{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5JWW2FJCK5NF4EGM4TBOVTHY2N","short_pith_number":"pith:5JWW2FJC","canonical_record":{"source":{"id":"2607.22949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-24T23:25:16Z","cross_cats_sorted":[],"title_canon_sha256":"d6c683ca6be323d824f041e800d4e388f976648c8129d4d614c1b895e759bfd0","abstract_canon_sha256":"3fb95ca9ec47765b2b027e7bdb3c2e48699407749e4cf82b53e90480f42a0ef5"},"schema_version":"1.0"},"canonical_sha256":"ea6d6d1522575a5e10cce4c2eaccf8d34de787b0fd657e71d7270f81923f2e54","source":{"kind":"arxiv","id":"2607.22949","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22949","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22949v1","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22949","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"5JWW2FJCK5NF","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"5JWW2FJCK5NF4EGM","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"5JWW2FJC","created_at":"2026-07-28T00:22:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5JWW2FJCK5NF4EGM4TBOVTHY2N","target":"record","payload":{"canonical_record":{"source":{"id":"2607.22949","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-24T23:25:16Z","cross_cats_sorted":[],"title_canon_sha256":"d6c683ca6be323d824f041e800d4e388f976648c8129d4d614c1b895e759bfd0","abstract_canon_sha256":"3fb95ca9ec47765b2b027e7bdb3c2e48699407749e4cf82b53e90480f42a0ef5"},"schema_version":"1.0"},"canonical_sha256":"ea6d6d1522575a5e10cce4c2eaccf8d34de787b0fd657e71d7270f81923f2e54","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T00:22:03.726976Z","signature_b64":"R6xoof+Rp37IEVhIDmGknOrEK8fMGXB5ZB7er8ZGCbIwPmWAHG7Ms1Ji+6cFDWywSiQiIxwLevp0KLR9mm54Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ea6d6d1522575a5e10cce4c2eaccf8d34de787b0fd657e71d7270f81923f2e54","last_reissued_at":"2026-07-28T00:22:03.726082Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T00:22:03.726082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.22949","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":"2026-07-28T00:22:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"n02YAv70EKXEitGQ+oFEmaX5BtGQKAiMlTSFZR9lGj5RwjJphWj4GYOa+Avp09tQ8TJkcoWIiKHGn1iYL/zGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T14:24:10.640993Z"},"content_sha256":"c7a0ec063840a4d30ebe236c4fc3945b5510eeaa52826fa4532d21cee7e28a99","schema_version":"1.0","event_id":"sha256:c7a0ec063840a4d30ebe236c4fc3945b5510eeaa52826fa4532d21cee7e28a99"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5JWW2FJCK5NF4EGM4TBOVTHY2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Beyond Exact Match: How Evaluation Methodology Dominates Model Choice in LLM-Based Product Attribute Extraction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Ashvi Soni, Ayush Dwivedi","submitted_at":"2026-07-24T23:25:16Z","abstract_excerpt":"Large language models (LLMs) have become a default choice for structured product attribute extraction in e-commerce pipelines, with practitioners reporting widely varying performance across models, datasets, and prompting strategies. This paper presents a controlled empirical study comparing four prompting strategies -- zero-shot, few-shot, schema-guided, and definition-augmented -- across two production-grade LLMs (GPT-4o-mini and Gemini 2.5 Flash) on the MAVE benchmark. We evaluate 6,400 attribute-level predictions using both exact and fuzzy string matching, and conduct a rigorous noise audi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22949","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/2607.22949/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":"2026-07-28T00:22:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7XnMjNi6dW1LG2SKMY4QWHfC18nMbshnTlB7lEQw1c6cQbR455TRCcbV6YjhXntvL2jwZrWHtk79E9OnJWeWDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T14:24:10.641513Z"},"content_sha256":"56725ec3b4bffb2f5ddbb7b1d1a19ea2cb6fdd74f2edaccd83bc78457d7eb772","schema_version":"1.0","event_id":"sha256:56725ec3b4bffb2f5ddbb7b1d1a19ea2cb6fdd74f2edaccd83bc78457d7eb772"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5JWW2FJCK5NF4EGM4TBOVTHY2N/bundle.json","state_url":"https://pith.science/pith/5JWW2FJCK5NF4EGM4TBOVTHY2