{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:UIDWNJCRD5HTYRPK3EJM4IA5YC","short_pith_number":"pith:UIDWNJCR","canonical_record":{"source":{"id":"2409.02727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T14:01:48Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"b623c783cbea8f5a308bd4de077044db1e87323d22a02bed2433d41561ac25e4","abstract_canon_sha256":"160f98bd6447f4386ea40f8ce7bb8fcfd9bf566bf00118207e23e7c5b97b0506"},"schema_version":"1.0"},"canonical_sha256":"a20766a4511f4f3c45ead912ce201dc0abbad14d0f7189b3dfc8dd64cc40438b","source":{"kind":"arxiv","id":"2409.02727","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02727","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02727v2","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02727","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"UIDWNJCRD5HT","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"UIDWNJCRD5HTYRPK","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"UIDWNJCR","created_at":"2026-07-05T09:03:23Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:UIDWNJCRD5HTYRPK3EJM4IA5YC","target":"record","payload":{"canonical_record":{"source":{"id":"2409.02727","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T14:01:48Z","cross_cats_sorted":["cs.IR"],"title_canon_sha256":"b623c783cbea8f5a308bd4de077044db1e87323d22a02bed2433d41561ac25e4","abstract_canon_sha256":"160f98bd6447f4386ea40f8ce7bb8fcfd9bf566bf00118207e23e7c5b97b0506"},"schema_version":"1.0"},"canonical_sha256":"a20766a4511f4f3c45ead912ce201dc0abbad14d0f7189b3dfc8dd64cc40438b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:03:23.761000Z","signature_b64":"uYnytdy5SUNK40dPTjsBZVC8TEsTmHwtzCby9ubDVWvAmadUu87KvJOdv1kplDvJmAc5f9kcb7Jp3iLnaI1MAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a20766a4511f4f3c45ead912ce201dc0abbad14d0f7189b3dfc8dd64cc40438b","last_reissued_at":"2026-07-05T09:03:23.760478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:03:23.760478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.02727","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4Vs+1octEz3kqrSU8DoPi+mbA3cDT0YrVhaEH49am3rfcBvWIhkt6UJgoR8DHAUeNLaUvCqeRdyxUog+hyGxBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:35:21.729704Z"},"content_sha256":"f97031c4bc61d544baf785b3013c927a9e352b2e173957dfeaf87bcddb61a180","schema_version":"1.0","event_id":"sha256:f97031c4bc61d544baf785b3013c927a9e352b2e173957dfeaf87bcddb61a180"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:UIDWNJCRD5HTYRPK3EJM4IA5YC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.IR"],"primary_cat":"cs.CL","authors_text":"Yixuan Tang, Yi Yang","submitted_at":"2024-09-04T14:01:48Z","abstract_excerpt":"The significant advancements of Large Language Models (LLMs) in generative tasks have led to a growing body of work exploring LLM-based embedding models. While these models, employing different pooling and attention strategies, have achieved state-of-the-art performance on public embedding benchmarks, questions still arise about what constitutes an effective design for LLM-based embedding models. However, these models are often trained on different datasets, using different LLM base models or training settings. Moreover, evaluations on public embedding benchmarks often fail to report statistic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02727","kind":"arxiv","version":2},"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/2409.02727/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":"2026-07-05T09:03:23Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SbtAxbquCx/DC9iUKqCDa7nx00cbaRoGQPNYIZufA30U11lkAqaH97RE6LhD+r6b1ipPfTD4sEQ1otiBcfRBCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T04:35:21.730230Z"},"content_sha256":"bd7bbbfece4827afcc968f2de88dd5108ef88e632fb7a7c2566edcee0a0fbf16","schema_version":"1.0","event_id":"sha256:bd7bbbfece4827afcc968f2de88dd5108ef88e632fb7a7c2566edcee0a0fbf16"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UIDWNJCRD5HTYRPK3EJM4IA5YC/bundle.json","state_url":"https://pith.science/pith/UIDWNJCRD5HTYRPK3EJM4IA5YC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UIDWNJCRD5HTYRPK3EJM4IA