{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:IJB767ZZGRNDMXQNCY5JPFYARA","short_pith_number":"pith:IJB767ZZ","canonical_record":{"source":{"id":"2602.04931","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T11:00:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a439ec4ab7834df2c02d85660c36db7492eb3807b3e0a6b4fbd993ee2609dba0","abstract_canon_sha256":"0aef3acb6296f4c497ad22c5715ad677c1fe5bd3995ffe87a1e13198f40f2a08"},"schema_version":"1.0"},"canonical_sha256":"4243ff7f39345a365e0d163a97970088046768413ee16ac3f719f370196d9ae7","source":{"kind":"arxiv","id":"2602.04931","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04931","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04931v2","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04931","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"IJB767ZZGRND","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"IJB767ZZGRNDMXQN","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"IJB767ZZ","created_at":"2026-05-27T01:05:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:IJB767ZZGRNDMXQNCY5JPFYARA","target":"record","payload":{"canonical_record":{"source":{"id":"2602.04931","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T11:00:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a439ec4ab7834df2c02d85660c36db7492eb3807b3e0a6b4fbd993ee2609dba0","abstract_canon_sha256":"0aef3acb6296f4c497ad22c5715ad677c1fe5bd3995ffe87a1e13198f40f2a08"},"schema_version":"1.0"},"canonical_sha256":"4243ff7f39345a365e0d163a97970088046768413ee16ac3f719f370196d9ae7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:44.122863Z","signature_b64":"AcIM0SGkcH5Deih84R7khpR7v7OMUu278SYWq0FQH4OeTkvDFpUGPMwRGp1yu8LBiTFJ/2B3lEGd8fdZ9SdYDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4243ff7f39345a365e0d163a97970088046768413ee16ac3f719f370196d9ae7","last_reissued_at":"2026-05-27T01:05:44.122170Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:44.122170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2602.04931","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":"2026-05-27T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dpG+0mcciDrldFjVJ0aKXt+e+db51lNGL6M/YA9iKeNRyVPRWD59EO585K7u8CVgx2egbxVSMro+Pg+3yjCiAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T07:26:40.656406Z"},"content_sha256":"6fb8137ec893f6c2765de3765715c37afca5963e41aaf0c0c19ed16da0779677","schema_version":"1.0","event_id":"sha256:6fb8137ec893f6c2765de3765715c37afca5963e41aaf0c0c19ed16da0779677"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:IJB767ZZGRNDMXQNCY5JPFYARA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Emergent Causal-Geometric Dynamics Across Depth in Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniel C McNamee, Shahar Haim","submitted_at":"2026-02-04T11:00:16Z","abstract_excerpt":"Geometric analyses of large language model (LLM) representations reveal structured variation across depth but remain fundamentally correlational with respect to token prediction formation. Meanwhile, causal interventions expose depth-dependent efficacy profiles without a unifying account of their representational dynamics. A complete account of LLM function requires explaining how representational structure evolves across depth to causally produce predictions. We synthesize these perspectives by combining geometric analysis with mechanistic interventions, explicitly centralizing depth-wise dyn"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04931","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/2602.04931/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":"2026-05-27T01:05:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QfQW1CCU8HsWvGZrZgSVsCUV063g/y2ZE5q696BgQYs3YVzDZHXS+kc+M0sAqQkp84XlQPv+hoNeF2axZPPTAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T07:26:40.657337Z"},"content_sha256":"aa167fd9b9035d5786f47fee415389e9f6347065e23b24b520595293c3e54495","schema_version":"1.0","event_id":"sha256:aa167fd9b9035d5786f47fee415389e9f6347065e23b24b520595293c3e54495"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IJB767ZZGRNDMXQNCY5JPFYARA/bundle.json","state_url":"https://pith.science/pith/IJB767ZZGRNDMXQNCY5JPFYARA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