{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:NMYYVRRQRMBNXT2MGI7T6LC2FP","short_pith_number":"pith:NMYYVRRQ","canonical_record":{"source":{"id":"2401.00788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T15:30:19Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"49c76e06784c83f7f8cff4ce7dd117b2ecf033548a2410008a9ba017e45542d4","abstract_canon_sha256":"49ca2d1ec3e0406e6f971548bd2996fe57877bff688af63fc1939f8a1197d9fc"},"schema_version":"1.0"},"canonical_sha256":"6b318ac6308b02dbcf4c323f3f2c5a2be1ef5f0ad9d59d0cb77eaeb17f3561ce","source":{"kind":"arxiv","id":"2401.00788","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00788","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00788v1","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00788","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"NMYYVRRQRMBN","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"NMYYVRRQRMBNXT2M","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"NMYYVRRQ","created_at":"2026-07-05T07:29:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:NMYYVRRQRMBNXT2MGI7T6LC2FP","target":"record","payload":{"canonical_record":{"source":{"id":"2401.00788","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T15:30:19Z","cross_cats_sorted":["cs.AI","cs.SE"],"title_canon_sha256":"49c76e06784c83f7f8cff4ce7dd117b2ecf033548a2410008a9ba017e45542d4","abstract_canon_sha256":"49ca2d1ec3e0406e6f971548bd2996fe57877bff688af63fc1939f8a1197d9fc"},"schema_version":"1.0"},"canonical_sha256":"6b318ac6308b02dbcf4c323f3f2c5a2be1ef5f0ad9d59d0cb77eaeb17f3561ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:29:22.856296Z","signature_b64":"0Vm2bd2200Ja0o1m/whts+9Qb0UaPVjTS6p0y2xNoGZq2ED769ysPVhGOSafjMj3fig3wxz7TYhHp34HYG+yAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b318ac6308b02dbcf4c323f3f2c5a2be1ef5f0ad9d59d0cb77eaeb17f3561ce","last_reissued_at":"2026-07-05T07:29:22.855812Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:29:22.855812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2401.00788","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":"2026-07-05T07:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RuJFDn8LQNIdEjFu+D3Bi3Ucw9oLCuz59RlvImvk0cvaBS4aSeB45j960jag+o/PTgC2q85Hnv6nbx+6pWlRAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T19:32:25.523899Z"},"content_sha256":"0cf81594679a1f5f25a7c0b0399301f05112c8a526d5f8161235115cfdd04a59","schema_version":"1.0","event_id":"sha256:0cf81594679a1f5f25a7c0b0399301f05112c8a526d5f8161235115cfdd04a59"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:NMYYVRRQRMBNXT2MGI7T6LC2FP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.SE"],"primary_cat":"cs.CL","authors_text":"Armel Zebaze, Harm de Vries, Leandro Von Werra, Niklas Muennighoff, Nitchakarn Suppattarachai, Qian Liu, Terry Yue Zhuo","submitted_at":"2024-01-01T15:30:19Z","abstract_excerpt":"The high cost of full-parameter fine-tuning (FFT) of Large Language Models (LLMs) has led to a series of parameter-efficient fine-tuning (PEFT) methods. However, it remains unclear which methods provide the best cost-performance trade-off at different model scales. We introduce Astraios, a suite of 28 instruction-tuned OctoCoder models using 7 tuning methods and 4 model sizes up to 16 billion parameters. Through investigations across 5 tasks and 8 different datasets encompassing both code comprehension and code generation tasks, we find that FFT generally leads to the best downstream performan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00788","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/2401.00788/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":"2026-07-05T07:29:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IvkJ0Lv7etB117Aj0rzWhYyJo4kaNJOfZEAASN6fXqH0RD8tuAkFeEUb0+N9mH3H4Baj+3y6lJc+6g4jKymsDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-31T19:32:25.524384Z"},"content_sha256":"45b44ccccb7e64b80ddbc38d1a652197a0de93ded22da7ec72c7a49d65bb8f3a","schema_version":"1.0","event_id":"sha256:45b44ccccb7e64b80ddbc38d1a652197a0de93ded22da7ec72c7a49d65bb8f3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NMYYVRRQRMBNXT2MGI7T6LC2FP/bundle.json","state_url":"https://pith.science/pith/NMYYVRRQRMBNXT2MGI7T6LC2FP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NMYYVRRQRMBNXT2MGI7T