{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:LOXGXCFGDS5X6EVBL6TZCQUG3B","short_pith_number":"pith:LOXGXCFG","canonical_record":{"source":{"id":"2310.16303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T02:22:50Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"6f40fea6188d65d4ff12c2ea64aeb880264799e0dc7cff05fcf72f4765e80046","abstract_canon_sha256":"5c848bc7d5f798b805373812fe163a8eb4f17127b6f821dee00627a4cce6f320"},"schema_version":"1.0"},"canonical_sha256":"5bae6b88a61cbb7f12a15fa7914286d85e03ba3df1899b4b48464d58b0a643a6","source":{"kind":"arxiv","id":"2310.16303","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16303","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16303v1","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16303","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"LOXGXCFGDS5X","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"LOXGXCFGDS5X6EVB","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"LOXGXCFG","created_at":"2026-07-05T07:04:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:LOXGXCFGDS5X6EVBL6TZCQUG3B","target":"record","payload":{"canonical_record":{"source":{"id":"2310.16303","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T02:22:50Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"6f40fea6188d65d4ff12c2ea64aeb880264799e0dc7cff05fcf72f4765e80046","abstract_canon_sha256":"5c848bc7d5f798b805373812fe163a8eb4f17127b6f821dee00627a4cce6f320"},"schema_version":"1.0"},"canonical_sha256":"5bae6b88a61cbb7f12a15fa7914286d85e03ba3df1899b4b48464d58b0a643a6","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:04:55.382993Z","signature_b64":"FbEW/kcOCh+AC9LM6aNM5ADdayTg/M9mnusNlUqKW6noUe7JALvgH2Um4tIxuehU104F5M/KVaibAxlRj0lfBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5bae6b88a61cbb7f12a15fa7914286d85e03ba3df1899b4b48464d58b0a643a6","last_reissued_at":"2026-07-05T07:04:55.382566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:04:55.382566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2310.16303","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":"2026-07-05T07:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1XMEh+2Qb/jLE3MFHxWUix//6KVC9TlGjzCo46KcxjKn+fCXd2QfV7bLCpGGUv+KBXgFOeIDSeNLzma9Q+yfAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T19:32:55.176910Z"},"content_sha256":"24eef64dd2aee7c7356555a34437ace71f4a9561adc89ae4cb683832ea133061","schema_version":"1.0","event_id":"sha256:24eef64dd2aee7c7356555a34437ace71f4a9561adc89ae4cb683832ea133061"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:LOXGXCFGDS5X6EVBL6TZCQUG3B","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"URL-BERT: Training Webpage Representations via Social Media Engagements","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Ahmed El-Kishky, Ayesha Qamar, Chetan Verma, Sneha Mehta, Sumit Binnani, Taylor Berg-Kirkpatrick","submitted_at":"2023-10-25T02:22:50Z","abstract_excerpt":"Understanding and representing webpages is crucial to online social networks where users may share and engage with URLs. Common language model (LM) encoders such as BERT can be used to understand and represent the textual content of webpages. However, these representations may not model thematic information of web domains and URLs or accurately capture their appeal to social media users. In this work, we introduce a new pre-training objective that can be used to adapt LMs to understand URLs and webpages. Our proposed framework consists of two steps: (1) scalable graph embeddings to learn shall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16303","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/2310.16303/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":"2026-07-05T07:04:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zgoFhzUvG+FZwat/LYcxoqz0peR07r9gP3gLsAKT3dsuBUKDp62xaTsctDMGvKbyPkmQGVNKcwHfYdnmMIo+AQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-15T19:32:55.177285Z"},"content_sha256":"ab633454ca25d4a5b32aebc08f4866edb2ccdd4ca70c784df000c1e8422c0ec0","schema_version":"1.0","event_id":"sha256:ab633454ca25d4a5b32aebc08f4866edb2ccdd4ca70c784df000c1e8422c0ec0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LOXGXCFGDS5X6EVBL6TZCQUG3B/bundle.json","state_url":"https://pith.science/pith/LOXGXCFGDS5X6EVBL6TZCQUG3B/