pith_number":"pith:477BOH2A","canonical_record":{"source":{"id":"1206.5249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-20T14:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"5582db8876fa3959ac3b1fef8c8798a15bc6b39028c2e222504b625a4d012510","abstract_canon_sha256":"33842ea07cc58ad844799e04670bd5af1b28bc6593f4049818cefc25a97142e7"},"schema_version":"1.0"},"canonical_sha256":"e7fe171f40cbb7346e399f6b99d65482d08c0769862bab17bc6a68fe5c783305","source":{"kind":"arxiv","id":"1206.5249","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.5249","created_at":"2026-05-18T03:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"1206.5249v1","created_at":"2026-05-18T03:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.5249","created_at":"2026-05-18T03:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"477BOH2AZO3T","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"477BOH2AZO3TI3RZ","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"477BOH2A","created_at":"2026-05-18T12:26:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:477BOH2AZO3TI3RZT5VZTVSUQL","target":"record","payload":{"canonical_record":{"source":{"id":"1206.5249","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-20T14:55:37Z","cross_cats_sorted":[],"title_canon_sha256":"5582db8876fa3959ac3b1fef8c8798a15bc6b39028c2e222504b625a4d012510","abstract_canon_sha256":"33842ea07cc58ad844799e04670bd5af1b28bc6593f4049818cefc25a97142e7"},"schema_version":"1.0"},"canonical_sha256":"e7fe171f40cbb7346e399f6b99d65482d08c0769862bab17bc6a68fe5c783305","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:52:40.932341Z","signature_b64":"mkf6AdlTsc9Nfru96JG4VOdvFkjXmcDYDmu9bGx5+fc8XsLtw/u4pna482a4Bo/SrTdMd6RMHs12SjQDyA0HDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e7fe171f40cbb7346e399f6b99d65482d08c0769862bab17bc6a68fe5c783305","last_reissued_at":"2026-05-18T03:52:40.931520Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:52:40.931520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1206.5249","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":"2026-05-18T03:52:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tr1XCHXc+ipzfUQgWoYVkswY6ouRkcgW9Y974/JBB1y3YP56iCuLeqRMiEdurukdSm28tmwBDfegrR+RvjiXCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T20:48:26.364568Z"},"content_sha256":"22de12e41f49dae6389ba397340165b8b4a5e281860ecb25fef94f96c8f82310","schema_version":"1.0","event_id":"sha256:22de12e41f49dae6389ba397340165b8b4a5e281860ecb25fef94f96c8f82310"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:477BOH2AZO3TI3RZT5VZTVSUQL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Probabilistic Relational Dynamics for Multiple Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ashwin Deshpande, Brian Milch, Leslie Pack Kaelbling, Luke S. Zettlemoyer","submitted_at":"2012-06-20T14:55:37Z","abstract_excerpt":"The ways in which an agent's actions affect the world can often be modeled compactly using a set of relational probabilistic planning rules. This paper addresses the problem of learning such rule sets for multiple related tasks. We take a hierarchical Bayesian approach, in which the system learns a prior distribution over rule sets. We present a class of prior distributions parameterized by a rule set prototype that is stochastically modified to produce a task-specific rule set. We also describe a coordinate ascent algorithm that iteratively optimizes the task-specific rule sets and the prior "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.5249","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":"2026-05-18T03:52:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yG09rQFCxTmOpQfb6PUSLjGdGTFn1ILUc9wn2cw9q3xIMWNrBJy8N3+SJFv84fzU8tu3PnrOj/an3eQGVB1TBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-07T20:48:26.365241Z"},"content_sha256":"16121ee9dfbddfd94fa7542eb0d2c08f7396161a5ac345c4bd86145c227e0912","schema_version":"1.0","event_id":"sha256:16121ee9dfbddfd94fa7542eb0d2c08f7396161a5ac345c4bd86145c227e0912"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/477BOH2AZO3TI3RZT5VZTVSUQL/bundle.json","state_url":"https://pith.science/pith/477BOH2AZO3TI3RZT5VZTVSUQL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