{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MODKYZ6PUH6EGQMWZIY2ZPPJQN","short_pith_number":"pith:MODKYZ6P","canonical_record":{"source":{"id":"2502.08759","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-12T20:03:56Z","cross_cats_sorted":[],"title_canon_sha256":"f3f2e556ae9173a405006106a2d05774450170d3ff9422d520c335ee3b722a34","abstract_canon_sha256":"4869d8de33f48bdfd35d341bd42c77393985896f2f6767a8d466a3eed4ab83d2"},"schema_version":"1.0"},"canonical_sha256":"6386ac67cfa1fc434196ca31acbde983522183c0b1ad935022a381eef478bb49","source":{"kind":"arxiv","id":"2502.08759","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08759","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08759v1","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08759","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"MODKYZ6PUH6E","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"MODKYZ6PUH6EGQMW","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"MODKYZ6P","created_at":"2026-07-05T10:13:29Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MODKYZ6PUH6EGQMWZIY2ZPPJQN","target":"record","payload":{"canonical_record":{"source":{"id":"2502.08759","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-12T20:03:56Z","cross_cats_sorted":[],"title_canon_sha256":"f3f2e556ae9173a405006106a2d05774450170d3ff9422d520c335ee3b722a34","abstract_canon_sha256":"4869d8de33f48bdfd35d341bd42c77393985896f2f6767a8d466a3eed4ab83d2"},"schema_version":"1.0"},"canonical_sha256":"6386ac67cfa1fc434196ca31acbde983522183c0b1ad935022a381eef478bb49","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:13:29.555236Z","signature_b64":"iqB1Ojiyp5gTVdfVgwWDzmpipkCPu9Z/BbaWfs9mvONoCR6qs6VU+v7xBDFTX1aYYE4kbYVBvyMl6dJfSGqeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6386ac67cfa1fc434196ca31acbde983522183c0b1ad935022a381eef478bb49","last_reissued_at":"2026-07-05T10:13:29.554680Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:13:29.554680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.08759","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":"2026-07-05T10:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rKFg99agQ0vsqFyAm1hvi+TTL2Lmx0M172e5wI98L+HKwvdo487FMDprjShrH4zRPfjWDS7hi39P7aL4s8umDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:49:34.578736Z"},"content_sha256":"b97a35611d81b6dff1c55f0979b74ebdd7df3b16d53fa143b80f58f6f6e1a6a1","schema_version":"1.0","event_id":"sha256:b97a35611d81b6dff1c55f0979b74ebdd7df3b16d53fa143b80f58f6f6e1a6a1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MODKYZ6PUH6EGQMWZIY2ZPPJQN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Contextual bandits with entropy-based human feedback","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Lili Meng, Raihan Seraj, Tristan Sylvain","submitted_at":"2025-02-12T20:03:56Z","abstract_excerpt":"In recent years, preference-based human feedback mechanisms have become essential for enhancing model performance across diverse applications, including conversational AI systems such as ChatGPT. However, existing approaches often neglect critical aspects, such as model uncertainty and the variability in feedback quality. To address these challenges, we introduce an entropy-based human feedback framework for contextual bandits, which dynamically balances exploration and exploitation by soliciting expert feedback only when model entropy exceeds a predefined threshold. Our method is model-agnost"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08759","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/2502.08759/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":"2026-07-05T10:13:29Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EmJU+G8Ym12uoMA3UZPxgTj+RKenqRq2lB3aPCC40nCKu0IZSuI4xRWO4aymGhfJY+PxISKZTcFBa92S4dMLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T06:49:34.579697Z"},"content_sha256":"51f260c16f44d7d5e5e7520042ec8df6cbf78f7cdbcbcc5dd6c0ceeeabd126a6","schema_version":"1.0","event_id":"sha256:51f260c16f44d7d5e5e7520042ec8df6cbf78f7cdbcbcc5dd6c0ceeeabd126a6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MODKYZ6PUH6EGQMWZIY2ZPPJQN/bundle.json","state_url":"https://pith.science/pith/MODKYZ6PUH6EGQMWZIY2ZPPJQN