{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:353AC4SAVWJPPHO2LBYJC5BTZ7","short_pith_number":"pith:353AC4SA","canonical_record":{"source":{"id":"1910.02655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-07T07:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"4e963d4d515ed101edcaeeaf5da48e8a256b7a0783f372accc4776ede3966370","abstract_canon_sha256":"23bd18d1e8181f7b4ec67ced8bbcef345e92cec36ae2218638d1decbde646fad"},"schema_version":"1.0"},"canonical_sha256":"df76017240ad92f79dda5870917433cfcd4e14005b5ba0c7d350fa36c14c2d8e","source":{"kind":"arxiv","id":"1910.02655","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.02655","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"1910.02655v1","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02655","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"353AC4SAVWJP","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"353AC4SAVWJPPHO2","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"353AC4SA","created_at":"2026-07-05T00:10:10Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:353AC4SAVWJPPHO2LBYJC5BTZ7","target":"record","payload":{"canonical_record":{"source":{"id":"1910.02655","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-07T07:58:26Z","cross_cats_sorted":[],"title_canon_sha256":"4e963d4d515ed101edcaeeaf5da48e8a256b7a0783f372accc4776ede3966370","abstract_canon_sha256":"23bd18d1e8181f7b4ec67ced8bbcef345e92cec36ae2218638d1decbde646fad"},"schema_version":"1.0"},"canonical_sha256":"df76017240ad92f79dda5870917433cfcd4e14005b5ba0c7d350fa36c14c2d8e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:10:10.191160Z","signature_b64":"gGWAwZ3qw4BsDLFDxExftoHm8ftZ3KPcpmwATuvOxguVvWp6i1sdnwMC83CNL2lwpeUd7MS6pCJnP3ZDaFZkCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"df76017240ad92f79dda5870917433cfcd4e14005b5ba0c7d350fa36c14c2d8e","last_reissued_at":"2026-07-05T00:10:10.190751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:10:10.190751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1910.02655","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":"2026-07-05T00:10:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PH5clEjlsdNYCzppOWm2EqBTway7uCVFE1KB0fI42QrV3iQKm4mx4KYwxSydqqXEQuwFKsMxwZrNX5Ry9gf/Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:04:38.035199Z"},"content_sha256":"789d063a6a3e552a03c1937c4e2238785188c11f8133739b073218b1909e7b80","schema_version":"1.0","event_id":"sha256:789d063a6a3e552a03c1937c4e2238785188c11f8133739b073218b1909e7b80"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:353AC4SAVWJPPHO2LBYJC5BTZ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BERT for Evidence Retrieval and Claim Verification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amir Soleimani, Christof Monz, Marcel Worring","submitted_at":"2019-10-07T07:58:26Z","abstract_excerpt":"Motivated by the promising performance of pre-trained language models, we investigate BERT in an evidence retrieval and claim verification pipeline for the FEVER fact extraction and verification challenge. To this end, we propose to use two BERT models, one for retrieving potential evidence sentences supporting or rejecting claims, and another for verifying claims based on the predicted evidence sets. To train the BERT retrieval system, we use pointwise and pairwise loss functions, and examine the effect of hard negative mining. A second BERT model is trained to classify the samples as support"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02655","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/1910.02655/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":"2026-07-05T00:10:10Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K8mlAbbACACEeNk/UjTXELuyfQd0yKBWDgF7W+KgMbdFcmK6ryUr+bI5iTqLUZtOolTxaLG6NFmyOclgdhS3BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T05:04:38.036168Z"},"content_sha256":"ce37d2e82696cd5e12f17e6de0215643193bbe1dc89d3f2a10768329bbf0eebc","schema_version":"1.0","event_id":"sha256:ce37d2e82696cd5e12f17e6de0215643193bbe1dc89d3f2a10768329bbf0eebc"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/353AC4SAVWJPPHO2LBYJC5BTZ7/bundle.json","state_url":"https://pith.science/pith/353AC4SAVWJPPHO2LBYJC5BTZ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/353AC4SAVWJPPHO2LBYJC5BTZ7/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":"2026-08-19T05:04:38Z","links":{"resolver":"https://pith.science/pith/353AC4SAVWJPPHO2LBYJC5BTZ7","bundle":"https://pith.science/pith/353AC4SAVWJPPHO2LBYJC5BTZ7/bundle.json","state":"https://pith.science/pith/353AC4SAVWJPPHO2LBYJC5BTZ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/353AC4SAVWJPPHO2LBYJC5BTZ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:353AC4SAVWJPPHO2LBYJC5BTZ7","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":"23bd18d1e8181f7b4ec67ced8bbcef345e92cec36ae2218638d1decbde646fad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-07T07:58:26Z","title_canon_sha256":"4e963d4d515ed101edcaeeaf5da48e8a256b7a0783f372accc4776ede3966370"},"schema_version":"1.0","source":{"id":"1910.02655","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.02655","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"arxiv_version","alias_value":"1910.02655v1","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.02655","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"pith_short_12","alias_value":"353AC4SAVWJP","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"pith_short_16","alias_value":"353AC4SAVWJPPHO2","created_at":"2026-07-05T00:10:10Z"},{"alias_kind":"pith_short_8","alias_value":"353AC4SA","created_at":"2026-07-05T00:10:10Z"}],"graph_snapshots":[{"event_id":"sha256:ce37d2e82696cd5e12f17e6de0215643193bbe1dc89d3f2a10768329bbf0eebc","target":"graph","created_at":"2026-07-05T00:10:10Z","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/1910.02655/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Motivated by the promising performance of pre-trained language models, we investigate BERT in an evidence retrieval and claim verification pipeline for the FEVER fact extraction and verification challenge. To this end, we propose to use two BERT models, one for retrieving potential evidence sentences supporting or rejecting claims, and another for verifying claims based on the predicted evidence sets. To train the BERT retrieval system, we use pointwise and pairwise loss functions, and examine the effect of hard negative mining. A second BERT model is trained to classify the samples as support","authors_text":"Amir Soleimani, Christof Monz, Marcel Worring","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-07T07:58:26Z","title":"BERT for Evidence Retrieval and Claim Verification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.02655","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":"sha256:789d063a6a3e552a03c1937c4e2238785188c11f8133739b073218b1909e7b80","target":"record","created_at":"2026-07-05T00:10:10Z","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":"23bd18d1e8181f7b4ec67ced8bbcef345e92cec36ae2218638d1decbde646fad","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-07T07:58:26Z","title_canon_sha256":"4e963d4d515ed101edcaeeaf5da48e8a256b7a0783f372accc4776ede3966370"},"schema_version":"1.0","source":{"id":"1910.02655","kind":"arxiv","version":1}},"canonical_sha256":"df76017240ad92f79dda5870917433cfcd4e14005b5ba0c7d350fa36c14c2d8e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"df76017240ad92f79dda5870917433cfcd4e14005b5ba0c7d350fa36c14c2d8e","first_computed_at":"2026-07-05T00:10:10.190751Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:10:10.190751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gGWAwZ3qw4BsDLFDxExftoHm8ftZ3KPcpmwATuvOxguVvWp6i1sdnwMC83CNL2lwpeUd7MS6pCJnP3ZDaFZkCg==","signature_status":"signed_v1","signed_at":"2026-07-05T00:10:10.191160Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.02655","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:789d063a6a3e552a03c1937c4e2238785188c11f8133739b073218b1909e7b80","sha256:ce37d2e82696cd5e12f17e6de0215643193bbe1dc89d3f2a10768329bbf0eebc"],"state_sha256":"8fbf215c23341140307ba37e647b7edb32e82fe55e68df342450048fad5c8dbf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WlzXa3tTHEfcz7RiS+nCI1D8/cwnDqQLcPiq1dElU6tdI98j8mryBGE1TQSvuPyr/Ntvpz23SosMz3oxA4YWAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T05:04:38.042514Z","bundle_sha256":"4c309be382d4b6de5d7bf7c599fa416622083fa5cb6172aff99bc706bbe9390d"}}