{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:R6TCYVAWSLMSCQPZ7IEWRUGEVX","short_pith_number":"pith:R6TCYVAW","canonical_record":{"source":{"id":"2201.02896","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-08T22:25:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ca3a766069fa9ac724145fbdc40cd57f419f8d487177b8c3ca4fe014616fde63","abstract_canon_sha256":"14f1200eaf1196d43588c66f677056819c699a4022bd8c4e7b432148c31f06c6"},"schema_version":"1.0"},"canonical_sha256":"8fa62c541692d92141f9fa0968d0c4adfb971e0c2520cd21b1d85e21083e9894","source":{"kind":"arxiv","id":"2201.02896","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02896","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02896v1","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02896","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"R6TCYVAWSLMS","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"pith_short_16","alias_value":"R6TCYVAWSLMSCQPZ","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"pith_short_8","alias_value":"R6TCYVAW","created_at":"2026-07-05T03:46:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:R6TCYVAWSLMSCQPZ7IEWRUGEVX","target":"record","payload":{"canonical_record":{"source":{"id":"2201.02896","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-08T22:25:32Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"ca3a766069fa9ac724145fbdc40cd57f419f8d487177b8c3ca4fe014616fde63","abstract_canon_sha256":"14f1200eaf1196d43588c66f677056819c699a4022bd8c4e7b432148c31f06c6"},"schema_version":"1.0"},"canonical_sha256":"8fa62c541692d92141f9fa0968d0c4adfb971e0c2520cd21b1d85e21083e9894","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:46:49.781687Z","signature_b64":"nMbdGZytScHLEuUmU7BadbtnpoHz0kRLSxJZ8jB0audxAZG2qUWtbUY3yicbWsc+pkeu0guB0MIplnePEoDzAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fa62c541692d92141f9fa0968d0c4adfb971e0c2520cd21b1d85e21083e9894","last_reissued_at":"2026-07-05T03:46:49.781266Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:46:49.781266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2201.02896","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":"2026-07-05T03:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2xKvPN63E6jZlr/6VECGCr0bXmY61j6jac5arn13CC3PdV9NfigWKhxpr+h6uV2JEQFmSK9NjBkI8QT6Pq1iCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:52:16.376415Z"},"content_sha256":"6018ffe0dd28a59fb31f0a87e5b3a10494c1b7e5f8c65e5c38661db1c520d9ba","schema_version":"1.0","event_id":"sha256:6018ffe0dd28a59fb31f0a87e5b3a10494c1b7e5f8c65e5c38661db1c520d9ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:R6TCYVAWSLMSCQPZ7IEWRUGEVX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Extraction of Product Specifications from the Web -- Going Beyond Tables and Lists","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Ashish Kulkarni, Govind Krishnan Gangadhar","submitted_at":"2022-01-08T22:25:32Z","abstract_excerpt":"E-commerce product pages on the web often present product specification data in structured tabular blocks. Extraction of these product attribute-value specifications has benefited applications like product catalogue curation, search, question answering, and others. However, across different Websites, there is a wide variety of HTML elements (like <table>, <ul>, <div>, <span>, <dl> etc.) typically used to render these blocks that makes their automatic extraction a challenge. Most of the current research has focused on extracting product specifications from tables and lists and, therefore, suffe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02896","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/2201.02896/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":"2026-07-05T03:46:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFQCc/oJm1E1gEbUErfOJXBo9KV6IW+v8E/JZOmyRfgmqL7u7k1Q0150ufQgDnvipoai3mSii3P0jHrKfSDzAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:52:16.376790Z"},"content_sha256":"5c706fb7275221cfd101a2c42b31f9a3339c74d7e25021c7462283c6b52db341","schema_version":"1.0","event_id":"sha256:5c706fb7275221cfd101a2c42b31f9a3339c74d7e25021c7462283c6b52db341"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/bundle.json","state_url":