{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:LOMNBZERIPOIDQ7WURCH2J3RO4","short_pith_number":"pith:LOMNBZER","canonical_record":{"source":{"id":"2409.03621","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T15:33:24Z","cross_cats_sorted":[],"title_canon_sha256":"0674399d42a9999d4e051e6f64568f3298ad46971deda4ede39ccef9bbd19c8a","abstract_canon_sha256":"18bc031b3e217002523e2ad660969a5019000cecb789b3b45d298041c60334df"},"schema_version":"1.0"},"canonical_sha256":"5b98d0e49143dc81c3f6a4447d27717725fbb0370791aa39baf636d77280f288","source":{"kind":"arxiv","id":"2409.03621","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03621","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03621v2","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03621","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"pith_short_12","alias_value":"LOMNBZERIPOI","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"LOMNBZERIPOIDQ7W","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"LOMNBZER","created_at":"2026-07-05T09:28:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:LOMNBZERIPOIDQ7WURCH2J3RO4","target":"record","payload":{"canonical_record":{"source":{"id":"2409.03621","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T15:33:24Z","cross_cats_sorted":[],"title_canon_sha256":"0674399d42a9999d4e051e6f64568f3298ad46971deda4ede39ccef9bbd19c8a","abstract_canon_sha256":"18bc031b3e217002523e2ad660969a5019000cecb789b3b45d298041c60334df"},"schema_version":"1.0"},"canonical_sha256":"5b98d0e49143dc81c3f6a4447d27717725fbb0370791aa39baf636d77280f288","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:28:54.600517Z","signature_b64":"2jg6fPaNdmOWehUzRelHawocMSr/N8J9bQKUZ/ylpuOiE/yLYTsHBsHZZfyQ1URmfxUTvwxRiB9cIdcFhZnlDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5b98d0e49143dc81c3f6a4447d27717725fbb0370791aa39baf636d77280f288","last_reissued_at":"2026-07-05T09:28:54.599950Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:28:54.599950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.03621","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":"2026-07-05T09:28:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"X/+0ZnzahnwWQwHw+qNl3jjtQoB0xmdl31enjb5d+USh62cOczn9HftfoyZPv6a1OaLzZSTKXiBASeL+vGIKAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:46:47.953532Z"},"content_sha256":"f5706a2335d74bd8cc373e703f42385eebcee0e57c29e966b2fec4a9e33e2f38","schema_version":"1.0","event_id":"sha256:f5706a2335d74bd8cc373e703f42385eebcee0e57c29e966b2fec4a9e33e2f38"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:LOMNBZERIPOIDQ7WURCH2J3RO4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Amit Ben-Artzy, Roy Schwartz","submitted_at":"2024-09-05T15:33:24Z","abstract_excerpt":"In decoder-based LLMs, the representation of a given layer serves two purposes: as input to the next layer during the computation of the current token; and as input to the attention mechanism of future tokens. In this work, we show that the importance of the latter role might be overestimated. To show that, we start by manipulating the representations of previous tokens; e.g. by replacing the hidden states at some layer k with random vectors. Our experimenting with four LLMs and four tasks show that this operation often leads to small to negligible drop in performance. Importantly, this happen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03621","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/2409.03621/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":"2026-07-05T09:28:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b8yWvf2PlDRskd/JQF+fRJ1lTD2gMCX9vrrxctk0RX6cznPVU4lKR/+kbgXwfCC2CUp0XpF9D4xWgldjuBM1Aw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:46:47.954063Z"},"content_sha256":"1aaa5418d7571eeeb4b88617fdec741bb1fca9c58cb182206150a44195926189","schema_version":"1.0","event_id":"sha256:1aaa5418d7571eeeb4b88617fdec741bb1fca9c58cb182206150a44195926189"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/LOMNBZERIPOIDQ7WURCH2J3RO4/bundle.json","state_url":"https://pith.science/pith/LOMNBZERIPOIDQ7WURCH2J3RO4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/LOMNBZERIPOIDQ7WURCH2