{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:PPRHVYFDYHZ7LTNRBRHSWGBOPW","short_pith_number":"pith:PPRHVYFD","canonical_record":{"source":{"id":"2403.13578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-20T13:24:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"564d053fdde4510a6e5e0c31c155d1f70eec93c1506158916445595d21230482","abstract_canon_sha256":"cb286e60f5d8a590248973740e5156416d8b571e3911131c8e9e62d6a9647e15"},"schema_version":"1.0"},"canonical_sha256":"7be27ae0a3c1f3f5cdb10c4f2b182e7d99b9ff4eb4a90da5e8f864dd99387bea","source":{"kind":"arxiv","id":"2403.13578","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13578","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13578v1","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13578","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"pith_short_12","alias_value":"PPRHVYFDYHZ7","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"pith_short_16","alias_value":"PPRHVYFDYHZ7LTNR","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"pith_short_8","alias_value":"PPRHVYFD","created_at":"2026-07-05T07:58:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:PPRHVYFDYHZ7LTNRBRHSWGBOPW","target":"record","payload":{"canonical_record":{"source":{"id":"2403.13578","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-20T13:24:41Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"564d053fdde4510a6e5e0c31c155d1f70eec93c1506158916445595d21230482","abstract_canon_sha256":"cb286e60f5d8a590248973740e5156416d8b571e3911131c8e9e62d6a9647e15"},"schema_version":"1.0"},"canonical_sha256":"7be27ae0a3c1f3f5cdb10c4f2b182e7d99b9ff4eb4a90da5e8f864dd99387bea","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:58:38.747194Z","signature_b64":"mY3XWRm4mSn0EcwtGjwAwWMFl3bLq+DG+qKnsqy6IXeWNj8CarZx4oTSrFYVJcDufD/IPHnBro/bJ40nBKm7CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7be27ae0a3c1f3f5cdb10c4f2b182e7d99b9ff4eb4a90da5e8f864dd99387bea","last_reissued_at":"2026-07-05T07:58:38.746698Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:58:38.746698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2403.13578","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":"2026-07-05T07:58:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AHpp0TjDyjcVkIwNW9Jzk6Cf13si0XCJKRl17xR90hcuJfie3mcjQfk5UE5mpaxGyagmTKWzlhCkO2gxSHdiBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:21:03.305776Z"},"content_sha256":"a1fc47496d0675990ad549ba055e7f65c516118044f12ba5d0d00dd866049d59","schema_version":"1.0","event_id":"sha256:a1fc47496d0675990ad549ba055e7f65c516118044f12ba5d0d00dd866049d59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:PPRHVYFDYHZ7LTNRBRHSWGBOPW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Do June Min, Kenneth Resnicow, Rada Mihalcea, Veronica Perez-Rosas","submitted_at":"2024-03-20T13:24:41Z","abstract_excerpt":"In this paper, we study the problem of multi-reward reinforcement learning to jointly optimize for multiple text qualities for natural language generation. We focus on the task of counselor reflection generation, where we optimize the generators to simultaneously improve the fluency, coherence, and reflection quality of generated counselor responses. We introduce two novel bandit methods, DynaOpt and C-DynaOpt, which rely on the broad strategy of combining rewards into a single value and optimizing them simultaneously. Specifically, we employ non-contextual and contextual multi-arm bandits to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13578","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/2403.13578/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":"2026-07-05T07:58:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OQvvLOC7GEnEHcoql8C0xusNxT5oYJsPRyDuIEPSgAkBE+WFa4sA34lGpCKJAbVzOdiYG/YaMPYjS3cXAAvODg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T01:21:03.306718Z"},"content_sha256":"2a101043c82f3c86476547130f9c821f7e56884a8a9d0cf43c3234cca1887b55","schema_version":"1.0","event_id":"sha256:2a101043c82f3c86476547130f9c821f7e56884a8a9d0cf43c3234cca1887b55"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PPRHVYFDYHZ7LTNRBRHSWGBOPW/bundle.json","state_url":"https://pith.science/pith/PPRHVYFDYHZ7LTNRBRHSWGBOPW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