{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:WISN6CK5PXQ5VXPKACTSP3REC2","short_pith_number":"pith:WISN6CK5","canonical_record":{"source":{"id":"2608.12090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T14:13:48Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"4fc4cffb8baf5e59fcddf6ac0ac0c1c38dbcfeb9acbb1dd06090221631585fcd","abstract_canon_sha256":"64f273a551bbed56aff08bfa998d40cb3a43e133afc3f348ab46ffb0eabf079f"},"schema_version":"1.0"},"canonical_sha256":"b224df095d7de1daddea00a727ee241692b03b1bfe6b5b76cffa0a36eaa0633e","source":{"kind":"arxiv","id":"2608.12090","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12090","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12090v1","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12090","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"pith_short_12","alias_value":"WISN6CK5PXQ5","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"pith_short_16","alias_value":"WISN6CK5PXQ5VXPK","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"pith_short_8","alias_value":"WISN6CK5","created_at":"2026-08-13T01:29:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:WISN6CK5PXQ5VXPKACTSP3REC2","target":"record","payload":{"canonical_record":{"source":{"id":"2608.12090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T14:13:48Z","cross_cats_sorted":["q-bio.BM"],"title_canon_sha256":"4fc4cffb8baf5e59fcddf6ac0ac0c1c38dbcfeb9acbb1dd06090221631585fcd","abstract_canon_sha256":"64f273a551bbed56aff08bfa998d40cb3a43e133afc3f348ab46ffb0eabf079f"},"schema_version":"1.0"},"canonical_sha256":"b224df095d7de1daddea00a727ee241692b03b1bfe6b5b76cffa0a36eaa0633e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-13T01:29:57.371127Z","signature_b64":"nHvpjzSv+Z4qtmxpp0dhBII5uKO/3Nl0t+YutNUcVpN12O9Nke1rX3FA4LVx6q0rCV1MgHOtb09A3y0Nl3xwBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b224df095d7de1daddea00a727ee241692b03b1bfe6b5b76cffa0a36eaa0633e","last_reissued_at":"2026-08-13T01:29:57.368825Z","signature_status":"signed_v1","first_computed_at":"2026-08-13T01:29:57.368825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2608.12090","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":"2026-08-13T01:29:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I0rDs0LIimbkLvRtWS5PriVvOqHYnUiQ+QeaIiIZspgQkcNvW3Gg4aWmZWI5ckiebxAGi1MXqw3z49oxsi2WAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:58:23.121751Z"},"content_sha256":"cda928eba892933c3c8e92978f9c1582da97f5c11152240d883835e169833264","schema_version":"1.0","event_id":"sha256:cda928eba892933c3c8e92978f9c1582da97f5c11152240d883835e169833264"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:WISN6CK5PXQ5VXPKACTSP3REC2","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Task- and dataset-specific information in protein language models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.BM"],"primary_cat":"cs.LG","authors_text":"Ilya Senatorov, Olga V. Kalinina, Roman Joeres","submitted_at":"2026-08-12T14:13:48Z","abstract_excerpt":"Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on large corpora of protein sequence data, are widely used to translate amino acid sequences into latent-space embeddings, ready for use in diverse downstream tasks (DTs). By a common consensus, embeddings from the model's last layer are used, and the model's internal behavior remains poorly understood. We analyzed 13 PLMs across 15 DTs from 11 datasets to investigate the informativeness of embeddings created in intermediate PLM layers. We trained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12090","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/2608.12090/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":"2026-08-13T01:29:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rI6WTLVkLisvXTdjYaYqxjdoaar8hPo6s5NcbTQiv/6mBWcCbwyjpU6qPMi8/TCHUygNmoN4rPhOf6VvpDy4DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-20T03:58:23.122270Z"},"content_sha256":"520ca88c3209f1a7b6ed7aa7629b5b638eea341e773b0c21026c54b771ea46b7","schema_version":"1.0","event_id":"sha256:520ca88c3209f1a7b6ed7aa7629b5b638eea341e773b0c21026c54b771ea46b7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WISN6CK5PXQ5VXPKACTSP3REC2/bundle.json","state_url":"https://pith.science/pith/WISN6CK5PXQ5VXPKACTSP3REC2/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