/477BOH2AZO3TI3RZT5VZTVSUQL/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":"2026-06-07T20:48:26Z","links":{"resolver":"https://pith.science/pith/477BOH2AZO3TI3RZT5VZTVSUQL","bundle":"https://pith.science/pith/477BOH2AZO3TI3RZT5VZTVSUQL/bundle.json","state":"https://pith.science/pith/477BOH2AZO3TI3RZT5VZTVSUQL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/477BOH2AZO3TI3RZT5VZTVSUQL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:477BOH2AZO3TI3RZT5VZTVSUQL","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":"33842ea07cc58ad844799e04670bd5af1b28bc6593f4049818cefc25a97142e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-20T14:55:37Z","title_canon_sha256":"5582db8876fa3959ac3b1fef8c8798a15bc6b39028c2e222504b625a4d012510"},"schema_version":"1.0","source":{"id":"1206.5249","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1206.5249","created_at":"2026-05-18T03:52:40Z"},{"alias_kind":"arxiv_version","alias_value":"1206.5249v1","created_at":"2026-05-18T03:52:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1206.5249","created_at":"2026-05-18T03:52:40Z"},{"alias_kind":"pith_short_12","alias_value":"477BOH2AZO3T","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"477BOH2AZO3TI3RZ","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"477BOH2A","created_at":"2026-05-18T12:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:16121ee9dfbddfd94fa7542eb0d2c08f7396161a5ac345c4bd86145c227e0912","target":"graph","created_at":"2026-05-18T03:52:40Z","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":"The ways in which an agent's actions affect the world can often be modeled compactly using a set of relational probabilistic planning rules. This paper addresses the problem of learning such rule sets for multiple related tasks. We take a hierarchical Bayesian approach, in which the system learns a prior distribution over rule sets. We present a class of prior distributions parameterized by a rule set prototype that is stochastically modified to produce a task-specific rule set. We also describe a coordinate ascent algorithm that iteratively optimizes the task-specific rule sets and the prior ","authors_text":"Ashwin Deshpande, Brian Milch, Leslie Pack Kaelbling, Luke S. Zettlemoyer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-20T14:55:37Z","title":"Learning Probabilistic Relational Dynamics for Multiple Tasks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1206.5249","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":"sha256:22de12e41f49dae6389ba397340165b8b4a5e281860ecb25fef94f96c8f82310","target":"record","created_at":"2026-05-18T03:52:40Z","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":"33842ea07cc58ad844799e04670bd5af1b28bc6593f4049818cefc25a97142e7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2012-06-20T14:55:37Z","title_canon_sha256":"5582db8876fa3959ac3b1fef8c8798a15bc6b39028c2e222504b625a4d012510"},"schema_version":"1.0","source":{"id":"1206.5249","kind":"arxiv","version":1}},"canonical_sha256":"e7fe171f40cbb7346e399f6b99d65482d08c0769862bab17bc6a68fe5c783305","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e7fe171f40cbb7346e399f6b99d65482d08c0769862bab17bc6a68fe5c783305","first_computed_at":"2026-05-18T03:52:40.931520Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:52:40.931520Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mkf6AdlTsc9Nfru96JG4VOdvFkjXmcDYDmu9bGx5+fc8XsLtw/u4pna482a4Bo/SrTdMd6RMHs12SjQDyA0HDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T03:52:40.932341Z","signed_message":"canonical_sha256_bytes"},"source_id":"1206.5249","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:22de12e41f49dae6389ba397340165b8b4a5e281860ecb25fef94f96c8f82310","sha256:16121ee9dfbddfd94fa7542eb0d2c08f7396161a5ac345c4bd86145c227e0912"],"state_sha256":"95729041bc00bf5f7c1feaa896bb3a94de60fadb12e63687bf05edd08afc806e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v/4+55wtAW1Y9SU1paok0iAFSiYTh3RAwQSVwC+UyZU5yNCws08iwqwX71ZJfHgZta+9LVQr46TELh3jIppVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-07T20:48:26.368776Z","bundle_sha256":"979a7f5f97717a848ac688c262d0b1f1f87064a98eded225ee3167f0cfe0408d"}}