6LC2FP/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":"2026-07-31T19:32:25Z","links":{"resolver":"https://pith.science/pith/NMYYVRRQRMBNXT2MGI7T6LC2FP","bundle":"https://pith.science/pith/NMYYVRRQRMBNXT2MGI7T6LC2FP/bundle.json","state":"https://pith.science/pith/NMYYVRRQRMBNXT2MGI7T6LC2FP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NMYYVRRQRMBNXT2MGI7T6LC2FP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:NMYYVRRQRMBNXT2MGI7T6LC2FP","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":"49ca2d1ec3e0406e6f971548bd2996fe57877bff688af63fc1939f8a1197d9fc","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T15:30:19Z","title_canon_sha256":"49c76e06784c83f7f8cff4ce7dd117b2ecf033548a2410008a9ba017e45542d4"},"schema_version":"1.0","source":{"id":"2401.00788","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.00788","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"arxiv_version","alias_value":"2401.00788v1","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.00788","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"pith_short_12","alias_value":"NMYYVRRQRMBN","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"pith_short_16","alias_value":"NMYYVRRQRMBNXT2M","created_at":"2026-07-05T07:29:22Z"},{"alias_kind":"pith_short_8","alias_value":"NMYYVRRQ","created_at":"2026-07-05T07:29:22Z"}],"graph_snapshots":[{"event_id":"sha256:45b44ccccb7e64b80ddbc38d1a652197a0de93ded22da7ec72c7a49d65bb8f3a","target":"graph","created_at":"2026-07-05T07:29:22Z","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/2401.00788/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The high cost of full-parameter fine-tuning (FFT) of Large Language Models (LLMs) has led to a series of parameter-efficient fine-tuning (PEFT) methods. However, it remains unclear which methods provide the best cost-performance trade-off at different model scales. We introduce Astraios, a suite of 28 instruction-tuned OctoCoder models using 7 tuning methods and 4 model sizes up to 16 billion parameters. Through investigations across 5 tasks and 8 different datasets encompassing both code comprehension and code generation tasks, we find that FFT generally leads to the best downstream performan","authors_text":"Armel Zebaze, Harm de Vries, Leandro Von Werra, Niklas Muennighoff, Nitchakarn Suppattarachai, Qian Liu, Terry Yue Zhuo","cross_cats":["cs.AI","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T15:30:19Z","title":"Astraios: Parameter-Efficient Instruction Tuning Code Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.00788","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":"sha256:0cf81594679a1f5f25a7c0b0399301f05112c8a526d5f8161235115cfdd04a59","target":"record","created_at":"2026-07-05T07:29:22Z","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":"49ca2d1ec3e0406e6f971548bd2996fe57877bff688af63fc1939f8a1197d9fc","cross_cats_sorted":["cs.AI","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-01T15:30:19Z","title_canon_sha256":"49c76e06784c83f7f8cff4ce7dd117b2ecf033548a2410008a9ba017e45542d4"},"schema_version":"1.0","source":{"id":"2401.00788","kind":"arxiv","version":1}},"canonical_sha256":"6b318ac6308b02dbcf4c323f3f2c5a2be1ef5f0ad9d59d0cb77eaeb17f3561ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b318ac6308b02dbcf4c323f3f2c5a2be1ef5f0ad9d59d0cb77eaeb17f3561ce","first_computed_at":"2026-07-05T07:29:22.855812Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:29:22.855812Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0Vm2bd2200Ja0o1m/whts+9Qb0UaPVjTS6p0y2xNoGZq2ED769ysPVhGOSafjMj3fig3wxz7TYhHp34HYG+yAA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:29:22.856296Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.00788","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0cf81594679a1f5f25a7c0b0399301f05112c8a526d5f8161235115cfdd04a59","sha256:45b44ccccb7e64b80ddbc38d1a652197a0de93ded22da7ec72c7a49d65bb8f3a"],"state_sha256":"c81713be8699e469dc19cac8e108088dafc235e4132863621df917b37e3fef9c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PvQioh/lDDzkyg+V1pigIKhJPakF08rNQpY/h0xkW8zIjrCDLOmyiBsS/gB1uKpiBXy4jxqtpr+P1ydC38rHBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-31T19:32:25.532287Z","bundle_sha256":"e1c48337f7840dcce3f132fab9436fbbb5891a950606db3e49067759d1c47156"}}