{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:M6QFB5623JUEIB3OUYYHYTZGQT","short_pith_number":"pith:M6QFB562","canonical_record":{"source":{"id":"1803.02912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-07T23:26:49Z","cross_cats_sorted":[],"title_canon_sha256":"ce6101d285b253b1d090ebbee34688561e5af152a1f05b73a52f5f2202893366","abstract_canon_sha256":"ba4730d1dc1f88cbbd3b262490f8aaf3801467b8e38d7029b62e8cde5c2aa9b1"},"schema_version":"1.0"},"canonical_sha256":"67a050f7dada6844076ea6307c4f2684c3e0314a3c4c558c45c83c0d146da9ad","source":{"kind":"arxiv","id":"1803.02912","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02912","created_at":"2026-05-18T00:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02912v1","created_at":"2026-05-18T00:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02912","created_at":"2026-05-18T00:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"M6QFB5623JUE","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M6QFB5623JUEIB3O","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M6QFB562","created_at":"2026-05-18T12:32:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:M6QFB5623JUEIB3OUYYHYTZGQT","target":"record","payload":{"canonical_record":{"source":{"id":"1803.02912","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-07T23:26:49Z","cross_cats_sorted":[],"title_canon_sha256":"ce6101d285b253b1d090ebbee34688561e5af152a1f05b73a52f5f2202893366","abstract_canon_sha256":"ba4730d1dc1f88cbbd3b262490f8aaf3801467b8e38d7029b62e8cde5c2aa9b1"},"schema_version":"1.0"},"canonical_sha256":"67a050f7dada6844076ea6307c4f2684c3e0314a3c4c558c45c83c0d146da9ad","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:21:44.999237Z","signature_b64":"uxL1Nj9u4Q1pHGLBz4K6NHG9Itn0zNISB4xQPQgrRZ/TeigdAzgsKFL9BKjjr9nLnk47Tx2V+tHlLzpVzzxoAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"67a050f7dada6844076ea6307c4f2684c3e0314a3c4c558c45c83c0d146da9ad","last_reissued_at":"2026-05-18T00:21:44.998575Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:21:44.998575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1803.02912","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":"2026-05-18T00:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dshxXIyZmJ9FnoG16WWsNoTXHtAdM7m0NesboDYTSpjYq3D4GXcxJn3lIButUZFOJ44/7exSxnfurFAQ7Sl6CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T01:27:21.084354Z"},"content_sha256":"84215e60fdb92f75ea529c4f660f9bf604d53ef6d4af671f8008608620522bce","schema_version":"1.0","event_id":"sha256:84215e60fdb92f75ea529c4f660f9bf604d53ef6d4af671f8008608620522bce"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:M6QFB5623JUEIB3OUYYHYTZGQT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Brandom-ian view of Reinforcement Learning towards strong-AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Atrisha Sarkar","submitted_at":"2018-03-07T23:26:49Z","abstract_excerpt":"The analytic philosophy of Robert Brandom, based on the ideas of pragmatism, paints a picture of sapience, through inferentialism. In this paper, we present a theory, that utilizes essential elements of Brandom's philosophy, towards the objective of achieving strong-AI. We do this by connecting the constitutive elements of reinforcement learning and the Game Of Giving and Asking For Reasons. Further, following Brandom's prescriptive thoughts, we restructure the popular reinforcement learning algorithm A3C, and show that RL algorithms can be tuned towards the objective of strong-AI."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02912","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":"2026-05-18T00:21:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6qSn7zLzz3nmr6EkwTLnJ41LyB8uy238gb0RkFxP/0NcYUAK4z8i/pVv/+E8OBPmKBWjIE8bJLt1ZVfT5fx2AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-28T01:27:21.084694Z"},"content_sha256":"8ffcd00da8464ead02eafddf91845e7434473c7c17a844b1c3a810150c2e688a","schema_version":"1.0","event_id":"sha256:8ffcd00da8464ead02eafddf91845e7434473c7c17a844b1c3a810150c2e688a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/M6QFB5623JUEIB3OUYYHYTZGQT/bundle.json","state_url":"https://pith.science/pith/M6QFB5623JUEIB3OUYYHYTZGQT