{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:TGTQHB3FG4NX5Q237THYR2IAF2","short_pith_number":"pith:TGTQHB3F","canonical_record":{"source":{"id":"2112.03103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T10:35:02Z","cross_cats_sorted":[],"title_canon_sha256":"55e8e714e21be4992c449eb4071e9489e36bca54fbd47456c049796452c245bd","abstract_canon_sha256":"1f5d5e908b64813f796b6a309bc43adeaf740c719a8048f042c987943565f125"},"schema_version":"1.0"},"canonical_sha256":"99a7038765371b7ec35bfccf88e9002ebd244e45572c2823273cbd6f20d99c39","source":{"kind":"arxiv","id":"2112.03103","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03103","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03103v1","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03103","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_12","alias_value":"TGTQHB3FG4NX","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_16","alias_value":"TGTQHB3FG4NX5Q23","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_8","alias_value":"TGTQHB3F","created_at":"2026-07-05T03:38:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:TGTQHB3FG4NX5Q237THYR2IAF2","target":"record","payload":{"canonical_record":{"source":{"id":"2112.03103","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T10:35:02Z","cross_cats_sorted":[],"title_canon_sha256":"55e8e714e21be4992c449eb4071e9489e36bca54fbd47456c049796452c245bd","abstract_canon_sha256":"1f5d5e908b64813f796b6a309bc43adeaf740c719a8048f042c987943565f125"},"schema_version":"1.0"},"canonical_sha256":"99a7038765371b7ec35bfccf88e9002ebd244e45572c2823273cbd6f20d99c39","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:38:02.052173Z","signature_b64":"v6a0av347ngSaEttThyYN2WT9fLvxDhvrvRcq2c89UsZmhruzdk8e0XwWfVDQ7eFxfd9QZNNBFKgeTN+tSk/Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99a7038765371b7ec35bfccf88e9002ebd244e45572c2823273cbd6f20d99c39","last_reissued_at":"2026-07-05T03:38:02.051653Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:38:02.051653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2112.03103","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":"2026-07-05T03:38:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/pP9zmhJrJbupVxr2hNbPQODob1eSY6LUcO2DHEXJdSC8iQrcl+nV2F7JHlFxTqFHCBe548iEizyboY2QldGBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T04:47:35.150429Z"},"content_sha256":"06b9ce42a6aedcf8eb9f078845b9b36de74aece351a2eee3492c9f8790e76d89","schema_version":"1.0","event_id":"sha256:06b9ce42a6aedcf8eb9f078845b9b36de74aece351a2eee3492c9f8790e76d89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:TGTQHB3FG4NX5Q237THYR2IAF2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FastWARC: Optimizing Large-Scale Web Archive Analytics","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Benno Stein, Janek Bevendorff, Martin Potthast","submitted_at":"2021-11-22T10:35:02Z","abstract_excerpt":"Web search and other large-scale web data analytics rely on processing archives of web pages stored in a standardized and efficient format. Since its introduction in 2008, the IIPC's Web ARCive (WARC) format has become the standard format for this purpose. As a list of individually compressed records of HTTP requests and responses, it allows for constant-time random access to all kinds of web data via off-the-shelf open source parsers in many programming languages, such as WARCIO, the de-facto standard for Python. When processing web archives at the terabyte or petabyte scale, however, even sm"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03103","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/2112.03103/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":"2026-07-05T03:38:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"epMO9s5pwdy1WRi8VDsBvyq8I7gQzVXBtqjojkZUyRD7xw7S1eg9YqgqeBzymXEq5gbdIeXsMAT4oUCsIskWDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-25T04:47:35.150814Z"},"content_sha256":"12371fd397825550c6c4cb9d912b8be1e3abe6198028f81f5328be348ed917bf","schema_version":"1.0","event_id":"sha256:12371fd397825550c6c4cb9d912b8be1e3abe6198028f81f5328be348ed917bf"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TGTQHB3FG4NX5Q237THYR2IAF2/bundle.json","state_url":"https://pith.science/pith/TGTQHB3FG4NX5Q237THYR2IAF2