{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:T4G5P347MCRLDKUYVACCBW3BOR","short_pith_number":"pith:T4G5P347","canonical_record":{"source":{"id":"2607.00004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-20T05:52:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ce2c72ae63f4e2253371d1e4d2ef9c3d0092f63415259503d4071e63efb5e574","abstract_canon_sha256":"0d2a4837776dd46ecc8f0a4480de9f50506628417113022e38ade9ebdd64e187"},"schema_version":"1.0"},"canonical_sha256":"9f0dd7ef9f60a2b1aa98a80420db61746e40766d7e79a4e4eb0ca972893dc7e0","source":{"kind":"arxiv","id":"2607.00004","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00004","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00004v1","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00004","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"T4G5P347MCRL","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"T4G5P347MCRLDKUY","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"T4G5P347","created_at":"2026-07-02T00:18:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:T4G5P347MCRLDKUYVACCBW3BOR","target":"record","payload":{"canonical_record":{"source":{"id":"2607.00004","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-20T05:52:25Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"ce2c72ae63f4e2253371d1e4d2ef9c3d0092f63415259503d4071e63efb5e574","abstract_canon_sha256":"0d2a4837776dd46ecc8f0a4480de9f50506628417113022e38ade9ebdd64e187"},"schema_version":"1.0"},"canonical_sha256":"9f0dd7ef9f60a2b1aa98a80420db61746e40766d7e79a4e4eb0ca972893dc7e0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-02T00:18:04.182001Z","signature_b64":"oDPiAo36nhhQIlzXjxSsQ11Se7aGDV7TkSjP06EdML3WtgY6Z5VUxZXN4lm5WxKlftZZsPznYfCoGurPu6mWCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9f0dd7ef9f60a2b1aa98a80420db61746e40766d7e79a4e4eb0ca972893dc7e0","last_reissued_at":"2026-07-02T00:18:04.181197Z","signature_status":"signed_v1","first_computed_at":"2026-07-02T00:18:04.181197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.00004","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":"2026-07-02T00:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OCNy0Mk4Qfv7ytsRpI9hjUhTQStxM13IGDh+7IIqFvwjqALurCUNXEacwlp+rKtsCaj3g0tpLhPKkQj9+2c7Bg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:48:32.361215Z"},"content_sha256":"c0498bf09937c9895df4bb0a6a9945cd0fbfad1b0238c928c9897061b1e0317b","schema_version":"1.0","event_id":"sha256:c0498bf09937c9895df4bb0a6a9945cd0fbfad1b0238c928c9897061b1e0317b"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:T4G5P347MCRLDKUYVACCBW3BOR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.IR","authors_text":"Yang Yang, Zhichao Geng","submitted_at":"2026-04-20T05:52:25Z","abstract_excerpt":"While advanced foundation models like ModernBERT significantly outperform older architectures in dense retrieval, they surprisingly lag behind the aging BERT-base baseline in learned sparse retrieval (LSR). We identify the root cause as the \\textit{Vocabulary Gap}: modern tokenizers utilize raw, case-sensitive vocabularies designed for lossless reconstruction, which map single semantic units to redundant surface forms, wasting model capacity on morphological noise and hindering lexical matching. We formalize this intuition through a theoretical framework, demonstrating that appropriate vocabul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00004","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/2607.00004/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":"2026-07-02T00:18:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"W3xTet8GPvpSvG7GkVjijF1eSIyrcUqIl+uYNF6+BHNx9UVpZjQYB5BNl/dCGcHlaW0fXBPRjgnSXT9FeaEOCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T14:48:32.361608Z"},"content_sha256":"df60d590a361a240ff3231fbb76f501f4a574c411fce81c8d580e2897a3a5eb3","schema_version":"1.0","event_id":"sha256:df60d590a361a240ff3231fbb76f501f4a574c411fce81c8d580e2897a3a5eb3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR/bundle.json","state_url":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T4G5P347MCRLDKUYVACCBW3BOR/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