{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SMQCWGIU27KPP2C4LCSJX2EEY6","short_pith_number":"pith:SMQCWGIU","canonical_record":{"source":{"id":"2606.24747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T16:09:57Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"3cfbc6ed8b6c8a0785303441a12ca7b76198796773b0e4cc780373a12d7e1981","abstract_canon_sha256":"10fa748e6048b4f424c58971a2b3a636aa91f2a629dfb1763357b0ac893bf5af"},"schema_version":"1.0"},"canonical_sha256":"93202b1914d7d4f7e85c58a49be884c7abc247655f5d61127c94cc0a4b14e4df","source":{"kind":"arxiv","id":"2606.24747","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24747","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24747v1","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24747","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"pith_short_12","alias_value":"SMQCWGIU27KP","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"pith_short_16","alias_value":"SMQCWGIU27KPP2C4","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"pith_short_8","alias_value":"SMQCWGIU","created_at":"2026-06-24T01:15:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SMQCWGIU27KPP2C4LCSJX2EEY6","target":"record","payload":{"canonical_record":{"source":{"id":"2606.24747","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T16:09:57Z","cross_cats_sorted":["cs.CE"],"title_canon_sha256":"3cfbc6ed8b6c8a0785303441a12ca7b76198796773b0e4cc780373a12d7e1981","abstract_canon_sha256":"10fa748e6048b4f424c58971a2b3a636aa91f2a629dfb1763357b0ac893bf5af"},"schema_version":"1.0"},"canonical_sha256":"93202b1914d7d4f7e85c58a49be884c7abc247655f5d61127c94cc0a4b14e4df","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-24T01:15:40.982784Z","signature_b64":"m/vf0hHPvP9oPkf1wWiEz83wmYoV4cWpLgMgYfMq0AI51X/GFSpdbzrCMK7A8ccAmKrI+h3YIFIS7/uYbUVEAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"93202b1914d7d4f7e85c58a49be884c7abc247655f5d61127c94cc0a4b14e4df","last_reissued_at":"2026-06-24T01:15:40.982390Z","signature_status":"signed_v1","first_computed_at":"2026-06-24T01:15:40.982390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.24747","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":"2026-06-24T01:15:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CO+/4zdNxJYUPPyX9827t5jpoVdMYTw/oq1FJqcIEMbtoRPwTSv9rHx/4xArDQ6YJZOvUvClepOSQ/5wYWFVDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T00:49:47.628679Z"},"content_sha256":"de196cd090810b3bd15646435f62a1f014e3fc50e9f87e866e533452232af274","schema_version":"1.0","event_id":"sha256:de196cd090810b3bd15646435f62a1f014e3fc50e9f87e866e533452232af274"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SMQCWGIU27KPP2C4LCSJX2EEY6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Scaling Laws for Task-Specific LLM Distillation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CE"],"primary_cat":"cs.AI","authors_text":"Dhruv Desai, Ioana Boier, Lavinia Ghita","submitted_at":"2026-06-23T16:09:57Z","abstract_excerpt":"Large Language Models (LLMs) achieve strong performance across a growing range of domains, yet their scale poses deployment challenges in applications where latency and cost constraints are critical. This paper derives empirical scaling laws for domain-specific LLM compression, quantifying how in-domain and general knowledge performance scale with dataset size, compression ratio, supervision format, and iterative pruning schedule. Using quantitative finance as our application domain, we compare logit-based and LoRA-based distillation under iterative structural pruning, introducing a blended ch"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24747","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/2606.24747/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":"2026-06-24T01:15:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U6M2ugkxj7c2SioJbVET0qOp+u/PviL9G3IAaLYIN8ml4elE3ahSk/HLbwr8PME/yFX+oknWClGT9WFnLyslDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-27T00:49:47.629050Z"},"content_sha256":"3e657cda05da296dd731e6bf69aa0306837d5b3be276d95f744c10446b55fb4b","schema_version":"1.0","event_id":"sha256:3e657cda05da296dd731e6bf69aa0306837d5b3be276d95f744c10446b55fb4b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SMQCWGIU27KPP2C4LCSJX2EEY6/bundle.json","state_url":