WISN6CK5PXQ5VXPKACTSP3REC2/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":"2026-08-20T03:58:23Z","links":{"resolver":"https://pith.science/pith/WISN6CK5PXQ5VXPKACTSP3REC2","bundle":"https://pith.science/pith/WISN6CK5PXQ5VXPKACTSP3REC2/bundle.json","state":"https://pith.science/pith/WISN6CK5PXQ5VXPKACTSP3REC2/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WISN6CK5PXQ5VXPKACTSP3REC2/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:WISN6CK5PXQ5VXPKACTSP3REC2","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":"64f273a551bbed56aff08bfa998d40cb3a43e133afc3f348ab46ffb0eabf079f","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T14:13:48Z","title_canon_sha256":"4fc4cffb8baf5e59fcddf6ac0ac0c1c38dbcfeb9acbb1dd06090221631585fcd"},"schema_version":"1.0","source":{"id":"2608.12090","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2608.12090","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"arxiv_version","alias_value":"2608.12090v1","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.12090","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"pith_short_12","alias_value":"WISN6CK5PXQ5","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"pith_short_16","alias_value":"WISN6CK5PXQ5VXPK","created_at":"2026-08-13T01:29:57Z"},{"alias_kind":"pith_short_8","alias_value":"WISN6CK5","created_at":"2026-08-13T01:29:57Z"}],"graph_snapshots":[{"event_id":"sha256:520ca88c3209f1a7b6ed7aa7629b5b638eea341e773b0c21026c54b771ea46b7","target":"graph","created_at":"2026-08-13T01:29:57Z","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/2608.12090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Protein language models (PLMs) have transferred the latest advances from natural language processing to computational biology. These models, trained on large corpora of protein sequence data, are widely used to translate amino acid sequences into latent-space embeddings, ready for use in diverse downstream tasks (DTs). By a common consensus, embeddings from the model's last layer are used, and the model's internal behavior remains poorly understood. We analyzed 13 PLMs across 15 DTs from 11 datasets to investigate the informativeness of embeddings created in intermediate PLM layers. We trained","authors_text":"Ilya Senatorov, Olga V. Kalinina, Roman Joeres","cross_cats":["q-bio.BM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T14:13:48Z","title":"Task- and dataset-specific information in protein language models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.12090","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:cda928eba892933c3c8e92978f9c1582da97f5c11152240d883835e169833264","target":"record","created_at":"2026-08-13T01:29:57Z","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":"64f273a551bbed56aff08bfa998d40cb3a43e133afc3f348ab46ffb0eabf079f","cross_cats_sorted":["q-bio.BM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-08-12T14:13:48Z","title_canon_sha256":"4fc4cffb8baf5e59fcddf6ac0ac0c1c38dbcfeb9acbb1dd06090221631585fcd"},"schema_version":"1.0","source":{"id":"2608.12090","kind":"arxiv","version":1}},"canonical_sha256":"b224df095d7de1daddea00a727ee241692b03b1bfe6b5b76cffa0a36eaa0633e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b224df095d7de1daddea00a727ee241692b03b1bfe6b5b76cffa0a36eaa0633e","first_computed_at":"2026-08-13T01:29:57.368825Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-08-13T01:29:57.368825Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nHvpjzSv+Z4qtmxpp0dhBII5uKO/3Nl0t+YutNUcVpN12O9Nke1rX3FA4LVx6q0rCV1MgHOtb09A3y0Nl3xwBw==","signature_status":"signed_v1","signed_at":"2026-08-13T01:29:57.371127Z","signed_message":"canonical_sha256_bytes"},"source_id":"2608.12090","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cda928eba892933c3c8e92978f9c1582da97f5c11152240d883835e169833264","sha256:520ca88c3209f1a7b6ed7aa7629b5b638eea341e773b0c21026c54b771ea46b7"],"state_sha256":"1768f85eb22054abc8fb142bf2479805eacaa8c936a1d41ac57ae6f1fa4ac233"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6+HpXaPf1iaYoAbgnn2XDWp3ZfCQXuwZM/9Ms3ZYYFsu0aJPYngOlYtBJ7aXupp741NfjovjijZaUkMqAtn/Dw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-20T03:58:23.127390Z","bundle_sha256":"bd52e4ca74082b29783e31f23206e64f2046311f880b90267fdce85acaf3f24e"}}