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MODKYZ6PUH6EGQMWZIY2ZPPJQN/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":"2026-08-21T06:49:34Z","links":{"resolver":"https://pith.science/pith/MODKYZ6PUH6EGQMWZIY2ZPPJQN","bundle":"https://pith.science/pith/MODKYZ6PUH6EGQMWZIY2ZPPJQN/bundle.json","state":"https://pith.science/pith/MODKYZ6PUH6EGQMWZIY2ZPPJQN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MODKYZ6PUH6EGQMWZIY2ZPPJQN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MODKYZ6PUH6EGQMWZIY2ZPPJQN","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":"4869d8de33f48bdfd35d341bd42c77393985896f2f6767a8d466a3eed4ab83d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-12T20:03:56Z","title_canon_sha256":"f3f2e556ae9173a405006106a2d05774450170d3ff9422d520c335ee3b722a34"},"schema_version":"1.0","source":{"id":"2502.08759","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.08759","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"arxiv_version","alias_value":"2502.08759v1","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.08759","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"pith_short_12","alias_value":"MODKYZ6PUH6E","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"pith_short_16","alias_value":"MODKYZ6PUH6EGQMW","created_at":"2026-07-05T10:13:29Z"},{"alias_kind":"pith_short_8","alias_value":"MODKYZ6P","created_at":"2026-07-05T10:13:29Z"}],"graph_snapshots":[{"event_id":"sha256:51f260c16f44d7d5e5e7520042ec8df6cbf78f7cdbcbcc5dd6c0ceeeabd126a6","target":"graph","created_at":"2026-07-05T10:13:29Z","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/2502.08759/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, preference-based human feedback mechanisms have become essential for enhancing model performance across diverse applications, including conversational AI systems such as ChatGPT. However, existing approaches often neglect critical aspects, such as model uncertainty and the variability in feedback quality. To address these challenges, we introduce an entropy-based human feedback framework for contextual bandits, which dynamically balances exploration and exploitation by soliciting expert feedback only when model entropy exceeds a predefined threshold. Our method is model-agnost","authors_text":"Lili Meng, Raihan Seraj, Tristan Sylvain","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-12T20:03:56Z","title":"Contextual bandits with entropy-based human feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.08759","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:b97a35611d81b6dff1c55f0979b74ebdd7df3b16d53fa143b80f58f6f6e1a6a1","target":"record","created_at":"2026-07-05T10:13:29Z","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":"4869d8de33f48bdfd35d341bd42c77393985896f2f6767a8d466a3eed4ab83d2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-12T20:03:56Z","title_canon_sha256":"f3f2e556ae9173a405006106a2d05774450170d3ff9422d520c335ee3b722a34"},"schema_version":"1.0","source":{"id":"2502.08759","kind":"arxiv","version":1}},"canonical_sha256":"6386ac67cfa1fc434196ca31acbde983522183c0b1ad935022a381eef478bb49","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6386ac67cfa1fc434196ca31acbde983522183c0b1ad935022a381eef478bb49","first_computed_at":"2026-07-05T10:13:29.554680Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:13:29.554680Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iqB1Ojiyp5gTVdfVgwWDzmpipkCPu9Z/BbaWfs9mvONoCR6qs6VU+v7xBDFTX1aYYE4kbYVBvyMl6dJfSGqeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:13:29.555236Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.08759","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b97a35611d81b6dff1c55f0979b74ebdd7df3b16d53fa143b80f58f6f6e1a6a1","sha256:51f260c16f44d7d5e5e7520042ec8df6cbf78f7cdbcbcc5dd6c0ceeeabd126a6"],"state_sha256":"cdff64ee3ec81802d88ced93c8186a7b9aa44b48557d148e33bb6fefaf763ba6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RGqleA3C2VWN8vp8zdOzaqr/IYsIcqVM6sgUO8VQjOxX3MAzgLB2cisr1ucsSN49zOu/XcqwNpxgmsTcuv7oCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T06:49:34.586616Z","bundle_sha256":"db1ae87ea59f5c2f3525349020e16e303e9ff0abc966caecf55cb900308b8ed6"}}