{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:7OYALTYKOIH7ZNEUXHZ4LSX2BF","short_pith_number":"pith:7OYALTYK","canonical_record":{"source":{"id":"2507.07996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T17:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"5682cb5298bacf7b2acfa93df6f652f24842dd73ad9458cf755595690d3190b3","abstract_canon_sha256":"24753c27da64dc98458d9e9a6926f687d87497aa438c94476971537e05251bb4"},"schema_version":"1.0"},"canonical_sha256":"fbb005cf0a720ffcb494b9f3c5cafa0941a669168b083ff7a98688642ae8f249","source":{"kind":"arxiv","id":"2507.07996","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07996","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07996v1","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07996","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"7OYALTYKOIH7","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"pith_short_16","alias_value":"7OYALTYKOIH7ZNEU","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"pith_short_8","alias_value":"7OYALTYK","created_at":"2026-07-05T11:35:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:7OYALTYKOIH7ZNEUXHZ4LSX2BF","target":"record","payload":{"canonical_record":{"source":{"id":"2507.07996","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T17:59:53Z","cross_cats_sorted":[],"title_canon_sha256":"5682cb5298bacf7b2acfa93df6f652f24842dd73ad9458cf755595690d3190b3","abstract_canon_sha256":"24753c27da64dc98458d9e9a6926f687d87497aa438c94476971537e05251bb4"},"schema_version":"1.0"},"canonical_sha256":"fbb005cf0a720ffcb494b9f3c5cafa0941a669168b083ff7a98688642ae8f249","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:08.372568Z","signature_b64":"a3U5SDf9T+7fwqk+uXpelhpOtM/XYe29lLz5nI80AK6dsrdrqx0Zw9e7mR5yEG8hZIFkXgwFGUaSHPmCPLpgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbb005cf0a720ffcb494b9f3c5cafa0941a669168b083ff7a98688642ae8f249","last_reissued_at":"2026-07-05T11:35:08.372080Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:08.372080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.07996","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":"2026-07-05T11:35:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2rXcC9j0GNxZQIm5MSkOyPijDbpVBv3XQdwEQugkHI+BHpSbEleAXD1otWvo8z1oQbSY9oJCsK0rupT+YEmHCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:33:14.859544Z"},"content_sha256":"8522a8c49b079e783ddc0d1099d2dd2408e56ba0c44b7780425ec5a56bbaadeb","schema_version":"1.0","event_id":"sha256:8522a8c49b079e783ddc0d1099d2dd2408e56ba0c44b7780425ec5a56bbaadeb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:7OYALTYKOIH7ZNEUXHZ4LSX2BF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tianyi Zhou, Yang Li, Ziyue Li","submitted_at":"2025-07-10T17:59:53Z","abstract_excerpt":"Can a pretrained neural network adapt its architecture to different inputs without any finetuning? Do we need all layers for simple tasks, and are they adequate for challenging tasks? We found that the layers of a pretrained large language model (LLM) can be manipulated as separate modules to build a better and even shallower model customized for each test sample. In particular, each layer from the pretrained model can be skipped/pruned or repeated multiple times as recurrent neural networks (RNN), and stacked with others in arbitrary orders, yielding a chain-of-layers (CoLa) per sample. This "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07996","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/2507.07996/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":"2026-07-05T11:35:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rd+p7QZnyzSb3dncoUp9SJjy3k9BMg7I67i38plmJumdlYV2l92N0QSm5fevA63GbBFVti15id58V0OZK60DDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T03:33:14.860407Z"},"content_sha256":"69a93165b9338468f55980cf50c5b23261d4b5d77e8e9cd5ce52929692bc6c17","schema_version":"1.0","event_id":"sha256:69a93165b9338468f55980cf50c5b23261d4b5d77e8e9cd5ce52929692bc6c17"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7OYALTYKOIH7ZNEUXHZ4LSX2BF/bundle.json","state_url":"https://pith.science/pith/7OYALTYKOIH7ZNEUXHZ4LSX2BF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