{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2DMUVHWUMFUXBOK3BYV6QIXJJU","short_pith_number":"pith:2DMUVHWU","canonical_record":{"source":{"id":"2507.12782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:48:54Z","cross_cats_sorted":[],"title_canon_sha256":"f05626c92c773a1d3726a7b4056d5da84f7ab2c379e23862fc2bfaec6486ec2f","abstract_canon_sha256":"5479962de425248f79e88a578d4ac496ea9f1b0ba695998cab1da975381e3af4"},"schema_version":"1.0"},"canonical_sha256":"d0d94a9ed4616970b95b0e2be822e94d39c5500f47e372bad81e12a2b7a9a8a4","source":{"kind":"arxiv","id":"2507.12782","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12782","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12782v1","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12782","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"pith_short_12","alias_value":"2DMUVHWUMFUX","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"pith_short_16","alias_value":"2DMUVHWUMFUXBOK3","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"pith_short_8","alias_value":"2DMUVHWU","created_at":"2026-07-05T11:38:39Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2DMUVHWUMFUXBOK3BYV6QIXJJU","target":"record","payload":{"canonical_record":{"source":{"id":"2507.12782","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:48:54Z","cross_cats_sorted":[],"title_canon_sha256":"f05626c92c773a1d3726a7b4056d5da84f7ab2c379e23862fc2bfaec6486ec2f","abstract_canon_sha256":"5479962de425248f79e88a578d4ac496ea9f1b0ba695998cab1da975381e3af4"},"schema_version":"1.0"},"canonical_sha256":"d0d94a9ed4616970b95b0e2be822e94d39c5500f47e372bad81e12a2b7a9a8a4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:39.036474Z","signature_b64":"SC/qDN7/T+DsoxdbheXTrqlfCMKK2/8n7fu6m0tNsckd6L53k2gCUDLsYUBun02+kiku+KRTA/dtLtxv9dJoBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0d94a9ed4616970b95b0e2be822e94d39c5500f47e372bad81e12a2b7a9a8a4","last_reissued_at":"2026-07-05T11:38:39.035782Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:39.035782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.12782","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":"2026-07-05T11:38:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pHtrGsBaxhlnLwFAhHI6NB0O7LefyVndz2hxKzCi3V+VJH/KM+FFpDW36d9HdSkjKqJz6DdEhbjOikwexNFjAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:24:27.255645Z"},"content_sha256":"b55dd1e79f81661c3eeb26b9485c60b287e0e27f69e7018b4cd8672a6bc1b598","schema_version":"1.0","event_id":"sha256:b55dd1e79f81661c3eeb26b9485c60b287e0e27f69e7018b4cd8672a6bc1b598"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2DMUVHWUMFUXBOK3BYV6QIXJJU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Robust Negation Text Representations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Karin Verspoor, Thinh Hung Truong, Timothy Baldwin, Trevor Cohn","submitted_at":"2025-07-17T04:48:54Z","abstract_excerpt":"Despite rapid adoption of autoregressive large language models, smaller text encoders still play an important role in text understanding tasks that require rich contextualized representations. Negation is an important semantic function that is still not properly captured by such methods, affecting many downstream applications relying on text embeddings. We propose a strategy to improve negation robustness of text encoders, by distilling data from large language models using diverse patterns of negation and hedging. We adopt a standard contrastive learning strategy to finetune a strong BERT-bas"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12782","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/2507.12782/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":"2026-07-05T11:38:39Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZXC4bKQQqIXbJjtpx5XHTSwvVY9AhP9bb+ijcKYQXscZSTz9iDENAUeFX9STjcDezB//t99HZAmX+Ar//RUjAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:24:27.256162Z"},"content_sha256":"63abb9dc42a6656a8f9ea6598370a8e0304330722eceef19c80105721b0be85f","schema_version":"1.0","event_id":"sha256:63abb9dc42a6656a8f9ea6598370a8e0304330722eceef19c80105721b0be85f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2DMUVHWUMFUXBOK3BYV6QIXJJU/bundle.json","state_url":"https://pith.science/pith/2DMUVHWUMFUXBOK3BYV6QIXJJU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2DMUVHWUMFUXBOK3BYV6QIXJJU/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":"2026-08-08T11:24:27Z","links":{"resolver":"https://pith.science/pith/2DMUVHWUMFUXBOK3BYV6QIXJJU","bundle":"https://pith.science/pith/2DMUVHWUMFUXBOK3BYV6QIXJJU/bundle.json","state":"https://pith.science/pith/2DMUVHWUMFUXBOK3BYV6QIXJJU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2DMUVHWUMFUXBOK3BYV6QIXJJU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2DMUVHWUMFUXBOK3BYV6QIXJJU","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":"5479962de425248f79e88a578d4ac496ea9f1b0ba695998cab1da975381e3af4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:48:54Z","title_canon_sha256":"f05626c92c773a1d3726a7b4056d5da84f7ab2c379e23862fc2bfaec6486ec2f"},"schema_version":"1.0","source":{"id":"2507.12782","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.12782","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"arxiv_version","alias_value":"2507.12782v1","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.12782","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"pith_short_12","alias_value":"2DMUVHWUMFUX","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"pith_short_16","alias_value":"2DMUVHWUMFUXBOK3","created_at":"2026-07-05T11:38:39Z"},{"alias_kind":"pith_short_8","alias_value":"2DMUVHWU","created_at":"2026-07-05T11:38:39Z"}],"graph_snapshots":[{"event_id":"sha256:63abb9dc42a6656a8f9ea6598370a8e0304330722eceef19c80105721b0be85f","target":"graph","created_at":"2026-07-05T11:38:39Z","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/2507.12782/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite rapid adoption of autoregressive large language models, smaller text encoders still play an important role in text understanding tasks that require rich contextualized representations. Negation is an important semantic function that is still not properly captured by such methods, affecting many downstream applications relying on text embeddings. We propose a strategy to improve negation robustness of text encoders, by distilling data from large language models using diverse patterns of negation and hedging. We adopt a standard contrastive learning strategy to finetune a strong BERT-bas","authors_text":"Karin Verspoor, Thinh Hung Truong, Timothy Baldwin, Trevor Cohn","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:48:54Z","title":"Learning Robust Negation Text Representations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.12782","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:b55dd1e79f81661c3eeb26b9485c60b287e0e27f69e7018b4cd8672a6bc1b598","target":"record","created_at":"2026-07-05T11:38:39Z","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":"5479962de425248f79e88a578d4ac496ea9f1b0ba695998cab1da975381e3af4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-17T04:48:54Z","title_canon_sha256":"f05626c92c773a1d3726a7b4056d5da84f7ab2c379e23862fc2bfaec6486ec2f"},"schema_version":"1.0","source":{"id":"2507.12782","kind":"arxiv","version":1}},"canonical_sha256":"d0d94a9ed4616970b95b0e2be822e94d39c5500f47e372bad81e12a2b7a9a8a4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0d94a9ed4616970b95b0e2be822e94d39c5500f47e372bad81e12a2b7a9a8a4","first_computed_at":"2026-07-05T11:38:39.035782Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:39.035782Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SC/qDN7/T+DsoxdbheXTrqlfCMKK2/8n7fu6m0tNsckd6L53k2gCUDLsYUBun02+kiku+KRTA/dtLtxv9dJoBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:39.036474Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.12782","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b55dd1e79f81661c3eeb26b9485c60b287e0e27f69e7018b4cd8672a6bc1b598","sha256:63abb9dc42a6656a8f9ea6598370a8e0304330722eceef19c80105721b0be85f"],"state_sha256":"42b4a744f6c10ec0f1f2cc90aa3da20ac6f99d77696675eb8092961b8359f517"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tznrbI50qcL4lEQ6w0oPQq8zF1AyBH5yH8YCesMUgrur5DizVBCDeMSwD1zmcKQPNJwjyb6bxOHSuByQmy6fAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:24:27.261059Z","bundle_sha256":"1be85762c0b4651913f546c349fe2e7a7ade880154d960376dbc62d18e250414"}}