{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:MVP7HGIKRAC7NDHU63UB4R67MI","short_pith_number":"pith:MVP7HGIK","canonical_record":{"source":{"id":"2108.11948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-26T17:58:51Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c7ed2b89ad5f576d2280e9a07e112bb0184c1f217b60af97577d5b8baad4f9f9","abstract_canon_sha256":"fb161caedf5946640711157256febef92c77cd169b22619cc65f502dd3323534"},"schema_version":"1.0"},"canonical_sha256":"655ff3990a8805f68cf4f6e81e47df622047f1bce34414ab65ba45bed233c54d","source":{"kind":"arxiv","id":"2108.11948","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.11948","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"2108.11948v1","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11948","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"MVP7HGIKRAC7","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"pith_short_16","alias_value":"MVP7HGIKRAC7NDHU","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"pith_short_8","alias_value":"MVP7HGIK","created_at":"2026-07-05T03:09:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:MVP7HGIKRAC7NDHU63UB4R67MI","target":"record","payload":{"canonical_record":{"source":{"id":"2108.11948","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-26T17:58:51Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"c7ed2b89ad5f576d2280e9a07e112bb0184c1f217b60af97577d5b8baad4f9f9","abstract_canon_sha256":"fb161caedf5946640711157256febef92c77cd169b22619cc65f502dd3323534"},"schema_version":"1.0"},"canonical_sha256":"655ff3990a8805f68cf4f6e81e47df622047f1bce34414ab65ba45bed233c54d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:11.254873Z","signature_b64":"4CgHvIYJOTNpI2D63WNuZudbG/mIYNDZQduR2wbsnZd6yVtm7RbdfpWNOeuilyVmpqbyJe7SCl4hS1vch8LLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"655ff3990a8805f68cf4f6e81e47df622047f1bce34414ab65ba45bed233c54d","last_reissued_at":"2026-07-05T03:09:11.254461Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:11.254461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2108.11948","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":"2026-07-05T03:09:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/wrEfW9M2V59b3EfkFoXA8jqK7cE/oHB3aTyTibDeo7KivubUlxWAi3Ap7JaAKlIih5X1QRwyosX/sMXkFqIBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:06:45.955765Z"},"content_sha256":"c449f44d7073c2548a44b1437b5561050e8291c7bf46d2017fd52816e6f97b58","schema_version":"1.0","event_id":"sha256:c449f44d7073c2548a44b1437b5561050e8291c7bf46d2017fd52816e6f97b58"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:MVP7HGIKRAC7NDHU63UB4R67MI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SAUCE: Truncated Sparse Document Signature Bit-Vectors for Fast Web-Scale Corpus Expansion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Alfredo Alba, Anna Lisa Gentile, Chad DeLuca, Daniel Gruhl, Ismini Lourentzou, Muntasir Wahed, Petar Ristoski, Steve Welch","submitted_at":"2021-08-26T17:58:51Z","abstract_excerpt":"Recent advances in text representation have shown that training on large amounts of text is crucial for natural language understanding. However, models trained without predefined notions of topical interest typically require careful fine-tuning when transferred to specialized domains. When a sufficient amount of within-domain text may not be available, expanding a seed corpus of relevant documents from large-scale web data poses several challenges. First, corpus expansion requires scoring and ranking each document in the collection, an operation that can quickly become computationally expensiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11948","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/2108.11948/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":"2026-07-05T03:09:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OLGkjT0DfkQB2EtrcZ3sQaijxQiNAJtCiXgEgSFf1y3E0mn8MnM+Vj+guy7me3cqmHTn2e1on6zFujkaRhr+BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:06:45.956348Z"},"content_sha256":"22d81f92eab7fb6884313fc683dc4d77dbf1cb261e6cc1dbb70688604489b074","schema_version":"1.0","event_id":"sha256:22d81f92eab7fb6884313fc683dc4d77dbf1cb261e6cc1dbb70688604489b074"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MVP7HGIKRAC7NDHU63UB4R67MI/bundle.json","state_url":"https://pith.science/pith/MVP7HGIKRAC7NDHU63UB4R67MI