IJB767ZZGRNDMXQNCY5JPFYARA/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":"2026-08-21T07:26:40Z","links":{"resolver":"https://pith.science/pith/IJB767ZZGRNDMXQNCY5JPFYARA","bundle":"https://pith.science/pith/IJB767ZZGRNDMXQNCY5JPFYARA/bundle.json","state":"https://pith.science/pith/IJB767ZZGRNDMXQNCY5JPFYARA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IJB767ZZGRNDMXQNCY5JPFYARA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:IJB767ZZGRNDMXQNCY5JPFYARA","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":"0aef3acb6296f4c497ad22c5715ad677c1fe5bd3995ffe87a1e13198f40f2a08","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T11:00:16Z","title_canon_sha256":"a439ec4ab7834df2c02d85660c36db7492eb3807b3e0a6b4fbd993ee2609dba0"},"schema_version":"1.0","source":{"id":"2602.04931","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2602.04931","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"arxiv_version","alias_value":"2602.04931v2","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.04931","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"pith_short_12","alias_value":"IJB767ZZGRND","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"pith_short_16","alias_value":"IJB767ZZGRNDMXQN","created_at":"2026-05-27T01:05:44Z"},{"alias_kind":"pith_short_8","alias_value":"IJB767ZZ","created_at":"2026-05-27T01:05:44Z"}],"graph_snapshots":[{"event_id":"sha256:aa167fd9b9035d5786f47fee415389e9f6347065e23b24b520595293c3e54495","target":"graph","created_at":"2026-05-27T01:05:44Z","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/2602.04931/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Geometric analyses of large language model (LLM) representations reveal structured variation across depth but remain fundamentally correlational with respect to token prediction formation. Meanwhile, causal interventions expose depth-dependent efficacy profiles without a unifying account of their representational dynamics. A complete account of LLM function requires explaining how representational structure evolves across depth to causally produce predictions. We synthesize these perspectives by combining geometric analysis with mechanistic interventions, explicitly centralizing depth-wise dyn","authors_text":"Daniel C McNamee, Shahar Haim","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T11:00:16Z","title":"Emergent Causal-Geometric Dynamics Across Depth in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.04931","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":"sha256:6fb8137ec893f6c2765de3765715c37afca5963e41aaf0c0c19ed16da0779677","target":"record","created_at":"2026-05-27T01:05:44Z","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":"0aef3acb6296f4c497ad22c5715ad677c1fe5bd3995ffe87a1e13198f40f2a08","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-04T11:00:16Z","title_canon_sha256":"a439ec4ab7834df2c02d85660c36db7492eb3807b3e0a6b4fbd993ee2609dba0"},"schema_version":"1.0","source":{"id":"2602.04931","kind":"arxiv","version":2}},"canonical_sha256":"4243ff7f39345a365e0d163a97970088046768413ee16ac3f719f370196d9ae7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4243ff7f39345a365e0d163a97970088046768413ee16ac3f719f370196d9ae7","first_computed_at":"2026-05-27T01:05:44.122170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:44.122170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AcIM0SGkcH5Deih84R7khpR7v7OMUu278SYWq0FQH4OeTkvDFpUGPMwRGp1yu8LBiTFJ/2B3lEGd8fdZ9SdYDQ==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:44.122863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2602.04931","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6fb8137ec893f6c2765de3765715c37afca5963e41aaf0c0c19ed16da0779677","sha256:aa167fd9b9035d5786f47fee415389e9f6347065e23b24b520595293c3e54495"],"state_sha256":"74f9ab9beb999dcbbf3f9c5eb2dcf7ee467aa142ac799f1a85d0ede9aaa4b0d8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pY57ALsxIOHp1h1W2izisXz0xKcH0fIUs1GikVFNxqH5l0cTuG4iIRcrJedPR2O7vW6fwutOopiainbD45nGDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T07:26:40.664101Z","bundle_sha256":"301be584a2c528da04bba15855b86766aa9e99d7b10ee6eed9c0d6b05b18d11c"}}