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TGTQHB3FG4NX5Q237THYR2IAF2/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":"2026-07-25T04:47:35Z","links":{"resolver":"https://pith.science/pith/TGTQHB3FG4NX5Q237THYR2IAF2","bundle":"https://pith.science/pith/TGTQHB3FG4NX5Q237THYR2IAF2/bundle.json","state":"https://pith.science/pith/TGTQHB3FG4NX5Q237THYR2IAF2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TGTQHB3FG4NX5Q237THYR2IAF2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:TGTQHB3FG4NX5Q237THYR2IAF2","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":"1f5d5e908b64813f796b6a309bc43adeaf740c719a8048f042c987943565f125","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T10:35:02Z","title_canon_sha256":"55e8e714e21be4992c449eb4071e9489e36bca54fbd47456c049796452c245bd"},"schema_version":"1.0","source":{"id":"2112.03103","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2112.03103","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"arxiv_version","alias_value":"2112.03103v1","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2112.03103","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_12","alias_value":"TGTQHB3FG4NX","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_16","alias_value":"TGTQHB3FG4NX5Q23","created_at":"2026-07-05T03:38:02Z"},{"alias_kind":"pith_short_8","alias_value":"TGTQHB3F","created_at":"2026-07-05T03:38:02Z"}],"graph_snapshots":[{"event_id":"sha256:12371fd397825550c6c4cb9d912b8be1e3abe6198028f81f5328be348ed917bf","target":"graph","created_at":"2026-07-05T03:38:02Z","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/2112.03103/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Web search and other large-scale web data analytics rely on processing archives of web pages stored in a standardized and efficient format. Since its introduction in 2008, the IIPC's Web ARCive (WARC) format has become the standard format for this purpose. As a list of individually compressed records of HTTP requests and responses, it allows for constant-time random access to all kinds of web data via off-the-shelf open source parsers in many programming languages, such as WARCIO, the de-facto standard for Python. When processing web archives at the terabyte or petabyte scale, however, even sm","authors_text":"Benno Stein, Janek Bevendorff, Martin Potthast","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T10:35:02Z","title":"FastWARC: Optimizing Large-Scale Web Archive Analytics"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2112.03103","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":"sha256:06b9ce42a6aedcf8eb9f078845b9b36de74aece351a2eee3492c9f8790e76d89","target":"record","created_at":"2026-07-05T03:38:02Z","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":"1f5d5e908b64813f796b6a309bc43adeaf740c719a8048f042c987943565f125","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2021-11-22T10:35:02Z","title_canon_sha256":"55e8e714e21be4992c449eb4071e9489e36bca54fbd47456c049796452c245bd"},"schema_version":"1.0","source":{"id":"2112.03103","kind":"arxiv","version":1}},"canonical_sha256":"99a7038765371b7ec35bfccf88e9002ebd244e45572c2823273cbd6f20d99c39","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99a7038765371b7ec35bfccf88e9002ebd244e45572c2823273cbd6f20d99c39","first_computed_at":"2026-07-05T03:38:02.051653Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:38:02.051653Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"v6a0av347ngSaEttThyYN2WT9fLvxDhvrvRcq2c89UsZmhruzdk8e0XwWfVDQ7eFxfd9QZNNBFKgeTN+tSk/Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:38:02.052173Z","signed_message":"canonical_sha256_bytes"},"source_id":"2112.03103","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:06b9ce42a6aedcf8eb9f078845b9b36de74aece351a2eee3492c9f8790e76d89","sha256:12371fd397825550c6c4cb9d912b8be1e3abe6198028f81f5328be348ed917bf"],"state_sha256":"51df13a423462320b1431552770a1d5c8b26a988ce62a45116d29729c392c50a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3csHdzo68y3QYXIpdEs/Ol9JQcxzf5VcD/Mqrk8ria2k+kLkjTV9+e/r9qXa+ff+9t3UHnhRCzInL5piFfkoCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-25T04:47:35.152917Z","bundle_sha256":"297e4f1d5f97c363832dbf28538d45e5fc0171f55ffa55d948e18c7d5ff882de"}}