{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:D5CFCLBED6AUYGFNT5RNADEYYL","short_pith_number":"pith:D5CFCLBE","schema_version":"1.0","canonical_sha256":"1f44512c241f814c18ad9f62d00c98c2c0d910a9da118e18f94ca198d7c08621","source":{"kind":"arxiv","id":"1809.05720","version":1},"attestation_state":"computed","paper":{"title":"Incorporating Behavioral Constraints in Online AI Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Avinash Balakrishnan, Djallel Bouneffouf, Francesca Rossi, Nicholas Mattei","submitted_at":"2018-09-15T14:24:37Z","abstract_excerpt":"AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many cases the online rewards should not be the only guiding criteria, as there are additional constraints and/or priorities imposed by regulations, values, preferences, or ethical principles. We detail a novel online agent that learns a set of behavioral constraints by observation and uses these learned constraints as a guide when making decisions in an online setting while still being reactive to reward feedback. To define "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1809.05720","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-09-15T14:24:37Z","cross_cats_sorted":["cs.HC","cs.LG"],"title_canon_sha256":"9715c44abad810b0cd0a6cf30de4ad5bf2b7964f099cde28bb82a3b2c3c53fbe","abstract_canon_sha256":"544fc29a3d1b5100effada5b29e1c8f10c7f65d490fc3cce37ee60d92fb1f53e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:36.722824Z","signature_b64":"kwGH0qyT7wCUJSGOAYKvSIiaZY6Umgwg8XVlkARbtP1GeeqlFhJwXo++bETNYNj275J6eKZsRG1q1mk6WaMLDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1f44512c241f814c18ad9f62d00c98c2c0d910a9da118e18f94ca198d7c08621","last_reissued_at":"2026-05-18T00:05:36.722437Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:36.722437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Incorporating Behavioral Constraints in Online AI Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.HC","cs.LG"],"primary_cat":"cs.AI","authors_text":"Avinash Balakrishnan, Djallel Bouneffouf, Francesca Rossi, Nicholas Mattei","submitted_at":"2018-09-15T14:24:37Z","abstract_excerpt":"AI systems that learn through reward feedback about the actions they take are increasingly deployed in domains that have significant impact on our daily life. However, in many cases the online rewards should not be the only guiding criteria, as there are additional constraints and/or priorities imposed by regulations, values, preferences, or ethical principles. We detail a novel online agent that learns a set of behavioral constraints by observation and uses these learned constraints as a guide when making decisions in an online setting while still being reactive to reward feedback. To define "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1809.05720","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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1809.05720","created_at":"2026-05-18T00:05:36.722494+00:00"},{"alias_kind":"arxiv_version","alias_value":"1809.05720v1","created_at":"2026-05-18T00:05:36.722494+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1809.05720","created_at":"2026-05-18T00:05:36.722494+00:00"},{"alias_kind":"pith_short_12","alias_value":"D5CFCLBED6AU","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_16","alias_value":"D5CFCLBED6AUYGFN","created_at":"2026-05-18T12:32:19.392346+00:00"},{"alias_kind":"pith_short_8","alias_value":"D5CFCLBE","created_at":"2026-05-18T12:32:19.392346+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/D5CFCLBED6AUYGFNT5RNADEYYL","json":"https://pith.science/pith/D5CFCLBED6AUYGFNT5RNADEYYL.json","graph_json":"https://pith.science/api/pith-number/D5CFCLBED6AUYGFNT5RNADEYYL/graph.json","events_json":"https://pith.science/api/pith-number/D5CFCLBED6AUYGFNT5RNADEYYL/events.json","paper":"https://pith.science/paper/D5CFCLBE"},"agent_actions":{"view_html":"https://pith.science/pith/D5CFCLBED6AUYGFNT5RNADEYYL","download_json":"https://pith.science/pith/D5CFCLBED6AUYGFNT5RNADEYYL.json","view_paper":"https://pith.science/paper/D5CFCLBE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1809.05720&json=true","fetch_graph":"https://pith.science/api/pith-number/D5CFCLBED6AUYGFNT5RNADEYYL/graph.json","fetch_events":"https://pith.science/api/pith-number/D5CFCLBED6AUYGFNT5RNADEYYL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/D5CFCLBED6AUYGFNT5RNADEYYL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/D5CFCLBED6AUYGFNT5RNADEYYL/action/storage_attestation","attest_author":"https://pith.science/pith/D5CFCLBED6AUYGFNT5RNADEYYL/action/author_attestation","sign_citation":"https://pith.science/pith/D5CFCLBED6AUYGFNT5RNADEYYL/action/citation_signature","submit_replication":"https://pith.science/pith/D5CFCLBED6AUYGFNT5RNADEYYL/action/replication_record"}},"created_at":"2026-05-18T00:05:36.722494+00:00","updated_at":"2026-05-18T00:05:36.722494+00:00"}