{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2012:4HFK5F4DNPOCP7LK6MLWAN5LZ4","short_pith_number":"pith:4HFK5F4D","canonical_record":{"source":{"id":"1204.0274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2012-04-01T22:35:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df9172f6dfbefd1ab154bb69369cdbb791db49abe31d852aa5c7e1956514e60d","abstract_canon_sha256":"ccbddf2b6376c915642ff215a3642d1e1e0b74d1564039ca31c0a8b8bfef4046"},"schema_version":"1.0"},"canonical_sha256":"e1caae97836bdc27fd6af3176037abcf3ec4e000ff09738d7658a894c07d92b0","source":{"kind":"arxiv","id":"1204.0274","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1204.0274","created_at":"2026-05-18T03:58:49Z"},{"alias_kind":"arxiv_version","alias_value":"1204.0274v1","created_at":"2026-05-18T03:58:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.0274","created_at":"2026-05-18T03:58:49Z"},{"alias_kind":"pith_short_12","alias_value":"4HFK5F4DNPOC","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"4HFK5F4DNPOCP7LK","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"4HFK5F4D","created_at":"2026-05-18T12:26:53Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2012:4HFK5F4DNPOCP7LK6MLWAN5LZ4","target":"record","payload":{"canonical_record":{"source":{"id":"1204.0274","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2012-04-01T22:35:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"df9172f6dfbefd1ab154bb69369cdbb791db49abe31d852aa5c7e1956514e60d","abstract_canon_sha256":"ccbddf2b6376c915642ff215a3642d1e1e0b74d1564039ca31c0a8b8bfef4046"},"schema_version":"1.0"},"canonical_sha256":"e1caae97836bdc27fd6af3176037abcf3ec4e000ff09738d7658a894c07d92b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T03:58:49.746735Z","signature_b64":"mv5GNvIHEFYm05U0C+/LRpMSPn7ZxUK620MrryPvVuLLgFXaiucoRikJUJwSK5AbEpd/jrsAL7CJjX5FRUz5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e1caae97836bdc27fd6af3176037abcf3ec4e000ff09738d7658a894c07d92b0","last_reissued_at":"2026-05-18T03:58:49.746182Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T03:58:49.746182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1204.0274","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":"2026-05-18T03:58:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"beBhHf85FtBxlAVEP5Xmw4sDSPCJMjrrPNBY6bxl9B51B0i412UQhm0paky8aYnJKXZ7sBA23qRdkiyQjjyACA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T09:40:51.583786Z"},"content_sha256":"41f75cbf5a0e5b00cd80c5e0495efee7341b79568d4bb782f4a5beaeddc9033b","schema_version":"1.0","event_id":"sha256:41f75cbf5a0e5b00cd80c5e0495efee7341b79568d4bb782f4a5beaeddc9033b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2012:4HFK5F4DNPOCP7LK6MLWAN5LZ4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning from Humans as an I-POMDP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.RO","authors_text":"Mark P. Woodward, Robert J. Wood","submitted_at":"2012-04-01T22:35:00Z","abstract_excerpt":"The interactive partially observable Markov decision process (I-POMDP) is a recently developed framework which extends the POMDP to the multi-agent setting by including agent models in the state space. This paper argues for formulating the problem of an agent learning interactively from a human teacher as an I-POMDP, where the agent \\emph{programming} to be learned is captured by random variables in the agent's state space, all \\emph{signals} from the human teacher are treated as observed random variables, and the human teacher, modeled as a distinct agent, is explicitly represented in the age"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1204.0274","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":"2026-05-18T03:58:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cCSl3YPrfgy9ef697ZHLxxCuwy4+fEIYe84Sg8j5kxAzO/1Mn5yEi6d8DqBwxli7cczmw34g1nC3cQSgo8atBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T09:40:51.584126Z"},"content_sha256":"654883323d6ba5036a3b4daf588d7d525240fe65757164a2b744428ac2ed6c09","schema_version":"1.0","event_id":"sha256:654883323d6ba5036a3b4daf588d7d525240fe65757164a2b744428ac2ed6c09"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4HFK5F4DNPOCP7LK6MLWAN5LZ4/bundle.json","state_url":"https://pith.science/pith/4HFK5F