{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WYJD7XE5WMYXPEDFOIWN3SJQGE","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":"88e1ea1165de64458c9ac108acb0106a63bbcc469c3dd04dfef3f23ecc44e63b","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T04:20:13Z","title_canon_sha256":"aa7a9093382424d4f40c5478347d799cf556e8c96e4e0b152c24d34113e53f8a"},"schema_version":"1.0","source":{"id":"2010.10755","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.10755","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"arxiv_version","alias_value":"2010.10755v1","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.10755","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"pith_short_12","alias_value":"WYJD7XE5WMYX","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"pith_short_16","alias_value":"WYJD7XE5WMYXPEDF","created_at":"2026-07-05T01:44:54Z"},{"alias_kind":"pith_short_8","alias_value":"WYJD7XE5","created_at":"2026-07-05T01:44:54Z"}],"graph_snapshots":[{"event_id":"sha256:6eaa2927c0bf75fb6577f94c7bba05e063ec1eafdf0f453d34fc3318e2bb5f34","target":"graph","created_at":"2026-07-05T01:44:54Z","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/2010.10755/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Extracting structured data from HTML documents is a long-studied problem with a broad range of applications like augmenting knowledge bases, supporting faceted search, and providing domain-specific experiences for key verticals like shopping and movies. Previous approaches have either required a small number of examples for each target site or relied on carefully handcrafted heuristics built over visual renderings of websites. In this paper, we present a novel two-stage neural approach, named FreeDOM, which overcomes both these limitations. The first stage learns a representation for each DOM ","authors_text":"Bill Yuchen Lin, Nguyen Vo, Sandeep Tata, Ying Sheng","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T04:20:13Z","title":"FreeDOM: A Transferable Neural Architecture for Structured Information Extraction on Web Documents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.10755","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:e8eb5e5d5f627867433230847b237047549bbab9ff28aa817fa8ebff6983e5c8","target":"record","created_at":"2026-07-05T01:44:54Z","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":"88e1ea1165de64458c9ac108acb0106a63bbcc469c3dd04dfef3f23ecc44e63b","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-21T04:20:13Z","title_canon_sha256":"aa7a9093382424d4f40c5478347d799cf556e8c96e4e0b152c24d34113e53f8a"},"schema_version":"1.0","source":{"id":"2010.10755","kind":"arxiv","version":1}},"canonical_sha256":"b6123fdc9db331779065722cddc93031330ecdfe949451312f5aab181139ecf1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6123fdc9db331779065722cddc93031330ecdfe949451312f5aab181139ecf1","first_computed_at":"2026-07-05T01:44:54.206308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:44:54.206308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"u5e4tem0Yeo71NmLLdc16nDKpvO3TFlwESnYg+RlB8iXHo67Q7OFfGAC3trREI2rFsXDz+e2yamp/0+dRzHhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:44:54.206801Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.10755","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e8eb5e5d5f627867433230847b237047549bbab9ff28aa817fa8ebff6983e5c8","sha256:6eaa2927c0bf75fb6577f94c7bba05e063ec1eafdf0f453d34fc3318e2bb5f34"],"state_sha256":"7a500bed713774a39e8d803fb24eb68dd93c9815221a464c79f05100cab14e63"}