{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TFPSMIPQPTUVYPBVSUTQ6POS2N","short_pith_number":"pith:TFPSMIPQ","schema_version":"1.0","canonical_sha256":"995f2621f07ce95c3c3595270f3dd2d37bc38505401ee52b5a12c6032c6fe34f","source":{"kind":"arxiv","id":"2606.26102","version":1},"attestation_state":"computed","paper":{"title":"Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Jasmine Brazilek, Juliana Seawell","submitted_at":"2026-04-30T17:55:22Z","abstract_excerpt":"Standard post-training pipelines apply supervised fine-tuning (SFT) and reinforcement learning (RL) to make language models helpful, but these processes may inadvertently degrade values instilled during pre-training. We investigate whether the domain of post-training data differentially affects the retention of animal compassion values in a Llama 3.1 8B model mid-trained on compassion-oriented synthetic data, using both SFT (helpfulness via Dolly-15k vs. coding via Magicoder-110K) and GRPO (helpfulness via RLHFlow vs. coding via Magicoder), evaluated on the Animal Harm Benchmark (AHB 2.2) and "},"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":"2606.26102","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-30T17:55:22Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"3f5d9eddb5e6b3bfd5151d16b33c36ff47a3b86d2e52a8fab4f9b415d47b8d4e","abstract_canon_sha256":"fae61846f6df048b556cedcf5eecf43729b3edf235d00a364d990748374f293a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:26.322239Z","signature_b64":"k65saILHZT5GI/cgBd6NhJ1Pi9c7A9he1fb5FCgQxAFt5jT55hpF+nhDgrjxVRHQQOY642zvLcnPy/8a9XnaCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"995f2621f07ce95c3c3595270f3dd2d37bc38505401ee52b5a12c6032c6fe34f","last_reissued_at":"2026-06-26T00:15:26.321734Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:26.321734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Helpfulness Hurts: Domain-Dependent Degradation of Mid-Trained Compassion Values Under Post-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Jasmine Brazilek, Juliana Seawell","submitted_at":"2026-04-30T17:55:22Z","abstract_excerpt":"Standard post-training pipelines apply supervised fine-tuning (SFT) and reinforcement learning (RL) to make language models helpful, but these processes may inadvertently degrade values instilled during pre-training. We investigate whether the domain of post-training data differentially affects the retention of animal compassion values in a Llama 3.1 8B model mid-trained on compassion-oriented synthetic data, using both SFT (helpfulness via Dolly-15k vs. coding via Magicoder-110K) and GRPO (helpfulness via RLHFlow vs. coding via Magicoder), evaluated on the Animal Harm Benchmark (AHB 2.2) and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.26102","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/2606.26102/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2606.26102","created_at":"2026-06-26T00:15:26.321799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.26102v1","created_at":"2026-06-26T00:15:26.321799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.26102","created_at":"2026-06-26T00:15:26.321799+00:00"},{"alias_kind":"pith_short_12","alias_value":"TFPSMIPQPTUV","created_at":"2026-06-26T00:15:26.321799+00:00"},{"alias_kind":"pith_short_16","alias_value":"TFPSMIPQPTUVYPBV","created_at":"2026-06-26T00:15:26.321799+00:00"},{"alias_kind":"pith_short_8","alias_value":"TFPSMIPQ","created_at":"2026-06-26T00:15:26.321799+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/TFPSMIPQPTUVYPBVSUTQ6POS2N","json":"https://pith.science/pith/TFPSMIPQPTUVYPBVSUTQ6POS2N.json","graph_json":"https://pith.science/api/pith-number/TFPSMIPQPTUVYPBVSUTQ6POS2N/graph.json","events_json":"https://pith.science/api/pith-number/TFPSMIPQPTUVYPBVSUTQ6POS2N/events.json","paper":"https://pith.science/paper/TFPSMIPQ"},"agent_actions":{"view_html":"https://pith.science/pith/TFPSMIPQPTUVYPBVSUTQ6POS2N","download_json":"https://pith.science/pith/TFPSMIPQPTUVYPBVSUTQ6POS2N.json","view_paper":"https://pith.science/paper/TFPSMIPQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.26102&json=true","fetch_graph":"https://pith.science/api/pith-number/TFPSMIPQPTUVYPBVSUTQ6POS2N/graph.json","fetch_events":"https://pith.science/api/pith-number/TFPSMIPQPTUVYPBVSUTQ6POS2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TFPSMIPQPTUVYPBVSUTQ6POS2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TFPSMIPQPTUVYPBVSUTQ6POS2N/action/storage_attestation","attest_author":"https://pith.science/pith/TFPSMIPQPTUVYPBVSUTQ6POS2N/action/author_attestation","sign_citation":"https://pith.science/pith/TFPSMIPQPTUVYPBVSUTQ6POS2N/action/citation_signature","submit_replication":"https://pith.science/pith/TFPSMIPQPTUVYPBVSUTQ6POS2N/action/replication_record"}},"created_at":"2026-06-26T00:15:26.321799+00:00","updated_at":"2026-06-26T00:15:26.321799+00:00"}