{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UPRZD74KTMQLKHXE7SFDIYXDAN","short_pith_number":"pith:UPRZD74K","canonical_record":{"source":{"id":"2506.21468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T16:56:43Z","cross_cats_sorted":[],"title_canon_sha256":"dc38e9590648123a7b589dcf3a774e5c53447b3c58c38a583a475a7118ef76ec","abstract_canon_sha256":"edbdf4e5c4d339d2fc58240572683c373cdd6eea355c4d6dc0d4c0dc8bbc544b"},"schema_version":"1.0"},"canonical_sha256":"a3e391ff8a9b20b51ee4fc8a3462e30347c67972f51c25717df3c037241949c5","source":{"kind":"arxiv","id":"2506.21468","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21468","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21468v1","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21468","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"pith_short_12","alias_value":"UPRZD74KTMQL","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"UPRZD74KTMQLKHXE","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"UPRZD74K","created_at":"2026-07-05T11:27:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UPRZD74KTMQLKHXE7SFDIYXDAN","target":"record","payload":{"canonical_record":{"source":{"id":"2506.21468","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T16:56:43Z","cross_cats_sorted":[],"title_canon_sha256":"dc38e9590648123a7b589dcf3a774e5c53447b3c58c38a583a475a7118ef76ec","abstract_canon_sha256":"edbdf4e5c4d339d2fc58240572683c373cdd6eea355c4d6dc0d4c0dc8bbc544b"},"schema_version":"1.0"},"canonical_sha256":"a3e391ff8a9b20b51ee4fc8a3462e30347c67972f51c25717df3c037241949c5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:46.470716Z","signature_b64":"p3Txe3Cyd5Jdaj66EjlNuhByuGTxvLVzJFsvVu8QeJj8ZwBFkUEtiZu/wDj8taYXQYzX2/4CG0dPLTnI7GrsBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a3e391ff8a9b20b51ee4fc8a3462e30347c67972f51c25717df3c037241949c5","last_reissued_at":"2026-07-05T11:27:46.470242Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:46.470242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.21468","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":"2026-07-05T11:27:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yHq3TjxUNThf9anr6nM2wgksX0mpLN4VO/WWyRpyFEAUxqaoBKvgMYi23w0UKpUDBff/BJFTpV98KTvBHBDIBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:48:36.605198Z"},"content_sha256":"d7b29a9afe54bd131a47fe82e6e3519c2f3eb02f4d1322d6fd57bda24d8a14c4","schema_version":"1.0","event_id":"sha256:d7b29a9afe54bd131a47fe82e6e3519c2f3eb02f4d1322d6fd57bda24d8a14c4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UPRZD74KTMQLKHXE7SFDIYXDAN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TopK Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Heinzerling, Kentaro Inui, Ryosuke Takahashi, Tatsuro Inaba","submitted_at":"2025-06-26T16:56:43Z","abstract_excerpt":"Sparse autoencoders (SAEs) have become an important tool for analyzing and interpreting the activation space of transformer-based language models (LMs). However, SAEs suffer several shortcomings that diminish their utility and internal validity. Since SAEs are trained post-hoc, it is unclear if the failure to discover a particular concept is a failure on the SAE's side or due to the underlying LM not representing this concept. This problem is exacerbated by training conditions and architecture choices affecting which features an SAE learns. When tracing how LMs learn concepts during training, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21468","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/2506.21468/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":"2026-07-05T11:27:46Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Os2Mh0DzykDZ0NWgJppVMKX69jTob+P6lUsv9jLyMf7UnhR/Xp+tobktr0Ye6IP48iskRqE79d3NjbypBDQqBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T10:48:36.605720Z"},"content_sha256":"2e55d2e008da40541db24779e87f6435bb746b5013bc99d9d950a4b94974a588","schema_version":"1.0","event_id":"sha256:2e55d2e008da40541db24779e87f6435bb746b5013bc99d9d950a4b94974a588"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UPRZD74KTMQLKHXE7SFDIYXDAN/bundle.json","state_url":"https://pith.science/pith/UPRZD74KTMQLKHXE7SFDIYXDAN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UPRZD74KTMQLKHXE7SFDIYXDAN/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":"2026-08-09T10:48:36Z","links":{"resolver":"https://pith.science/pith/UPRZD74KTMQLKHXE7SFDIYXDAN","bundle":"https://pith.science/pith/UPRZD74KTMQLKHXE7SFDIYXDAN/bundle.json","state":"https://pith.science/pith/UPRZD74KTMQLKHXE7SFDIYXDAN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UPRZD74KTMQLKHXE7SFDIYXDAN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UPRZD74KTMQLKHXE7SFDIYXDAN","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":"edbdf4e5c4d339d2fc58240572683c373cdd6eea355c4d6dc0d4c0dc8bbc544b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T16:56:43Z","title_canon_sha256":"dc38e9590648123a7b589dcf3a774e5c53447b3c58c38a583a475a7118ef76ec"},"schema_version":"1.0","source":{"id":"2506.21468","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.21468","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.21468v1","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21468","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"pith_short_12","alias_value":"UPRZD74KTMQL","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"pith_short_16","alias_value":"UPRZD74KTMQLKHXE","created_at":"2026-07-05T11:27:46Z"},{"alias_kind":"pith_short_8","alias_value":"UPRZD74K","created_at":"2026-07-05T11:27:46Z"}],"graph_snapshots":[{"event_id":"sha256:2e55d2e008da40541db24779e87f6435bb746b5013bc99d9d950a4b94974a588","target":"graph","created_at":"2026-07-05T11:27:46Z","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/2506.21468/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse autoencoders (SAEs) have become an important tool for analyzing and interpreting the activation space of transformer-based language models (LMs). However, SAEs suffer several shortcomings that diminish their utility and internal validity. Since SAEs are trained post-hoc, it is unclear if the failure to discover a particular concept is a failure on the SAE's side or due to the underlying LM not representing this concept. This problem is exacerbated by training conditions and architecture choices affecting which features an SAE learns. When tracing how LMs learn concepts during training, ","authors_text":"Benjamin Heinzerling, Kentaro Inui, Ryosuke Takahashi, Tatsuro Inaba","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T16:56:43Z","title":"TopK Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21468","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:d7b29a9afe54bd131a47fe82e6e3519c2f3eb02f4d1322d6fd57bda24d8a14c4","target":"record","created_at":"2026-07-05T11:27:46Z","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":"edbdf4e5c4d339d2fc58240572683c373cdd6eea355c4d6dc0d4c0dc8bbc544b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-06-26T16:56:43Z","title_canon_sha256":"dc38e9590648123a7b589dcf3a774e5c53447b3c58c38a583a475a7118ef76ec"},"schema_version":"1.0","source":{"id":"2506.21468","kind":"arxiv","version":1}},"canonical_sha256":"a3e391ff8a9b20b51ee4fc8a3462e30347c67972f51c25717df3c037241949c5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a3e391ff8a9b20b51ee4fc8a3462e30347c67972f51c25717df3c037241949c5","first_computed_at":"2026-07-05T11:27:46.470242Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:27:46.470242Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"p3Txe3Cyd5Jdaj66EjlNuhByuGTxvLVzJFsvVu8QeJj8ZwBFkUEtiZu/wDj8taYXQYzX2/4CG0dPLTnI7GrsBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:27:46.470716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.21468","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d7b29a9afe54bd131a47fe82e6e3519c2f3eb02f4d1322d6fd57bda24d8a14c4","sha256:2e55d2e008da40541db24779e87f6435bb746b5013bc99d9d950a4b94974a588"],"state_sha256":"85368955364ac958283d3c7d2e47aeb19f3f0b4b021f19d57d4d6451315121df"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hX2s7eR3l02JQSxEP39LYPxwwhRENtzUhCpA7q/ZmrZwn8aVduwgqA54myB+NBi/+UGXdvx5Q+TN/qElwyBYDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T10:48:36.609721Z","bundle_sha256":"40f6b0a5901ee51bc663b99eb490babfd07ac4471ff8d243bc514a85e1e5d04e"}}