"https://pith.science/pith/SMQCWGIU27KPP2C4LCSJX2EEY6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SMQCWGIU27KPP2C4LCSJX2EEY6/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":"2026-06-27T00:49:47Z","links":{"resolver":"https://pith.science/pith/SMQCWGIU27KPP2C4LCSJX2EEY6","bundle":"https://pith.science/pith/SMQCWGIU27KPP2C4LCSJX2EEY6/bundle.json","state":"https://pith.science/pith/SMQCWGIU27KPP2C4LCSJX2EEY6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SMQCWGIU27KPP2C4LCSJX2EEY6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SMQCWGIU27KPP2C4LCSJX2EEY6","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":"10fa748e6048b4f424c58971a2b3a636aa91f2a629dfb1763357b0ac893bf5af","cross_cats_sorted":["cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T16:09:57Z","title_canon_sha256":"3cfbc6ed8b6c8a0785303441a12ca7b76198796773b0e4cc780373a12d7e1981"},"schema_version":"1.0","source":{"id":"2606.24747","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.24747","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.24747v1","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.24747","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"pith_short_12","alias_value":"SMQCWGIU27KP","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"pith_short_16","alias_value":"SMQCWGIU27KPP2C4","created_at":"2026-06-24T01:15:40Z"},{"alias_kind":"pith_short_8","alias_value":"SMQCWGIU","created_at":"2026-06-24T01:15:40Z"}],"graph_snapshots":[{"event_id":"sha256:3e657cda05da296dd731e6bf69aa0306837d5b3be276d95f744c10446b55fb4b","target":"graph","created_at":"2026-06-24T01:15:40Z","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/2606.24747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) achieve strong performance across a growing range of domains, yet their scale poses deployment challenges in applications where latency and cost constraints are critical. This paper derives empirical scaling laws for domain-specific LLM compression, quantifying how in-domain and general knowledge performance scale with dataset size, compression ratio, supervision format, and iterative pruning schedule. Using quantitative finance as our application domain, we compare logit-based and LoRA-based distillation under iterative structural pruning, introducing a blended ch","authors_text":"Dhruv Desai, Ioana Boier, Lavinia Ghita","cross_cats":["cs.CE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T16:09:57Z","title":"Scaling Laws for Task-Specific LLM Distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.24747","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:de196cd090810b3bd15646435f62a1f014e3fc50e9f87e866e533452232af274","target":"record","created_at":"2026-06-24T01:15:40Z","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":"10fa748e6048b4f424c58971a2b3a636aa91f2a629dfb1763357b0ac893bf5af","cross_cats_sorted":["cs.CE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-23T16:09:57Z","title_canon_sha256":"3cfbc6ed8b6c8a0785303441a12ca7b76198796773b0e4cc780373a12d7e1981"},"schema_version":"1.0","source":{"id":"2606.24747","kind":"arxiv","version":1}},"canonical_sha256":"93202b1914d7d4f7e85c58a49be884c7abc247655f5d61127c94cc0a4b14e4df","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"93202b1914d7d4f7e85c58a49be884c7abc247655f5d61127c94cc0a4b14e4df","first_computed_at":"2026-06-24T01:15:40.982390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-24T01:15:40.982390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"m/vf0hHPvP9oPkf1wWiEz83wmYoV4cWpLgMgYfMq0AI51X/GFSpdbzrCMK7A8ccAmKrI+h3YIFIS7/uYbUVEAg==","signature_status":"signed_v1","signed_at":"2026-06-24T01:15:40.982784Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.24747","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:de196cd090810b3bd15646435f62a1f014e3fc50e9f87e866e533452232af274","sha256:3e657cda05da296dd731e6bf69aa0306837d5b3be276d95f744c10446b55fb4b"],"state_sha256":"0992fde33645d509556bc198d8984d03ad7d30970c2e774cfeb074fc74e735d7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9Tp4zthQTYqxt72MyIo8U8TsCobBaZXGg1e5a9q9qxleruuF58ceW678+NlpoC1Qer7MVFzAW+2Ze2Myia0SBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-27T00:49:47.631008Z","bundle_sha256":"9b01553145d8a5f894c9059b9463633cdd2e7505304f5aa7a2bd8ee96a0e6dbc"}}