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MVP7HGIKRAC7NDHU63UB4R67MI/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":"2026-08-03T17:06:45Z","links":{"resolver":"https://pith.science/pith/MVP7HGIKRAC7NDHU63UB4R67MI","bundle":"https://pith.science/pith/MVP7HGIKRAC7NDHU63UB4R67MI/bundle.json","state":"https://pith.science/pith/MVP7HGIKRAC7NDHU63UB4R67MI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MVP7HGIKRAC7NDHU63UB4R67MI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:MVP7HGIKRAC7NDHU63UB4R67MI","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":"fb161caedf5946640711157256febef92c77cd169b22619cc65f502dd3323534","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-26T17:58:51Z","title_canon_sha256":"c7ed2b89ad5f576d2280e9a07e112bb0184c1f217b60af97577d5b8baad4f9f9"},"schema_version":"1.0","source":{"id":"2108.11948","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.11948","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"arxiv_version","alias_value":"2108.11948v1","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.11948","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"pith_short_12","alias_value":"MVP7HGIKRAC7","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"pith_short_16","alias_value":"MVP7HGIKRAC7NDHU","created_at":"2026-07-05T03:09:11Z"},{"alias_kind":"pith_short_8","alias_value":"MVP7HGIK","created_at":"2026-07-05T03:09:11Z"}],"graph_snapshots":[{"event_id":"sha256:22d81f92eab7fb6884313fc683dc4d77dbf1cb261e6cc1dbb70688604489b074","target":"graph","created_at":"2026-07-05T03:09:11Z","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/2108.11948/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in text representation have shown that training on large amounts of text is crucial for natural language understanding. However, models trained without predefined notions of topical interest typically require careful fine-tuning when transferred to specialized domains. When a sufficient amount of within-domain text may not be available, expanding a seed corpus of relevant documents from large-scale web data poses several challenges. First, corpus expansion requires scoring and ranking each document in the collection, an operation that can quickly become computationally expensiv","authors_text":"Alfredo Alba, Anna Lisa Gentile, Chad DeLuca, Daniel Gruhl, Ismini Lourentzou, Muntasir Wahed, Petar Ristoski, Steve Welch","cross_cats":["cs.IR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-26T17:58:51Z","title":"SAUCE: Truncated Sparse Document Signature Bit-Vectors for Fast Web-Scale Corpus Expansion"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.11948","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:c449f44d7073c2548a44b1437b5561050e8291c7bf46d2017fd52816e6f97b58","target":"record","created_at":"2026-07-05T03:09:11Z","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":"fb161caedf5946640711157256febef92c77cd169b22619cc65f502dd3323534","cross_cats_sorted":["cs.IR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-08-26T17:58:51Z","title_canon_sha256":"c7ed2b89ad5f576d2280e9a07e112bb0184c1f217b60af97577d5b8baad4f9f9"},"schema_version":"1.0","source":{"id":"2108.11948","kind":"arxiv","version":1}},"canonical_sha256":"655ff3990a8805f68cf4f6e81e47df622047f1bce34414ab65ba45bed233c54d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"655ff3990a8805f68cf4f6e81e47df622047f1bce34414ab65ba45bed233c54d","first_computed_at":"2026-07-05T03:09:11.254461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:09:11.254461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4CgHvIYJOTNpI2D63WNuZudbG/mIYNDZQduR2wbsnZd6yVtm7RbdfpWNOeuilyVmpqbyJe7SCl4hS1vch8LLAg==","signature_status":"signed_v1","signed_at":"2026-07-05T03:09:11.254873Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.11948","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c449f44d7073c2548a44b1437b5561050e8291c7bf46d2017fd52816e6f97b58","sha256:22d81f92eab7fb6884313fc683dc4d77dbf1cb261e6cc1dbb70688604489b074"],"state_sha256":"ea610c4ec9a11bbf4b23e653f1f4638f0ef263e2350010f3339c0659ae7f94fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X9IrL7Ex0DAabIQNOoJa8mg06nlc1avJ7UGUH+RkUySZSemdNCiUEUPabHtsUJzKFpiSA9sf9px6tsRcqVFRAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:06:45.961211Z","bundle_sha256":"f6b608a2d71947b3185c89a494469b7baa1b9faa8fcaec0d842999c896d76433"}}