{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:THBFZXVJFRFVYRGMEI7XHZ7YFU","short_pith_number":"pith:THBFZXVJ","canonical_record":{"source":{"id":"2602.02726","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T19:43:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a1fe25b5ab909d6a6cdd39dfcfa13645bc59e5400129c324e206d0fa1a99a251","abstract_canon_sha256":"469ecd215431cf0deaed37f51a675bff93735b6c48317a2c6d49f0630b6ff94d"},"schema_version":"1.0"},"canonical_sha256":"99c25cdea92c4b5c44cc223f73e7f82d0326d266915bc898466b93a5daf1fe8f","source":{"kind":"arxiv","id":"2602.02726","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.02726","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"arxiv_version","alias_value":"2602.02726v2","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02726","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"pith_short_12","alias_value":"THBFZXVJFRFV","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"pith_short_16","alias_value":"THBFZXVJFRFVYRGM","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"pith_short_8","alias_value":"THBFZXVJ","created_at":"2026-06-11T01:09:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:THBFZXVJFRFVYRGMEI7XHZ7YFU","target":"record","payload":{"canonical_record":{"source":{"id":"2602.02726","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T19:43:20Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"a1fe25b5ab909d6a6cdd39dfcfa13645bc59e5400129c324e206d0fa1a99a251","abstract_canon_sha256":"469ecd215431cf0deaed37f51a675bff93735b6c48317a2c6d49f0630b6ff94d"},"schema_version":"1.0"},"canonical_sha256":"99c25cdea92c4b5c44cc223f73e7f82d0326d266915bc898466b93a5daf1fe8f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-11T01:09:28.340581Z","signature_b64":"Gm39pCpldDBBxNht9TZ4joO792KnssAHIu0TAq/HdhV00iHfUAjKyagPn/8DDjDa7uK56XOqzRdsA0fMpkShDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99c25cdea92c4b5c44cc223f73e7f82d0326d266915bc898466b93a5daf1fe8f","last_reissued_at":"2026-06-11T01:09:28.339469Z","signature_status":"signed_v1","first_computed_at":"2026-06-11T01:09:28.339469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.02726","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":"2026-06-11T01:09:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/IsBSbVjLbOxV7n67FLJewR9QT8bnawR85XGjpUiuUFIAyoIh4ZhWuuVWmQHrupdOOpB4gnoWe1AtqlE08HMCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T13:09:19.459725Z"},"content_sha256":"548e4154b00f3b0d0c725417044e9528cea931c1b527a02a1a82c176d11d767f","schema_version":"1.0","event_id":"sha256:548e4154b00f3b0d0c725417044e9528cea931c1b527a02a1a82c176d11d767f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:THBFZXVJFRFVYRGMEI7XHZ7YFU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Ankur Garg, Hassan Sajjad, Samira Ebrahimi Kahou, Xuemin Yu","submitted_at":"2026-02-02T19:43:20Z","abstract_excerpt":"Large language models (LLMs) encode rich semantic information in their hidden states, yet it remains difficult to understand what information these internal representations capture. Latent concepts extracted from hidden states offer a promising direction for interpreting LLMs, but existing clustering-based methods face a trade-off: hierarchical clustering produces coherent concepts but is limited to small datasets due to its quadratic memory cost, while K-Means scales efficiently but may yield less semantically coherent concepts. We propose Vector Quantized Latent Concept (VQLC), a discrete co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02726","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/2602.02726/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":"2026-06-11T01:09:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KW0INkw7wHXunI9ZQIlMXBzdKbdIS4hxxgc+R0R2+fbOXlBwN/9zaRoAS5M93Tb5zJ1CK5EbBZj/nXJc8+whCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-11T13:09:19.460450Z"},"content_sha256":"a9501c1cdb30c6cfe7ad832ea22b52d3607596f1a69ce6f4532abde5ef399c69","schema_version":"1.0","event_id":"sha256:a9501c1cdb30c6cfe7ad832ea22b52d3607596f1a69ce6f4532abde5ef399c69"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/THBFZXVJFRFVYRGMEI7XHZ7YFU/bundle.json","state_url":"https://pith.science/pith/THBFZXVJFRFVYRGMEI7XHZ7YFU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