7OYALTYKOIH7ZNEUXHZ4LSX2BF/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":"2026-08-08T03:33:14Z","links":{"resolver":"https://pith.science/pith/7OYALTYKOIH7ZNEUXHZ4LSX2BF","bundle":"https://pith.science/pith/7OYALTYKOIH7ZNEUXHZ4LSX2BF/bundle.json","state":"https://pith.science/pith/7OYALTYKOIH7ZNEUXHZ4LSX2BF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7OYALTYKOIH7ZNEUXHZ4LSX2BF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:7OYALTYKOIH7ZNEUXHZ4LSX2BF","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":"24753c27da64dc98458d9e9a6926f687d87497aa438c94476971537e05251bb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T17:59:53Z","title_canon_sha256":"5682cb5298bacf7b2acfa93df6f652f24842dd73ad9458cf755595690d3190b3"},"schema_version":"1.0","source":{"id":"2507.07996","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07996","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07996v1","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07996","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"pith_short_12","alias_value":"7OYALTYKOIH7","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"pith_short_16","alias_value":"7OYALTYKOIH7ZNEU","created_at":"2026-07-05T11:35:08Z"},{"alias_kind":"pith_short_8","alias_value":"7OYALTYK","created_at":"2026-07-05T11:35:08Z"}],"graph_snapshots":[{"event_id":"sha256:69a93165b9338468f55980cf50c5b23261d4b5d77e8e9cd5ce52929692bc6c17","target":"graph","created_at":"2026-07-05T11:35:08Z","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/2507.07996/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Can a pretrained neural network adapt its architecture to different inputs without any finetuning? Do we need all layers for simple tasks, and are they adequate for challenging tasks? We found that the layers of a pretrained large language model (LLM) can be manipulated as separate modules to build a better and even shallower model customized for each test sample. In particular, each layer from the pretrained model can be skipped/pruned or repeated multiple times as recurrent neural networks (RNN), and stacked with others in arbitrary orders, yielding a chain-of-layers (CoLa) per sample. This ","authors_text":"Tianyi Zhou, Yang Li, Ziyue Li","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T17:59:53Z","title":"Skip a Layer or Loop it? Test-Time Depth Adaptation of Pretrained LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07996","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":"sha256:8522a8c49b079e783ddc0d1099d2dd2408e56ba0c44b7780425ec5a56bbaadeb","target":"record","created_at":"2026-07-05T11:35:08Z","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":"24753c27da64dc98458d9e9a6926f687d87497aa438c94476971537e05251bb4","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T17:59:53Z","title_canon_sha256":"5682cb5298bacf7b2acfa93df6f652f24842dd73ad9458cf755595690d3190b3"},"schema_version":"1.0","source":{"id":"2507.07996","kind":"arxiv","version":1}},"canonical_sha256":"fbb005cf0a720ffcb494b9f3c5cafa0941a669168b083ff7a98688642ae8f249","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fbb005cf0a720ffcb494b9f3c5cafa0941a669168b083ff7a98688642ae8f249","first_computed_at":"2026-07-05T11:35:08.372080Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:08.372080Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a3U5SDf9T+7fwqk+uXpelhpOtM/XYe29lLz5nI80AK6dsrdrqx0Zw9e7mR5yEG8hZIFkXgwFGUaSHPmCPLpgDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:08.372568Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07996","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8522a8c49b079e783ddc0d1099d2dd2408e56ba0c44b7780425ec5a56bbaadeb","sha256:69a93165b9338468f55980cf50c5b23261d4b5d77e8e9cd5ce52929692bc6c17"],"state_sha256":"fb071dfe7e4db5c8f8df1da79af8533a08342817fa9a7a87ee72c35fbee60328"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mlZ9WkrYFF2f/VAwuwKNAG4k6zXiKU0SUjPA/UVTSxXP8vrXAU6Vm/tf+sFjQlwhRuaXyevOzP/j4EHdIjqvAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T03:33:14.867868Z","bundle_sha256":"7a8231575321e8de198589f3096bac03ca62299cddbf45c03731f0b33b8fe10e"}}