":"2026-07-06T14:48:32Z","links":{"resolver":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR","bundle":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR/bundle.json","state":"https://pith.science/pith/T4G5P347MCRLDKUYVACCBW3BOR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T4G5P347MCRLDKUYVACCBW3BOR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:T4G5P347MCRLDKUYVACCBW3BOR","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":"0d2a4837776dd46ecc8f0a4480de9f50506628417113022e38ade9ebdd64e187","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-20T05:52:25Z","title_canon_sha256":"ce2c72ae63f4e2253371d1e4d2ef9c3d0092f63415259503d4071e63efb5e574"},"schema_version":"1.0","source":{"id":"2607.00004","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.00004","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"arxiv_version","alias_value":"2607.00004v1","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.00004","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_12","alias_value":"T4G5P347MCRL","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_16","alias_value":"T4G5P347MCRLDKUY","created_at":"2026-07-02T00:18:04Z"},{"alias_kind":"pith_short_8","alias_value":"T4G5P347","created_at":"2026-07-02T00:18:04Z"}],"graph_snapshots":[{"event_id":"sha256:df60d590a361a240ff3231fbb76f501f4a574c411fce81c8d580e2897a3a5eb3","target":"graph","created_at":"2026-07-02T00:18:04Z","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/2607.00004/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While advanced foundation models like ModernBERT significantly outperform older architectures in dense retrieval, they surprisingly lag behind the aging BERT-base baseline in learned sparse retrieval (LSR). We identify the root cause as the \\textit{Vocabulary Gap}: modern tokenizers utilize raw, case-sensitive vocabularies designed for lossless reconstruction, which map single semantic units to redundant surface forms, wasting model capacity on morphological noise and hindering lexical matching. We formalize this intuition through a theoretical framework, demonstrating that appropriate vocabul","authors_text":"Yang Yang, Zhichao Geng","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-20T05:52:25Z","title":"Why Advanced Encoders Lag on Sparse Retrieval? The Answer and an Approach to Bridging Vocabulary Gaps"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.00004","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:c0498bf09937c9895df4bb0a6a9945cd0fbfad1b0238c928c9897061b1e0317b","target":"record","created_at":"2026-07-02T00:18:04Z","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":"0d2a4837776dd46ecc8f0a4480de9f50506628417113022e38ade9ebdd64e187","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2026-04-20T05:52:25Z","title_canon_sha256":"ce2c72ae63f4e2253371d1e4d2ef9c3d0092f63415259503d4071e63efb5e574"},"schema_version":"1.0","source":{"id":"2607.00004","kind":"arxiv","version":1}},"canonical_sha256":"9f0dd7ef9f60a2b1aa98a80420db61746e40766d7e79a4e4eb0ca972893dc7e0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f0dd7ef9f60a2b1aa98a80420db61746e40766d7e79a4e4eb0ca972893dc7e0","first_computed_at":"2026-07-02T00:18:04.181197Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-02T00:18:04.181197Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oDPiAo36nhhQIlzXjxSsQ11Se7aGDV7TkSjP06EdML3WtgY6Z5VUxZXN4lm5WxKlftZZsPznYfCoGurPu6mWCQ==","signature_status":"signed_v1","signed_at":"2026-07-02T00:18:04.182001Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.00004","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c0498bf09937c9895df4bb0a6a9945cd0fbfad1b0238c928c9897061b1e0317b","sha256:df60d590a361a240ff3231fbb76f501f4a574c411fce81c8d580e2897a3a5eb3"],"state_sha256":"e048aa6b69d29fb6e3bc1a8043f60a0af9d6440df279cdf16c7a1f2b431f4859"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"osekuAU4onnJfQzzBYPxaCVV+hKbTN57ZiFt/JPyzMC+qv7OAHpw3Jcb8kkgx4vcxvS6zCyyDSS961LHcWKLAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T14:48:32.363527Z","bundle_sha256":"583e38bb621cb79994f8e1e665cbe387734b38a946a993073e92e5a21a91683e"}}