J3RO4/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":"2026-08-08T11:46:47Z","links":{"resolver":"https://pith.science/pith/LOMNBZERIPOIDQ7WURCH2J3RO4","bundle":"https://pith.science/pith/LOMNBZERIPOIDQ7WURCH2J3RO4/bundle.json","state":"https://pith.science/pith/LOMNBZERIPOIDQ7WURCH2J3RO4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/LOMNBZERIPOIDQ7WURCH2J3RO4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:LOMNBZERIPOIDQ7WURCH2J3RO4","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":"18bc031b3e217002523e2ad660969a5019000cecb789b3b45d298041c60334df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T15:33:24Z","title_canon_sha256":"0674399d42a9999d4e051e6f64568f3298ad46971deda4ede39ccef9bbd19c8a"},"schema_version":"1.0","source":{"id":"2409.03621","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.03621","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"arxiv_version","alias_value":"2409.03621v2","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.03621","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"pith_short_12","alias_value":"LOMNBZERIPOI","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"pith_short_16","alias_value":"LOMNBZERIPOIDQ7W","created_at":"2026-07-05T09:28:54Z"},{"alias_kind":"pith_short_8","alias_value":"LOMNBZER","created_at":"2026-07-05T09:28:54Z"}],"graph_snapshots":[{"event_id":"sha256:1aaa5418d7571eeeb4b88617fdec741bb1fca9c58cb182206150a44195926189","target":"graph","created_at":"2026-07-05T09:28:54Z","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/2409.03621/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In decoder-based LLMs, the representation of a given layer serves two purposes: as input to the next layer during the computation of the current token; and as input to the attention mechanism of future tokens. In this work, we show that the importance of the latter role might be overestimated. To show that, we start by manipulating the representations of previous tokens; e.g. by replacing the hidden states at some layer k with random vectors. Our experimenting with four LLMs and four tasks show that this operation often leads to small to negligible drop in performance. Importantly, this happen","authors_text":"Amit Ben-Artzy, Roy Schwartz","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T15:33:24Z","title":"Attend First, Consolidate Later: On the Importance of Attention in Different LLM Layers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.03621","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:f5706a2335d74bd8cc373e703f42385eebcee0e57c29e966b2fec4a9e33e2f38","target":"record","created_at":"2026-07-05T09:28:54Z","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":"18bc031b3e217002523e2ad660969a5019000cecb789b3b45d298041c60334df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-05T15:33:24Z","title_canon_sha256":"0674399d42a9999d4e051e6f64568f3298ad46971deda4ede39ccef9bbd19c8a"},"schema_version":"1.0","source":{"id":"2409.03621","kind":"arxiv","version":2}},"canonical_sha256":"5b98d0e49143dc81c3f6a4447d27717725fbb0370791aa39baf636d77280f288","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5b98d0e49143dc81c3f6a4447d27717725fbb0370791aa39baf636d77280f288","first_computed_at":"2026-07-05T09:28:54.599950Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:28:54.599950Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2jg6fPaNdmOWehUzRelHawocMSr/N8J9bQKUZ/ylpuOiE/yLYTsHBsHZZfyQ1URmfxUTvwxRiB9cIdcFhZnlDw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:28:54.600517Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.03621","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f5706a2335d74bd8cc373e703f42385eebcee0e57c29e966b2fec4a9e33e2f38","sha256:1aaa5418d7571eeeb4b88617fdec741bb1fca9c58cb182206150a44195926189"],"state_sha256":"877ab0d22b6edaa19dc34a4d6dff301aed390a37b6d05d4fc215d6933271cfda"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"alErre9g6ghNuQRX7UxWQ/6Xpbl+yH26NiEbm79/RthrSw/+AlAEuynwalxPPyfSqTr8xwtB7WHMdQBT6j2iAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:46:47.958867Z","bundle_sha256":"e07283a38f1ea09536309e302a5ba6bdb31380571c692aa461187e78e162788d"}}