4DNPOCP7LK6MLWAN5LZ4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4HFK5F4DNPOCP7LK6MLWAN5LZ4/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":"2026-06-03T09:40:51Z","links":{"resolver":"https://pith.science/pith/4HFK5F4DNPOCP7LK6MLWAN5LZ4","bundle":"https://pith.science/pith/4HFK5F4DNPOCP7LK6MLWAN5LZ4/bundle.json","state":"https://pith.science/pith/4HFK5F4DNPOCP7LK6MLWAN5LZ4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4HFK5F4DNPOCP7LK6MLWAN5LZ4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2012:4HFK5F4DNPOCP7LK6MLWAN5LZ4","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":"ccbddf2b6376c915642ff215a3642d1e1e0b74d1564039ca31c0a8b8bfef4046","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2012-04-01T22:35:00Z","title_canon_sha256":"df9172f6dfbefd1ab154bb69369cdbb791db49abe31d852aa5c7e1956514e60d"},"schema_version":"1.0","source":{"id":"1204.0274","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1204.0274","created_at":"2026-05-18T03:58:49Z"},{"alias_kind":"arxiv_version","alias_value":"1204.0274v1","created_at":"2026-05-18T03:58:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1204.0274","created_at":"2026-05-18T03:58:49Z"},{"alias_kind":"pith_short_12","alias_value":"4HFK5F4DNPOC","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_16","alias_value":"4HFK5F4DNPOCP7LK","created_at":"2026-05-18T12:26:53Z"},{"alias_kind":"pith_short_8","alias_value":"4HFK5F4D","created_at":"2026-05-18T12:26:53Z"}],"graph_snapshots":[{"event_id":"sha256:654883323d6ba5036a3b4daf588d7d525240fe65757164a2b744428ac2ed6c09","target":"graph","created_at":"2026-05-18T03:58:49Z","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 interactive partially observable Markov decision process (I-POMDP) is a recently developed framework which extends the POMDP to the multi-agent setting by including agent models in the state space. This paper argues for formulating the problem of an agent learning interactively from a human teacher as an I-POMDP, where the agent \\emph{programming} to be learned is captured by random variables in the agent's state space, all \\emph{signals} from the human teacher are treated as observed random variables, and the human teacher, modeled as a distinct agent, is explicitly represented in the age","authors_text":"Mark P. Woodward, Robert J. Wood","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2012-04-01T22:35:00Z","title":"Learning from Humans as an I-POMDP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1204.0274","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":"sha256:41f75cbf5a0e5b00cd80c5e0495efee7341b79568d4bb782f4a5beaeddc9033b","target":"record","created_at":"2026-05-18T03:58:49Z","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":"ccbddf2b6376c915642ff215a3642d1e1e0b74d1564039ca31c0a8b8bfef4046","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2012-04-01T22:35:00Z","title_canon_sha256":"df9172f6dfbefd1ab154bb69369cdbb791db49abe31d852aa5c7e1956514e60d"},"schema_version":"1.0","source":{"id":"1204.0274","kind":"arxiv","version":1}},"canonical_sha256":"e1caae97836bdc27fd6af3176037abcf3ec4e000ff09738d7658a894c07d92b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e1caae97836bdc27fd6af3176037abcf3ec4e000ff09738d7658a894c07d92b0","first_computed_at":"2026-05-18T03:58:49.746182Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T03:58:49.746182Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mv5GNvIHEFYm05U0C+/LRpMSPn7ZxUK620MrryPvVuLLgFXaiucoRikJUJwSK5AbEpd/jrsAL7CJjX5FRUz5Ag==","signature_status":"signed_v1","signed_at":"2026-05-18T03:58:49.746735Z","signed_message":"canonical_sha256_bytes"},"source_id":"1204.0274","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41f75cbf5a0e5b00cd80c5e0495efee7341b79568d4bb782f4a5beaeddc9033b","sha256:654883323d6ba5036a3b4daf588d7d525240fe65757164a2b744428ac2ed6c09"],"state_sha256":"4085ce5dcf4b08aaa4ed03955c52941225af8d548a4e664398bc2e8070c62fb7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"t+PrzOh5B6cZFN+7Pf4vc49+C2FgzIirB8M/hDPVCXf+2o6AQO4V9+MgCJoJnIfBzNiDBS+UKlU0aoVOO2XWDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T09:40:51.586044Z","bundle_sha256":"4dc70e347a806c341049e32d5848f672a36b7e5b8378a7bafa31248348169558"}}