{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:MCBTYTZDF6A7253MY3OUU2OMNV","short_pith_number":"pith:MCBTYTZD","canonical_record":{"source":{"id":"2509.00842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-31T13:24:48Z","cross_cats_sorted":[],"title_canon_sha256":"0e18c2448687d092c48e64855607bd29d618b993d7dadce34e168969c9d894cc","abstract_canon_sha256":"0d584ad0769fcdce7d13119f376917ff41f6d69d8eff1aaef9a71e2aada8d377"},"schema_version":"1.0"},"canonical_sha256":"60833c4f232f81fd776cc6dd4a69cc6d5b3f1f95dbbeabdb71dd1acf025b7265","source":{"kind":"arxiv","id":"2509.00842","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00842","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00842v1","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00842","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"MCBTYTZDF6A7","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"MCBTYTZDF6A7253M","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"MCBTYTZD","created_at":"2026-07-05T12:02:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:MCBTYTZDF6A7253MY3OUU2OMNV","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-31T13:24:48Z","cross_cats_sorted":[],"title_canon_sha256":"0e18c2448687d092c48e64855607bd29d618b993d7dadce34e168969c9d894cc","abstract_canon_sha256":"0d584ad0769fcdce7d13119f376917ff41f6d69d8eff1aaef9a71e2aada8d377"},"schema_version":"1.0"},"canonical_sha256":"60833c4f232f81fd776cc6dd4a69cc6d5b3f1f95dbbeabdb71dd1acf025b7265","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:23.526521Z","signature_b64":"ZIF/WfburCPVpAiWI4UIcYwRP9/7HDvZ1LxbYdrdJdJOK1Dnamvew5Ct9fYk2YzjJBkDMLzjaz1WwHtg7pfABw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60833c4f232f81fd776cc6dd4a69cc6d5b3f1f95dbbeabdb71dd1acf025b7265","last_reissued_at":"2026-07-05T12:02:23.525926Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:23.525926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00842","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":"2026-07-05T12:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dDZgU6bHFloQR1xiQ3ENGPKmsyfiYPXfexwgNZXr58c1Rom8rkSMZdL+Pr/YF/O7jyJvEB1laKSgQtinlAAZAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:03:07.650323Z"},"content_sha256":"c12b7e55d9a7003ea74ea28b23bcae64c3e1e489db1710edc256608d1bf173fc","schema_version":"1.0","event_id":"sha256:c12b7e55d9a7003ea74ea28b23bcae64c3e1e489db1710edc256608d1bf173fc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:MCBTYTZDF6A7253MY3OUU2OMNV","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bowen Dong, Jianyong Wang, Ning Liu, Tengyu Pan, Xiuxing Li, Zhenyu Li, Zhichao Duan","submitted_at":"2025-08-31T13:24:48Z","abstract_excerpt":"Text embedding models are essential for various natural language processing tasks, enabling the effective encoding of semantic information into dense vector representations. These models are typically optimized using triplets of (query, positive, negative) data pairs for contrastive learning, where the negative samples play a critical role in enhancing the model's ability to discern subtle semantic distinctions. In this work, we introduce a Multi-Granularity Hard-negative (MGH) synthesis framework that leverages large language models (LLMs) to generate diverse negative samples with varying lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00842","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/2509.00842/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":"2026-07-05T12:02:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rQR5m64k6NAyyQrcDjjswxjd+o9vaEbGjMQadF9/SPyqrjvTuqSKsLK7av/uxwqsjqKdo2+jBHQXjejXTKPIAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T22:03:07.651765Z"},"content_sha256":"3ccb47b638a2b2320378ff59418cce6dffa788963fc934b4354d7d7615e5753e","schema_version":"1.0","event_id":"sha256:3ccb47b638a2b2320378ff59418cce6dffa788963fc934b4354d7d7615e5753e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MCBTYTZDF6A7253MY3OUU2OMNV/bundle.json","state_url":"https://pith.science/pith/MCBTYTZDF6A7253MY3OUU2OMNV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MCBTYTZDF6A7253MY3OUU2OMNV/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":"2