{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:E6A6XBJLGUIRE2OR5A6F7YLQSC","short_pith_number":"pith:E6A6XBJL","canonical_record":{"source":{"id":"2607.04011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-04T20:13:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54ce4844ee6589c825d0fbe1338d26a7dcabc65a9a4e0d851635c103fc644c55","abstract_canon_sha256":"9b936371bbb25c947822c1801f22b7852411bbdb364b2fb2926e505395ac68ea"},"schema_version":"1.0"},"canonical_sha256":"2781eb852b35111269d1e83c5fe170908ac5e36db2b0fbc6e418c4c558d7f697","source":{"kind":"arxiv","id":"2607.04011","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04011","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04011v1","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04011","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"pith_short_12","alias_value":"E6A6XBJLGUIR","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"pith_short_16","alias_value":"E6A6XBJLGUIRE2OR","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"pith_short_8","alias_value":"E6A6XBJL","created_at":"2026-07-07T02:18:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:E6A6XBJLGUIRE2OR5A6F7YLQSC","target":"record","payload":{"canonical_record":{"source":{"id":"2607.04011","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-04T20:13:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"54ce4844ee6589c825d0fbe1338d26a7dcabc65a9a4e0d851635c103fc644c55","abstract_canon_sha256":"9b936371bbb25c947822c1801f22b7852411bbdb364b2fb2926e505395ac68ea"},"schema_version":"1.0"},"canonical_sha256":"2781eb852b35111269d1e83c5fe170908ac5e36db2b0fbc6e418c4c558d7f697","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:18:52.952497Z","signature_b64":"GxiCy7INgVWVMOh2S0FJuyT6vEulMNxoYC6YX+wlXZZLAi883p7rEvuR2UG7ZvMuL19Su8JhX+QT3rJugGRCBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2781eb852b35111269d1e83c5fe170908ac5e36db2b0fbc6e418c4c558d7f697","last_reissued_at":"2026-07-07T02:18:52.951605Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:18:52.951605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.04011","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":"2026-07-07T02:18:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6nC8Fl4yKHSW18JLvj9F9g3zHBw8DIWTSpZkD5pCf3ECqB5JUXsF3+H5odqI60rGGsnVlFXdTo3RwROzPC3NAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T13:04:37.540325Z"},"content_sha256":"8b29ec177236e363c1b76ab4e59603c5f2aaa7270fcf94c69da9d8ad495b4449","schema_version":"1.0","event_id":"sha256:8b29ec177236e363c1b76ab4e59603c5f2aaa7270fcf94c69da9d8ad495b4449"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:E6A6XBJLGUIRE2OR5A6F7YLQSC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Separating Representation from Reconstruction Enables Scalable Text Encoders","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Mathurin Videau, Megi Dervishi, Yann LeCun","submitted_at":"2026-07-04T20:13:38Z","abstract_excerpt":"While decoders have rapidly scaled, encoders have remained largely unchanged since BERT. We revisit this disparity by frozen backbone evaluation via probing. Under this lens, the representations of BERT encoders become increasingly $\\textit{unexploitable}$ by frozen probes, despite improved perplexity. The misalignment originates in BERT's flat design, which couples representation learning to the token reconstruction loss. We propose $\\textbf{CrossBERT}$, a two-part architecture that separates the learning of high-quality encoded representations from the rigid grounding of token reconstruction"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04011","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/2607.04011/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":"2026-07-07T02:18:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TOf2N6DQd/pGIjlx9oPOYMKNHwsQRU2HaZ6UUaC/GTm9ac26B7ENuS3qmDo0EAwjZeDJU3VJAVOJRMT4/Xg5DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-21T13:04:37.540694Z"},"content_sha256":"4d7141a5c6d9ea41498aefa62ce8d8a78a66c95c0d50df9fb232cc50c5ba0107","schema_version":"1.0","event_id":"sha256:4d7141a5c6d9ea41498aefa62ce8d8a78a66c95c0d50df9fb232cc50c5ba0107"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E6A6XBJLGUIRE2OR5A6F7YLQSC/bundle.json","state_url":"https://pith.science/pith/E6A6XBJLGUIRE2OR5A6F7YLQSC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E6A6XBJLGUIRE2OR5A6F7YLQSC/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":"2026-07-21T13:04:37Z","links":{"resolver":"https://pith.science/pith/E6A6XBJLGUIRE2OR5A6F7YLQSC","bundle":"https://pith.science/pith/E6A6XBJLGUIRE2OR5A6F7YLQSC/bundle.json","state":"https://pith.science/pith/E6A6XBJLGUIRE2OR5A6F7YLQSC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E6A6XBJLGUIRE2OR5A6F7YLQSC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:E6A6XBJLGUIRE2OR5A6F7YLQSC","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":"9b936371bbb25c947822c1801f22b7852411bbdb364b2fb2926e505395ac68ea","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-04T20:13:38Z","title_canon_sha256":"54ce4844ee6589c825d0fbe1338d26a7dcabc65a9a4e0d851635c103fc644c55"},"schema_version":"1.0","source":{"id":"2607.04011","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.04011","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"arxiv_version","alias_value":"2607.04011v1","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.04011","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"pith_short_12","alias_value":"E6A6XBJLGUIR","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"pith_short_16","alias_value":"E6A6XBJLGUIRE2OR","created_at":"2026-07-07T02:18:52Z"},{"alias_kind":"pith_short_8","alias_value":"E6A6XBJL","created_at":"2026-07-07T02:18:52Z"}],"graph_snapshots":[{"event_id":"sha256:4d7141a5c6d9ea41498aefa62ce8d8a78a66c95c0d50df9fb232cc50c5ba0107","target":"graph","created_at":"2026-07-07T02:18:52Z","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/2607.04011/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"While decoders have rapidly scaled, encoders have remained largely unchanged since BERT. We revisit this disparity by frozen backbone evaluation via probing. Under this lens, the representations of BERT encoders become increasingly $\\textit{unexploitable}$ by frozen probes, despite improved perplexity. The misalignment originates in BERT's flat design, which couples representation learning to the token reconstruction loss. We propose $\\textbf{CrossBERT}$, a two-part architecture that separates the learning of high-quality encoded representations from the rigid grounding of token reconstruction","authors_text":"Mathurin Videau, Megi Dervishi, Yann LeCun","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-04T20:13:38Z","title":"Separating Representation from Reconstruction Enables Scalable Text Encoders"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.04011","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":"sha256:8b29ec177236e363c1b76ab4e59603c5f2aaa7270fcf94c69da9d8ad495b4449","target":"record","created_at":"2026-07-07T02:18:52Z","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":"9b936371bbb25c947822c1801f22b7852411bbdb364b2fb2926e505395ac68ea","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-07-04T20:13:38Z","title_canon_sha256":"54ce4844ee6589c825d0fbe1338d26a7dcabc65a9a4e0d851635c103fc644c55"},"schema_version":"1.0","source":{"id":"2607.04011","kind":"arxiv","version":1}},"canonical_sha256":"2781eb852b35111269d1e83c5fe170908ac5e36db2b0fbc6e418c4c558d7f697","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2781eb852b35111269d1e83c5fe170908ac5e36db2b0fbc6e418c4c558d7f697","first_computed_at":"2026-07-07T02:18:52.951605Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:18:52.951605Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GxiCy7INgVWVMOh2S0FJuyT6vEulMNxoYC6YX+wlXZZLAi883p7rEvuR2UG7ZvMuL19Su8JhX+QT3rJugGRCBw==","signature_status":"signed_v1","signed_at":"2026-07-07T02:18:52.952497Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.04011","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8b29ec177236e363c1b76ab4e59603c5f2aaa7270fcf94c69da9d8ad495b4449","sha256:4d7141a5c6d9ea41498aefa62ce8d8a78a66c95c0d50df9fb232cc50c5ba0107"],"state_sha256":"cd5940dd31cb521ef13c03c979927feaa6f62685aa3c1c893897b8605c6dccc2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"baoj851QCNXTDD2jAY2UpRSSzWEW2oq0iLm3o0dASeQJQE9hEoGyVnko7M5MRcFLxYnM2/sGnrnmBz//Aeq9AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-21T13:04:37.542825Z","bundle_sha256":"b89b3bedf1acae664ec12759da2f5785b7c3f862c9800416ecfbd3f19399c305"}}