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5JWW2FJCK5NF4EGM4TBOVTHY2N/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":"2026-08-01T14:24:10Z","links":{"resolver":"https://pith.science/pith/5JWW2FJCK5NF4EGM4TBOVTHY2N","bundle":"https://pith.science/pith/5JWW2FJCK5NF4EGM4TBOVTHY2N/bundle.json","state":"https://pith.science/pith/5JWW2FJCK5NF4EGM4TBOVTHY2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5JWW2FJCK5NF4EGM4TBOVTHY2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5JWW2FJCK5NF4EGM4TBOVTHY2N","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":"3fb95ca9ec47765b2b027e7bdb3c2e48699407749e4cf82b53e90480f42a0ef5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-24T23:25:16Z","title_canon_sha256":"d6c683ca6be323d824f041e800d4e388f976648c8129d4d614c1b895e759bfd0"},"schema_version":"1.0","source":{"id":"2607.22949","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.22949","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"arxiv_version","alias_value":"2607.22949v1","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.22949","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"pith_short_12","alias_value":"5JWW2FJCK5NF","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"pith_short_16","alias_value":"5JWW2FJCK5NF4EGM","created_at":"2026-07-28T00:22:03Z"},{"alias_kind":"pith_short_8","alias_value":"5JWW2FJC","created_at":"2026-07-28T00:22:03Z"}],"graph_snapshots":[{"event_id":"sha256:56725ec3b4bffb2f5ddbb7b1d1a19ea2cb6fdd74f2edaccd83bc78457d7eb772","target":"graph","created_at":"2026-07-28T00:22:03Z","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/2607.22949/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have become a default choice for structured product attribute extraction in e-commerce pipelines, with practitioners reporting widely varying performance across models, datasets, and prompting strategies. This paper presents a controlled empirical study comparing four prompting strategies -- zero-shot, few-shot, schema-guided, and definition-augmented -- across two production-grade LLMs (GPT-4o-mini and Gemini 2.5 Flash) on the MAVE benchmark. We evaluate 6,400 attribute-level predictions using both exact and fuzzy string matching, and conduct a rigorous noise audi","authors_text":"Ashvi Soni, Ayush Dwivedi","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-24T23:25:16Z","title":"Beyond Exact Match: How Evaluation Methodology Dominates Model Choice in LLM-Based Product Attribute Extraction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.22949","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:c7a0ec063840a4d30ebe236c4fc3945b5510eeaa52826fa4532d21cee7e28a99","target":"record","created_at":"2026-07-28T00:22:03Z","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":"3fb95ca9ec47765b2b027e7bdb3c2e48699407749e4cf82b53e90480f42a0ef5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-07-24T23:25:16Z","title_canon_sha256":"d6c683ca6be323d824f041e800d4e388f976648c8129d4d614c1b895e759bfd0"},"schema_version":"1.0","source":{"id":"2607.22949","kind":"arxiv","version":1}},"canonical_sha256":"ea6d6d1522575a5e10cce4c2eaccf8d34de787b0fd657e71d7270f81923f2e54","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea6d6d1522575a5e10cce4c2eaccf8d34de787b0fd657e71d7270f81923f2e54","first_computed_at":"2026-07-28T00:22:03.726082Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T00:22:03.726082Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R6xoof+Rp37IEVhIDmGknOrEK8fMGXB5ZB7er8ZGCbIwPmWAHG7Ms1Ji+6cFDWywSiQiIxwLevp0KLR9mm54Dw==","signature_status":"signed_v1","signed_at":"2026-07-28T00:22:03.726976Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.22949","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c7a0ec063840a4d30ebe236c4fc3945b5510eeaa52826fa4532d21cee7e28a99","sha256:56725ec3b4bffb2f5ddbb7b1d1a19ea2cb6fdd74f2edaccd83bc78457d7eb772"],"state_sha256":"050d2626ab970a093a84ddd59d3f8ce489e814aabb617d315546a8196dbcd524"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jcmz205hXWUjhujHjTgJ5GJZzhEZQemXeqg0mRfGl14z5Fd5gwfiV1iBJXUldvUuYm1/gHVjo9CVJAPRgVvgAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T14:24:10.647073Z","bundle_sha256":"731c4521df413a5c54fec9577acfb5c54c5d83bec3e743fa49f6173786062d1d"}}