{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NFPY4S3NDQHJA6YSKEBGDXQNWV","short_pith_number":"pith:NFPY4S3N","canonical_record":{"source":{"id":"2410.15181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-19T18:59:39Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"632e07cd1676a58621f4f4830270469cd7ac4acf51196b1e16cd415968d4d67e","abstract_canon_sha256":"d730e44b1066f4d49577678138a204bb84389429f25a21fb43769df64883b006"},"schema_version":"1.0"},"canonical_sha256":"695f8e4b6d1c0e907b12510261de0db55fcf519a69aa31972c8c7a1856b12167","source":{"kind":"arxiv","id":"2410.15181","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15181","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15181v1","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15181","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"pith_short_12","alias_value":"NFPY4S3NDQHJ","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"pith_short_16","alias_value":"NFPY4S3NDQHJA6YS","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"pith_short_8","alias_value":"NFPY4S3N","created_at":"2026-07-05T09:22:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NFPY4S3NDQHJA6YSKEBGDXQNWV","target":"record","payload":{"canonical_record":{"source":{"id":"2410.15181","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-19T18:59:39Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"632e07cd1676a58621f4f4830270469cd7ac4acf51196b1e16cd415968d4d67e","abstract_canon_sha256":"d730e44b1066f4d49577678138a204bb84389429f25a21fb43769df64883b006"},"schema_version":"1.0"},"canonical_sha256":"695f8e4b6d1c0e907b12510261de0db55fcf519a69aa31972c8c7a1856b12167","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:51.412325Z","signature_b64":"V8SZo7VsJmCKV4XgMzgcSVIYgWrT71zUwcvyH3zvs6jYg/3lzpT1X4Dlt3lRgkc96jpU7X2KBH3Xek4Mh6P0BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"695f8e4b6d1c0e907b12510261de0db55fcf519a69aa31972c8c7a1856b12167","last_reissued_at":"2026-07-05T09:22:51.411785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:51.411785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2410.15181","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":"2026-07-05T09:22:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XJeAvY0x29YoDw5dQaUQtF20DL+wsgHN3ASalVsccSpNrEZDmJNfWtdmIOLiSbEq/WpXO5YuLZT7YIktIT7aBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:40:38.267334Z"},"content_sha256":"2328dd27e6f06f08c498ca97932e598b7fd6075a49098bb44b5fd05321587fc6","schema_version":"1.0","event_id":"sha256:2328dd27e6f06f08c498ca97932e598b7fd6075a49098bb44b5fd05321587fc6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NFPY4S3NDQHJA6YSKEBGDXQNWV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GUIDE: Real-Time Human-Shaped Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.LG","authors_text":"Boyuan Chen, Lingyu Zhang, Nicholas R Waytowich, Zhengran Ji","submitted_at":"2024-10-19T18:59:39Z","abstract_excerpt":"The recent rapid advancement of machine learning has been driven by increasingly powerful models with the growing availability of training data and computational resources. However, real-time decision-making tasks with limited time and sparse learning signals remain challenging. One way of improving the learning speed and performance of these agents is to leverage human guidance. In this work, we introduce GUIDE, a framework for real-time human-guided reinforcement learning by enabling continuous human feedback and grounding such feedback into dense rewards to accelerate policy learning. Addit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15181","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2410.15181/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2026-07-05T09:22:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kmwvP7AK1NEp5ppy1eri4neVBh3MBkf1OvNPBZRfUoSURS39kVEn8zHLsdaIZ9AE7F1+TZs327TlMI8oCXH8BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-15T12:40:38.267873Z"},"content_sha256":"8874a7a4abcd8275f0ad20505246dfcd78c820969cceb6a3d3b0e24c106264fb","schema_version":"1.0","event_id":"sha256:8874a7a4abcd8275f0ad20505246dfcd78c820969cceb6a3d3b0e24c106264fb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NFPY4S3NDQHJA6YSKEBGDXQNWV/bundle.json","state_url":"https://pith.science/pith/NFPY4S3NDQHJA6YSKEBGDXQNWV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NFPY4S3NDQHJA6YSKEBGDXQNWV/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":"2026-08-15T12:40:38Z","links":{"resolver":"https://pith.science/pith/NFPY4S3NDQHJA6YSKEBGDXQNWV","bundle":"https://pith.science/pith/NFPY4S3NDQHJA6YSKEBGDXQNWV/bundle.json","state":"https://pith.science/pith/NFPY4S3NDQHJA6YSKEBGDXQNWV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NFPY4S3NDQHJA6YSKEBGDXQNWV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NFPY4S3NDQHJA6YSKEBGDXQNWV","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":"d730e44b1066f4d49577678138a204bb84389429f25a21fb43769df64883b006","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-19T18:59:39Z","title_canon_sha256":"632e07cd1676a58621f4f4830270469cd7ac4acf51196b1e16cd415968d4d67e"},"schema_version":"1.0","source":{"id":"2410.15181","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2410.15181","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"arxiv_version","alias_value":"2410.15181v1","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.15181","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"pith_short_12","alias_value":"NFPY4S3NDQHJ","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"pith_short_16","alias_value":"NFPY4S3NDQHJA6YS","created_at":"2026-07-05T09:22:51Z"},{"alias_kind":"pith_short_8","alias_value":"NFPY4S3N","created_at":"2026-07-05T09:22:51Z"}],"graph_snapshots":[{"event_id":"sha256:8874a7a4abcd8275f0ad20505246dfcd78c820969cceb6a3d3b0e24c106264fb","target":"graph","created_at":"2026-07-05T09:22:51Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2410.15181/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The recent rapid advancement of machine learning has been driven by increasingly powerful models with the growing availability of training data and computational resources. However, real-time decision-making tasks with limited time and sparse learning signals remain challenging. One way of improving the learning speed and performance of these agents is to leverage human guidance. In this work, we introduce GUIDE, a framework for real-time human-guided reinforcement learning by enabling continuous human feedback and grounding such feedback into dense rewards to accelerate policy learning. Addit","authors_text":"Boyuan Chen, Lingyu Zhang, Nicholas R Waytowich, Zhengran Ji","cross_cats":["cs.HC"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-19T18:59:39Z","title":"GUIDE: Real-Time Human-Shaped Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.15181","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":"sha256:2328dd27e6f06f08c498ca97932e598b7fd6075a49098bb44b5fd05321587fc6","target":"record","created_at":"2026-07-05T09:22:51Z","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":"d730e44b1066f4d49577678138a204bb84389429f25a21fb43769df64883b006","cross_cats_sorted":["cs.HC"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-10-19T18:59:39Z","title_canon_sha256":"632e07cd1676a58621f4f4830270469cd7ac4acf51196b1e16cd415968d4d67e"},"schema_version":"1.0","source":{"id":"2410.15181","kind":"arxiv","version":1}},"canonical_sha256":"695f8e4b6d1c0e907b12510261de0db55fcf519a69aa31972c8c7a1856b12167","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"695f8e4b6d1c0e907b12510261de0db55fcf519a69aa31972c8c7a1856b12167","first_computed_at":"2026-07-05T09:22:51.411785Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:22:51.411785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"V8SZo7VsJmCKV4XgMzgcSVIYgWrT71zUwcvyH3zvs6jYg/3lzpT1X4Dlt3lRgkc96jpU7X2KBH3Xek4Mh6P0BQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:22:51.412325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2410.15181","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2328dd27e6f06f08c498ca97932e598b7fd6075a49098bb44b5fd05321587fc6","sha256:8874a7a4abcd8275f0ad20505246dfcd78c820969cceb6a3d3b0e24c106264fb"],"state_sha256":"279eeb1f65d22178aa62a3e2505f6b57c12ff63ddac8f6eb1c2e930c949b26d0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Q7K5bwn1jYvcIIwMSX7ObohiKGvGZzzi0xjOnl71AlXjZl401pSXK9CMIPQwG0SUBwrUXSwRyApxd/6JVzwFDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-15T12:40:38.271222Z","bundle_sha256":"934cbb10892558395316be8cb9d4ddfbd1da575c4922c7d2bdbfa68e5a8809ce"}}