PPRHVYFDYHZ7LTNRBRHSWGBOPW/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":"2026-08-13T01:21:03Z","links":{"resolver":"https://pith.science/pith/PPRHVYFDYHZ7LTNRBRHSWGBOPW","bundle":"https://pith.science/pith/PPRHVYFDYHZ7LTNRBRHSWGBOPW/bundle.json","state":"https://pith.science/pith/PPRHVYFDYHZ7LTNRBRHSWGBOPW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PPRHVYFDYHZ7LTNRBRHSWGBOPW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:PPRHVYFDYHZ7LTNRBRHSWGBOPW","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":"cb286e60f5d8a590248973740e5156416d8b571e3911131c8e9e62d6a9647e15","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-20T13:24:41Z","title_canon_sha256":"564d053fdde4510a6e5e0c31c155d1f70eec93c1506158916445595d21230482"},"schema_version":"1.0","source":{"id":"2403.13578","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.13578","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"arxiv_version","alias_value":"2403.13578v1","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13578","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"pith_short_12","alias_value":"PPRHVYFDYHZ7","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"pith_short_16","alias_value":"PPRHVYFDYHZ7LTNR","created_at":"2026-07-05T07:58:38Z"},{"alias_kind":"pith_short_8","alias_value":"PPRHVYFD","created_at":"2026-07-05T07:58:38Z"}],"graph_snapshots":[{"event_id":"sha256:2a101043c82f3c86476547130f9c821f7e56884a8a9d0cf43c3234cca1887b55","target":"graph","created_at":"2026-07-05T07:58:38Z","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/2403.13578/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we study the problem of multi-reward reinforcement learning to jointly optimize for multiple text qualities for natural language generation. We focus on the task of counselor reflection generation, where we optimize the generators to simultaneously improve the fluency, coherence, and reflection quality of generated counselor responses. We introduce two novel bandit methods, DynaOpt and C-DynaOpt, which rely on the broad strategy of combining rewards into a single value and optimizing them simultaneously. Specifically, we employ non-contextual and contextual multi-arm bandits to ","authors_text":"Do June Min, Kenneth Resnicow, Rada Mihalcea, Veronica Perez-Rosas","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-20T13:24:41Z","title":"Dynamic Reward Adjustment in Multi-Reward Reinforcement Learning for Counselor Reflection Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13578","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:a1fc47496d0675990ad549ba055e7f65c516118044f12ba5d0d00dd866049d59","target":"record","created_at":"2026-07-05T07:58:38Z","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":"cb286e60f5d8a590248973740e5156416d8b571e3911131c8e9e62d6a9647e15","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-03-20T13:24:41Z","title_canon_sha256":"564d053fdde4510a6e5e0c31c155d1f70eec93c1506158916445595d21230482"},"schema_version":"1.0","source":{"id":"2403.13578","kind":"arxiv","version":1}},"canonical_sha256":"7be27ae0a3c1f3f5cdb10c4f2b182e7d99b9ff4eb4a90da5e8f864dd99387bea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7be27ae0a3c1f3f5cdb10c4f2b182e7d99b9ff4eb4a90da5e8f864dd99387bea","first_computed_at":"2026-07-05T07:58:38.746698Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:58:38.746698Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mY3XWRm4mSn0EcwtGjwAwWMFl3bLq+DG+qKnsqy6IXeWNj8CarZx4oTSrFYVJcDufD/IPHnBro/bJ40nBKm7CA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:58:38.747194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.13578","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a1fc47496d0675990ad549ba055e7f65c516118044f12ba5d0d00dd866049d59","sha256:2a101043c82f3c86476547130f9c821f7e56884a8a9d0cf43c3234cca1887b55"],"state_sha256":"9de0d0f734ddcb2ee76d4c23d10a417342878674040ca92c49ecf9921f2ddc3b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5vtqxrWsP0JOfw8a46qfllRN2pDvYrGsYvV9hvQeSLfVUv03Mw1B8QJ8Ah+FZHjirgAvkVLvmtQ9pWTzBo+UBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T01:21:03.337105Z","bundle_sha256":"0a4f3d69366358c89383054aeb46ecc65f8aaa6c6a4f40e0604afa7bcd8513ae"}}