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/M6QFB5623JUEIB3OUYYHYTZGQT/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":"2026-06-28T01:27:21Z","links":{"resolver":"https://pith.science/pith/M6QFB5623JUEIB3OUYYHYTZGQT","bundle":"https://pith.science/pith/M6QFB5623JUEIB3OUYYHYTZGQT/bundle.json","state":"https://pith.science/pith/M6QFB5623JUEIB3OUYYHYTZGQT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/M6QFB5623JUEIB3OUYYHYTZGQT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:M6QFB5623JUEIB3OUYYHYTZGQT","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":"ba4730d1dc1f88cbbd3b262490f8aaf3801467b8e38d7029b62e8cde5c2aa9b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-07T23:26:49Z","title_canon_sha256":"ce6101d285b253b1d090ebbee34688561e5af152a1f05b73a52f5f2202893366"},"schema_version":"1.0","source":{"id":"1803.02912","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1803.02912","created_at":"2026-05-18T00:21:44Z"},{"alias_kind":"arxiv_version","alias_value":"1803.02912v1","created_at":"2026-05-18T00:21:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1803.02912","created_at":"2026-05-18T00:21:44Z"},{"alias_kind":"pith_short_12","alias_value":"M6QFB5623JUE","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_16","alias_value":"M6QFB5623JUEIB3O","created_at":"2026-05-18T12:32:37Z"},{"alias_kind":"pith_short_8","alias_value":"M6QFB562","created_at":"2026-05-18T12:32:37Z"}],"graph_snapshots":[{"event_id":"sha256:8ffcd00da8464ead02eafddf91845e7434473c7c17a844b1c3a810150c2e688a","target":"graph","created_at":"2026-05-18T00:21:44Z","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 analytic philosophy of Robert Brandom, based on the ideas of pragmatism, paints a picture of sapience, through inferentialism. In this paper, we present a theory, that utilizes essential elements of Brandom's philosophy, towards the objective of achieving strong-AI. We do this by connecting the constitutive elements of reinforcement learning and the Game Of Giving and Asking For Reasons. Further, following Brandom's prescriptive thoughts, we restructure the popular reinforcement learning algorithm A3C, and show that RL algorithms can be tuned towards the objective of strong-AI.","authors_text":"Atrisha Sarkar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-07T23:26:49Z","title":"A Brandom-ian view of Reinforcement Learning towards strong-AI"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1803.02912","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":"sha256:84215e60fdb92f75ea529c4f660f9bf604d53ef6d4af671f8008608620522bce","target":"record","created_at":"2026-05-18T00:21:44Z","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":"ba4730d1dc1f88cbbd3b262490f8aaf3801467b8e38d7029b62e8cde5c2aa9b1","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2018-03-07T23:26:49Z","title_canon_sha256":"ce6101d285b253b1d090ebbee34688561e5af152a1f05b73a52f5f2202893366"},"schema_version":"1.0","source":{"id":"1803.02912","kind":"arxiv","version":1}},"canonical_sha256":"67a050f7dada6844076ea6307c4f2684c3e0314a3c4c558c45c83c0d146da9ad","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"67a050f7dada6844076ea6307c4f2684c3e0314a3c4c558c45c83c0d146da9ad","first_computed_at":"2026-05-18T00:21:44.998575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:21:44.998575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uxL1Nj9u4Q1pHGLBz4K6NHG9Itn0zNISB4xQPQgrRZ/TeigdAzgsKFL9BKjjr9nLnk47Tx2V+tHlLzpVzzxoAw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:21:44.999237Z","signed_message":"canonical_sha256_bytes"},"source_id":"1803.02912","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:84215e60fdb92f75ea529c4f660f9bf604d53ef6d4af671f8008608620522bce","sha256:8ffcd00da8464ead02eafddf91845e7434473c7c17a844b1c3a810150c2e688a"],"state_sha256":"c3eccda795dc280fc560c4d28022691d3b406a457d39f6dc227330541e52996d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fzdKXQGokrRRYLjhASJJPTYcYqBI/lIqTJIxUDURtOsHyzFRGzGSPSsXoS06+CBfcQCI2tTfuu8KuIYx4Cj5Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-28T01:27:21.086598Z","bundle_sha256":"b065b2425d8d9e83c7b7f19d68a81b893ecc4fbcc47e0f8d11c5a24c7c4914ef"}}