5YC/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":"2026-08-08T04:35:21Z","links":{"resolver":"https://pith.science/pith/UIDWNJCRD5HTYRPK3EJM4IA5YC","bundle":"https://pith.science/pith/UIDWNJCRD5HTYRPK3EJM4IA5YC/bundle.json","state":"https://pith.science/pith/UIDWNJCRD5HTYRPK3EJM4IA5YC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UIDWNJCRD5HTYRPK3EJM4IA5YC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:UIDWNJCRD5HTYRPK3EJM4IA5YC","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":"160f98bd6447f4386ea40f8ce7bb8fcfd9bf566bf00118207e23e7c5b97b0506","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T14:01:48Z","title_canon_sha256":"b623c783cbea8f5a308bd4de077044db1e87323d22a02bed2433d41561ac25e4"},"schema_version":"1.0","source":{"id":"2409.02727","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.02727","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2409.02727v2","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.02727","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"UIDWNJCRD5HT","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"UIDWNJCRD5HTYRPK","created_at":"2026-07-05T09:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"UIDWNJCR","created_at":"2026-07-05T09:03:23Z"}],"graph_snapshots":[{"event_id":"sha256:bd7bbbfece4827afcc968f2de88dd5108ef88e632fb7a7c2566edcee0a0fbf16","target":"graph","created_at":"2026-07-05T09:03:23Z","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/2409.02727/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The significant advancements of Large Language Models (LLMs) in generative tasks have led to a growing body of work exploring LLM-based embedding models. While these models, employing different pooling and attention strategies, have achieved state-of-the-art performance on public embedding benchmarks, questions still arise about what constitutes an effective design for LLM-based embedding models. However, these models are often trained on different datasets, using different LLM base models or training settings. Moreover, evaluations on public embedding benchmarks often fail to report statistic","authors_text":"Yixuan Tang, Yi Yang","cross_cats":["cs.IR"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T14:01:48Z","title":"Pooling And Attention: What Are Effective Designs For LLM-Based Embedding Models?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.02727","kind":"arxiv","version":2},"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:f97031c4bc61d544baf785b3013c927a9e352b2e173957dfeaf87bcddb61a180","target":"record","created_at":"2026-07-05T09:03:23Z","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":"160f98bd6447f4386ea40f8ce7bb8fcfd9bf566bf00118207e23e7c5b97b0506","cross_cats_sorted":["cs.IR"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-04T14:01:48Z","title_canon_sha256":"b623c783cbea8f5a308bd4de077044db1e87323d22a02bed2433d41561ac25e4"},"schema_version":"1.0","source":{"id":"2409.02727","kind":"arxiv","version":2}},"canonical_sha256":"a20766a4511f4f3c45ead912ce201dc0abbad14d0f7189b3dfc8dd64cc40438b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a20766a4511f4f3c45ead912ce201dc0abbad14d0f7189b3dfc8dd64cc40438b","first_computed_at":"2026-07-05T09:03:23.760478Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:03:23.760478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uYnytdy5SUNK40dPTjsBZVC8TEsTmHwtzCby9ubDVWvAmadUu87KvJOdv1kplDvJmAc5f9kcb7Jp3iLnaI1MAA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:03:23.761000Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.02727","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f97031c4bc61d544baf785b3013c927a9e352b2e173957dfeaf87bcddb61a180","sha256:bd7bbbfece4827afcc968f2de88dd5108ef88e632fb7a7c2566edcee0a0fbf16"],"state_sha256":"daf34357df80db2fded4146d487209710009416254d31005a18d2afb5d8b1f41"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KkHDl0SlRIBcl+SA8zrhFAHYa35ZYf9kZa3Q9e+DQy4HWV+Dreous8TyWgYZjQRAaw3Z5tuZr9JSJdmBzyQjDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T04:35:21.735925Z","bundle_sha256":"a85a8c3fe98cc7146b79d2c17be35662aa1648915a0e9d82d1f576c5cbb42db1"}}