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LOXGXCFGDS5X6EVBL6TZCQUG3B/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":"2026-07-15T19:32:55Z","links":{"resolver":"https://pith.science/pith/LOXGXCFGDS5X6EVBL6TZCQUG3B","bundle":"https://pith.science/pith/LOXGXCFGDS5X6EVBL6TZCQUG3B/bundle.json","state":"https://pith.science/pith/LOXGXCFGDS5X6EVBL6TZCQUG3B/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LOXGXCFGDS5X6EVBL6TZCQUG3B/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LOXGXCFGDS5X6EVBL6TZCQUG3B","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":"5c848bc7d5f798b805373812fe163a8eb4f17127b6f821dee00627a4cce6f320","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T02:22:50Z","title_canon_sha256":"6f40fea6188d65d4ff12c2ea64aeb880264799e0dc7cff05fcf72f4765e80046"},"schema_version":"1.0","source":{"id":"2310.16303","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.16303","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"arxiv_version","alias_value":"2310.16303v1","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.16303","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"pith_short_12","alias_value":"LOXGXCFGDS5X","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"pith_short_16","alias_value":"LOXGXCFGDS5X6EVB","created_at":"2026-07-05T07:04:55Z"},{"alias_kind":"pith_short_8","alias_value":"LOXGXCFG","created_at":"2026-07-05T07:04:55Z"}],"graph_snapshots":[{"event_id":"sha256:ab633454ca25d4a5b32aebc08f4866edb2ccdd4ca70c784df000c1e8422c0ec0","target":"graph","created_at":"2026-07-05T07:04:55Z","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/2310.16303/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Understanding and representing webpages is crucial to online social networks where users may share and engage with URLs. Common language model (LM) encoders such as BERT can be used to understand and represent the textual content of webpages. However, these representations may not model thematic information of web domains and URLs or accurately capture their appeal to social media users. In this work, we introduce a new pre-training objective that can be used to adapt LMs to understand URLs and webpages. Our proposed framework consists of two steps: (1) scalable graph embeddings to learn shall","authors_text":"Ahmed El-Kishky, Ayesha Qamar, Chetan Verma, Sneha Mehta, Sumit Binnani, Taylor Berg-Kirkpatrick","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T02:22:50Z","title":"URL-BERT: Training Webpage Representations via Social Media Engagements"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.16303","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":"sha256:24eef64dd2aee7c7356555a34437ace71f4a9561adc89ae4cb683832ea133061","target":"record","created_at":"2026-07-05T07:04:55Z","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":"5c848bc7d5f798b805373812fe163a8eb4f17127b6f821dee00627a4cce6f320","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-25T02:22:50Z","title_canon_sha256":"6f40fea6188d65d4ff12c2ea64aeb880264799e0dc7cff05fcf72f4765e80046"},"schema_version":"1.0","source":{"id":"2310.16303","kind":"arxiv","version":1}},"canonical_sha256":"5bae6b88a61cbb7f12a15fa7914286d85e03ba3df1899b4b48464d58b0a643a6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5bae6b88a61cbb7f12a15fa7914286d85e03ba3df1899b4b48464d58b0a643a6","first_computed_at":"2026-07-05T07:04:55.382566Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:04:55.382566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FbEW/kcOCh+AC9LM6aNM5ADdayTg/M9mnusNlUqKW6noUe7JALvgH2Um4tIxuehU104F5M/KVaibAxlRj0lfBg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:04:55.382993Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.16303","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:24eef64dd2aee7c7356555a34437ace71f4a9561adc89ae4cb683832ea133061","sha256:ab633454ca25d4a5b32aebc08f4866edb2ccdd4ca70c784df000c1e8422c0ec0"],"state_sha256":"bc8a2c0466db5bab76f28b55487ef9e270d34a1575506769f9b5fc0f0cb08bdf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fLvMC8C3JpdkL9kaRjMzcA33fPlogyNRpjtzKxsaq6BjEzdSUYQ4RoljmZlRZ/ogaNkovTZ9cZRiSk4ew7t9CA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-15T19:32:55.179531Z","bundle_sha256":"3340f8c7541a2495e3f34aa68b1ee45cdc997e6de7df493d511d758b4328be81"}}