/THBFZXVJFRFVYRGMEI7XHZ7YFU/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":"2026-06-11T13:09:19Z","links":{"resolver":"https://pith.science/pith/THBFZXVJFRFVYRGMEI7XHZ7YFU","bundle":"https://pith.science/pith/THBFZXVJFRFVYRGMEI7XHZ7YFU/bundle.json","state":"https://pith.science/pith/THBFZXVJFRFVYRGMEI7XHZ7YFU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/THBFZXVJFRFVYRGMEI7XHZ7YFU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:THBFZXVJFRFVYRGMEI7XHZ7YFU","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":"469ecd215431cf0deaed37f51a675bff93735b6c48317a2c6d49f0630b6ff94d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T19:43:20Z","title_canon_sha256":"a1fe25b5ab909d6a6cdd39dfcfa13645bc59e5400129c324e206d0fa1a99a251"},"schema_version":"1.0","source":{"id":"2602.02726","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.02726","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"arxiv_version","alias_value":"2602.02726v2","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.02726","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"pith_short_12","alias_value":"THBFZXVJFRFV","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"pith_short_16","alias_value":"THBFZXVJFRFVYRGM","created_at":"2026-06-11T01:09:28Z"},{"alias_kind":"pith_short_8","alias_value":"THBFZXVJ","created_at":"2026-06-11T01:09:28Z"}],"graph_snapshots":[{"event_id":"sha256:a9501c1cdb30c6cfe7ad832ea22b52d3607596f1a69ce6f4532abde5ef399c69","target":"graph","created_at":"2026-06-11T01:09:28Z","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/2602.02726/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) encode rich semantic information in their hidden states, yet it remains difficult to understand what information these internal representations capture. Latent concepts extracted from hidden states offer a promising direction for interpreting LLMs, but existing clustering-based methods face a trade-off: hierarchical clustering produces coherent concepts but is limited to small datasets due to its quadratic memory cost, while K-Means scales efficiently but may yield less semantically coherent concepts. We propose Vector Quantized Latent Concept (VQLC), a discrete co","authors_text":"Ankur Garg, Hassan Sajjad, Samira Ebrahimi Kahou, Xuemin Yu","cross_cats":["cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T19:43:20Z","title":"Vector Quantized Latent Concepts: A Scalable Alternative to Clustering-Based Concept Discovery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.02726","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":"sha256:548e4154b00f3b0d0c725417044e9528cea931c1b527a02a1a82c176d11d767f","target":"record","created_at":"2026-06-11T01:09:28Z","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":"469ecd215431cf0deaed37f51a675bff93735b6c48317a2c6d49f0630b6ff94d","cross_cats_sorted":["cs.CL"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-02T19:43:20Z","title_canon_sha256":"a1fe25b5ab909d6a6cdd39dfcfa13645bc59e5400129c324e206d0fa1a99a251"},"schema_version":"1.0","source":{"id":"2602.02726","kind":"arxiv","version":2}},"canonical_sha256":"99c25cdea92c4b5c44cc223f73e7f82d0326d266915bc898466b93a5daf1fe8f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"99c25cdea92c4b5c44cc223f73e7f82d0326d266915bc898466b93a5daf1fe8f","first_computed_at":"2026-06-11T01:09:28.339469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-11T01:09:28.339469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Gm39pCpldDBBxNht9TZ4joO792KnssAHIu0TAq/HdhV00iHfUAjKyagPn/8DDjDa7uK56XOqzRdsA0fMpkShDg==","signature_status":"signed_v1","signed_at":"2026-06-11T01:09:28.340581Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.02726","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:548e4154b00f3b0d0c725417044e9528cea931c1b527a02a1a82c176d11d767f","sha256:a9501c1cdb30c6cfe7ad832ea22b52d3607596f1a69ce6f4532abde5ef399c69"],"state_sha256":"135cde45e92cd217841a227f7784bdc1ddc49f9fc68106a06e235b0de64e4ba7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zEQlsTrBneRLYIzD8OazqrI+XqkEg12lwUrokHsSXqxCo1hTYaMxzd2rf2s+nWSfzhVdxri81eLgZf3Jz3fTDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-11T13:09:19.464347Z","bundle_sha256":"ad83ce13dd0e7017b62a3dc182dcadd758685bf338b5831c6c630096fa7b951e"}}