{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:UH4VOP5LSB4KGBVE7JK27M5T73","short_pith_number":"pith:UH4VOP5L","canonical_record":{"source":{"id":"2607.07469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T14:32:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99d65d2cfd6d9e08ce552fbc2e3308de300c887ae62a39a41620e84c7debdcfb","abstract_canon_sha256":"09d7f7c75e7ac44d0ff352cb327c51669317d6f0e847be723ee81edb872aa0d8"},"schema_version":"1.0"},"canonical_sha256":"a1f9573fab9078a306a4fa55afb3b3fef411a194205f6e5d26282d9deb8ddb72","source":{"kind":"arxiv","id":"2607.07469","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07469","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07469v1","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07469","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"pith_short_12","alias_value":"UH4VOP5LSB4K","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"pith_short_16","alias_value":"UH4VOP5LSB4KGBVE","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"pith_short_8","alias_value":"UH4VOP5L","created_at":"2026-07-09T01:20:25Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:UH4VOP5LSB4KGBVE7JK27M5T73","target":"record","payload":{"canonical_record":{"source":{"id":"2607.07469","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T14:32:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"99d65d2cfd6d9e08ce552fbc2e3308de300c887ae62a39a41620e84c7debdcfb","abstract_canon_sha256":"09d7f7c75e7ac44d0ff352cb327c51669317d6f0e847be723ee81edb872aa0d8"},"schema_version":"1.0"},"canonical_sha256":"a1f9573fab9078a306a4fa55afb3b3fef411a194205f6e5d26282d9deb8ddb72","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-09T01:20:25.797032Z","signature_b64":"DwpcTqu4YLTf1sOMdm1T/oBi9mCvMR/zodBDqG/PWphhqyfzQAPg9w4rZK1EdGZr0tMoPeJacDZBU9aVszVsCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1f9573fab9078a306a4fa55afb3b3fef411a194205f6e5d26282d9deb8ddb72","last_reissued_at":"2026-07-09T01:20:25.796646Z","signature_status":"signed_v1","first_computed_at":"2026-07-09T01:20:25.796646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.07469","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":"2026-07-09T01:20:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ypSM0mou1ksMTP+BvIGHY6/2s96erYAvl8fFqIZ3P4CmAEgCH7YIqEUWUudWF7ZwyuoteJ30uEYKaRsPRhFhAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:45:20.988303Z"},"content_sha256":"221f11c1333b5be3119f63010809dac5b6990e6cec537b5b995b3d2675cdf2a3","schema_version":"1.0","event_id":"sha256:221f11c1333b5be3119f63010809dac5b6990e6cec537b5b995b3d2675cdf2a3"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:UH4VOP5LSB4KGBVE7JK27M5T73","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Andrea Scarinci, Brayan Impata, Marcello Federico, Suleiman Khan, Victor Martinez, Virginia Negri","submitted_at":"2026-07-08T14:32:28Z","abstract_excerpt":"Fine-tuning large language models (LLMs) for e-commerce attribute extraction requires labeled data representative across thousands of product types, attributes, and multiple languages. This combinatorial scale translates to millions of annotations, rendering human labeling prohibitively costly. While recent work has demonstrated synthetic label generation using LLMs, deploying such approaches at industrial scale requires integrated quality control mechanisms. We present SynthAVE, a large-scale human-validated benchmark for attribute value extraction spanning 12,726 products across 229 product "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07469","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/2607.07469/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":"2026-07-09T01:20:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QRZ5ZPZOlF0g2qlul9ayTipoFOW5IZjTdN5kWUuRLm0/WYMqUbbsohoGS+SZEtqmvzLQ6vM3L198tFvs+z1PAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T15:45:20.989059Z"},"content_sha256":"77a218e3b6932f19c52e8076bcb50da963d22b3de0ed8c969a1da4c394c545de","schema_version":"1.0","event_id":"sha256:77a218e3b6932f19c52e8076bcb50da963d22b3de0ed8c969a1da4c394c545de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UH4VOP5LSB4KGBVE7JK27M5T73/bundle.json","state_url":"https://pith.science/pith/UH4VOP5LSB4KGBVE7JK27M5T73/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