026-08-05T22:03:07Z","links":{"resolver":"https://pith.science/pith/MCBTYTZDF6A7253MY3OUU2OMNV","bundle":"https://pith.science/pith/MCBTYTZDF6A7253MY3OUU2OMNV/bundle.json","state":"https://pith.science/pith/MCBTYTZDF6A7253MY3OUU2OMNV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MCBTYTZDF6A7253MY3OUU2OMNV/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:MCBTYTZDF6A7253MY3OUU2OMNV","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":"0d584ad0769fcdce7d13119f376917ff41f6d69d8eff1aaef9a71e2aada8d377","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-31T13:24:48Z","title_canon_sha256":"0e18c2448687d092c48e64855607bd29d618b993d7dadce34e168969c9d894cc"},"schema_version":"1.0","source":{"id":"2509.00842","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00842","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00842v1","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00842","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"pith_short_12","alias_value":"MCBTYTZDF6A7","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"pith_short_16","alias_value":"MCBTYTZDF6A7253M","created_at":"2026-07-05T12:02:23Z"},{"alias_kind":"pith_short_8","alias_value":"MCBTYTZD","created_at":"2026-07-05T12:02:23Z"}],"graph_snapshots":[{"event_id":"sha256:3ccb47b638a2b2320378ff59418cce6dffa788963fc934b4354d7d7615e5753e","target":"graph","created_at":"2026-07-05T12:02:23Z","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/2509.00842/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text embedding models are essential for various natural language processing tasks, enabling the effective encoding of semantic information into dense vector representations. These models are typically optimized using triplets of (query, positive, negative) data pairs for contrastive learning, where the negative samples play a critical role in enhancing the model's ability to discern subtle semantic distinctions. In this work, we introduce a Multi-Granularity Hard-negative (MGH) synthesis framework that leverages large language models (LLMs) to generate diverse negative samples with varying lev","authors_text":"Bowen Dong, Jianyong Wang, Ning Liu, Tengyu Pan, Xiuxing Li, Zhenyu Li, Zhichao Duan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-31T13:24:48Z","title":"Negative Matters: Multi-Granularity Hard-Negative Synthesis and Anchor-Token-Aware Pooling for Enhanced Text Embeddings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00842","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:c12b7e55d9a7003ea74ea28b23bcae64c3e1e489db1710edc256608d1bf173fc","target":"record","created_at":"2026-07-05T12:02:23Z","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":"0d584ad0769fcdce7d13119f376917ff41f6d69d8eff1aaef9a71e2aada8d377","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-31T13:24:48Z","title_canon_sha256":"0e18c2448687d092c48e64855607bd29d618b993d7dadce34e168969c9d894cc"},"schema_version":"1.0","source":{"id":"2509.00842","kind":"arxiv","version":1}},"canonical_sha256":"60833c4f232f81fd776cc6dd4a69cc6d5b3f1f95dbbeabdb71dd1acf025b7265","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"60833c4f232f81fd776cc6dd4a69cc6d5b3f1f95dbbeabdb71dd1acf025b7265","first_computed_at":"2026-07-05T12:02:23.525926Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:02:23.525926Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZIF/WfburCPVpAiWI4UIcYwRP9/7HDvZ1LxbYdrdJdJOK1Dnamvew5Ct9fYk2YzjJBkDMLzjaz1WwHtg7pfABw==","signature_status":"signed_v1","signed_at":"2026-07-05T12:02:23.526521Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00842","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c12b7e55d9a7003ea74ea28b23bcae64c3e1e489db1710edc256608d1bf173fc","sha256:3ccb47b638a2b2320378ff59418cce6dffa788963fc934b4354d7d7615e5753e"],"state_sha256":"b3b771d6ee1e809344f5eb1e0cb0ad6bffddb6a202b9641a1790cb9d4d5a6aac"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OKynORKDmbfcFTb78qXHMATtS8PA+AAI9Jx2SFh7Mwt3nFMMcijtv2gpn3GgWqYcc2UNqA3yLcGY/mZmc8QpDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T22:03:07.659045Z","bundle_sha256":"7b1f439d777a71eb8ebddfce2a646f8c372c883c12aba0b5dd200205a6541cf1"}}