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/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":"2026-07-06T14:52:16Z","links":{"resolver":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX","bundle":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/bundle.json","state":"https://pith.science/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/R6TCYVAWSLMSCQPZ7IEWRUGEVX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:R6TCYVAWSLMSCQPZ7IEWRUGEVX","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":"14f1200eaf1196d43588c66f677056819c699a4022bd8c4e7b432148c31f06c6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-08T22:25:32Z","title_canon_sha256":"ca3a766069fa9ac724145fbdc40cd57f419f8d487177b8c3ca4fe014616fde63"},"schema_version":"1.0","source":{"id":"2201.02896","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2201.02896","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"arxiv_version","alias_value":"2201.02896v1","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.02896","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"pith_short_12","alias_value":"R6TCYVAWSLMS","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"pith_short_16","alias_value":"R6TCYVAWSLMSCQPZ","created_at":"2026-07-05T03:46:49Z"},{"alias_kind":"pith_short_8","alias_value":"R6TCYVAW","created_at":"2026-07-05T03:46:49Z"}],"graph_snapshots":[{"event_id":"sha256:5c706fb7275221cfd101a2c42b31f9a3339c74d7e25021c7462283c6b52db341","target":"graph","created_at":"2026-07-05T03:46:49Z","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/2201.02896/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"E-commerce product pages on the web often present product specification data in structured tabular blocks. Extraction of these product attribute-value specifications has benefited applications like product catalogue curation, search, question answering, and others. However, across different Websites, there is a wide variety of HTML elements (like <table>, <ul>, <div>, <span>, <dl> etc.) typically used to render these blocks that makes their automatic extraction a challenge. Most of the current research has focused on extracting product specifications from tables and lists and, therefore, suffe","authors_text":"Ashish Kulkarni, Govind Krishnan Gangadhar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-08T22:25:32Z","title":"Extraction of Product Specifications from the Web -- Going Beyond Tables and Lists"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.02896","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":"sha256:6018ffe0dd28a59fb31f0a87e5b3a10494c1b7e5f8c65e5c38661db1c520d9ba","target":"record","created_at":"2026-07-05T03:46:49Z","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":"14f1200eaf1196d43588c66f677056819c699a4022bd8c4e7b432148c31f06c6","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2022-01-08T22:25:32Z","title_canon_sha256":"ca3a766069fa9ac724145fbdc40cd57f419f8d487177b8c3ca4fe014616fde63"},"schema_version":"1.0","source":{"id":"2201.02896","kind":"arxiv","version":1}},"canonical_sha256":"8fa62c541692d92141f9fa0968d0c4adfb971e0c2520cd21b1d85e21083e9894","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8fa62c541692d92141f9fa0968d0c4adfb971e0c2520cd21b1d85e21083e9894","first_computed_at":"2026-07-05T03:46:49.781266Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:46:49.781266Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nMbdGZytScHLEuUmU7BadbtnpoHz0kRLSxJZ8jB0audxAZG2qUWtbUY3yicbWsc+pkeu0guB0MIplnePEoDzAw==","signature_status":"signed_v1","signed_at":"2026-07-05T03:46:49.781687Z","signed_message":"canonical_sha256_bytes"},"source_id":"2201.02896","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6018ffe0dd28a59fb31f0a87e5b3a10494c1b7e5f8c65e5c38661db1c520d9ba","sha256:5c706fb7275221cfd101a2c42b31f9a3339c74d7e25021c7462283c6b52db341"],"state_sha256":"ce5b82a01a1010ad3a269d92ec4dace24b9961e49ca048199e915b4f27e587f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ez8DP8U7oOjtU6DxQiY1wdTDUpEoKDRVPQ2Fzb2mOI1uwvXjBAlUHnezLubE8T9mS1jtJmULr7u98fZ2c/J3Aw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T14:52:16.378766Z","bundle_sha256":"5008bb3aea771559613462fee7eccc6c77ffdd155c63c4ff931410b5b8b325d6"}}