UH4VOP5LSB4KGBVE7JK27M5T73/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":"2026-08-19T15:45:20Z","links":{"resolver":"https://pith.science/pith/UH4VOP5LSB4KGBVE7JK27M5T73","bundle":"https://pith.science/pith/UH4VOP5LSB4KGBVE7JK27M5T73/bundle.json","state":"https://pith.science/pith/UH4VOP5LSB4KGBVE7JK27M5T73/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UH4VOP5LSB4KGBVE7JK27M5T73/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UH4VOP5LSB4KGBVE7JK27M5T73","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":"09d7f7c75e7ac44d0ff352cb327c51669317d6f0e847be723ee81edb872aa0d8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T14:32:28Z","title_canon_sha256":"99d65d2cfd6d9e08ce552fbc2e3308de300c887ae62a39a41620e84c7debdcfb"},"schema_version":"1.0","source":{"id":"2607.07469","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.07469","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"arxiv_version","alias_value":"2607.07469v1","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.07469","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"pith_short_12","alias_value":"UH4VOP5LSB4K","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"pith_short_16","alias_value":"UH4VOP5LSB4KGBVE","created_at":"2026-07-09T01:20:25Z"},{"alias_kind":"pith_short_8","alias_value":"UH4VOP5L","created_at":"2026-07-09T01:20:25Z"}],"graph_snapshots":[{"event_id":"sha256:77a218e3b6932f19c52e8076bcb50da963d22b3de0ed8c969a1da4c394c545de","target":"graph","created_at":"2026-07-09T01:20:25Z","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/2607.07469/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Fine-tuning large language models (LLMs) for e-commerce attribute extraction requires labeled data representative across thousands of product types, attributes, and multiple languages. This combinatorial scale translates to millions of annotations, rendering human labeling prohibitively costly. While recent work has demonstrated synthetic label generation using LLMs, deploying such approaches at industrial scale requires integrated quality control mechanisms. We present SynthAVE, a large-scale human-validated benchmark for attribute value extraction spanning 12,726 products across 229 product ","authors_text":"Andrea Scarinci, Brayan Impata, Marcello Federico, Suleiman Khan, Victor Martinez, Virginia Negri","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T14:32:28Z","title":"SynthAVE: Scalable Synthetic Labeling for E-Commerce with LLM-Arena Validation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.07469","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":"sha256:221f11c1333b5be3119f63010809dac5b6990e6cec537b5b995b3d2675cdf2a3","target":"record","created_at":"2026-07-09T01:20:25Z","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":"09d7f7c75e7ac44d0ff352cb327c51669317d6f0e847be723ee81edb872aa0d8","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-07-08T14:32:28Z","title_canon_sha256":"99d65d2cfd6d9e08ce552fbc2e3308de300c887ae62a39a41620e84c7debdcfb"},"schema_version":"1.0","source":{"id":"2607.07469","kind":"arxiv","version":1}},"canonical_sha256":"a1f9573fab9078a306a4fa55afb3b3fef411a194205f6e5d26282d9deb8ddb72","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a1f9573fab9078a306a4fa55afb3b3fef411a194205f6e5d26282d9deb8ddb72","first_computed_at":"2026-07-09T01:20:25.796646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-09T01:20:25.796646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DwpcTqu4YLTf1sOMdm1T/oBi9mCvMR/zodBDqG/PWphhqyfzQAPg9w4rZK1EdGZr0tMoPeJacDZBU9aVszVsCQ==","signature_status":"signed_v1","signed_at":"2026-07-09T01:20:25.797032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.07469","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:221f11c1333b5be3119f63010809dac5b6990e6cec537b5b995b3d2675cdf2a3","sha256:77a218e3b6932f19c52e8076bcb50da963d22b3de0ed8c969a1da4c394c545de"],"state_sha256":"99e1877503e1fd086c18f667c0b7a361b34da3f9e66a3a726015196fb22fbaf8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"u1nXK1d4UX28CTo4ckIj9pPIncCc7qIvRu7I3kEv5uHMmMc/RFg0+yU+uj1nwcjzDStv26hT8ERivgSJIrjgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T15:45:20.993561Z","bundle_sha256":"8b85eabff5ca3a2065cc7617e5131035bdefd8d66a0d842de4d4c42b0bab0bd6"}}