{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:QDRDPX6VG2XO2EQ7GT4NP2GWOH","short_pith_number":"pith:QDRDPX6V","canonical_record":{"source":{"id":"2603.16039","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T00:56:29Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ed2e4cdef73dafbdc8737d75e9c4617db3fe6195084c68ffb224e6e5ca58a20c","abstract_canon_sha256":"7effd2bd771efce4f30668994ead6c42326b4f138da9003c7778af433e90101c"},"schema_version":"1.0"},"canonical_sha256":"80e237dfd536aeed121f34f8d7e8d671f4b78230b02122d902ca88241561836d","source":{"kind":"arxiv","id":"2603.16039","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16039","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16039v2","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16039","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"QDRDPX6VG2XO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QDRDPX6VG2XO2EQ7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QDRDPX6V","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:QDRDPX6VG2XO2EQ7GT4NP2GWOH","target":"record","payload":{"canonical_record":{"source":{"id":"2603.16039","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T00:56:29Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"ed2e4cdef73dafbdc8737d75e9c4617db3fe6195084c68ffb224e6e5ca58a20c","abstract_canon_sha256":"7effd2bd771efce4f30668994ead6c42326b4f138da9003c7778af433e90101c"},"schema_version":"1.0"},"canonical_sha256":"80e237dfd536aeed121f34f8d7e8d671f4b78230b02122d902ca88241561836d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:59.636470Z","signature_b64":"e/dYgzar4CAaOvrLC9QN2F/rn2RDLOYOwhBfO4nRS9z9QZh5vobUj+uNkYKcZ8aN2LJ/w74MGLAVuPL4bLpLBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"80e237dfd536aeed121f34f8d7e8d671f4b78230b02122d902ca88241561836d","last_reissued_at":"2026-05-17T23:38:59.635560Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:59.635560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2603.16039","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":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+1/ZK2vV8OSf31aFGQC6YpNANPbR3d7b0NYbMMQ9B8ZQdABuTYZFbFuqruUpDgWJvvvCAfujsDlAhkBkrVCBCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T16:15:39.248642Z"},"content_sha256":"73815f4db062239eaf36504d672c833c491a3e1d03374313c2306881b9e46e17","schema_version":"1.0","event_id":"sha256:73815f4db062239eaf36504d672c833c491a3e1d03374313c2306881b9e46e17"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:QDRDPX6VG2XO2EQ7GT4NP2GWOH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Residual Stream Duality in Modern Transformer Architectures","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"The residual stream in Transformers is equivalent to causal short sliding-window attention when interpreted over layer depth instead of sequence positions.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Yifan Zhang","submitted_at":"2026-03-17T00:56:29Z","abstract_excerpt":"Recent work has made clear that the residual pathway is not mere optimization plumbing; it is part of the model's representational machinery. We agree, but argue that the cleanest way to organize this design space is through a two-axis view of the Transformer. A decoder evolves information along two ordered dimensions: sequence position and layer depth. Self-attention already provides adaptive mixing along the sequence axis, whereas the residual stream usually performs fixed addition along the depth axis. If we fix a token position and treat layer index as the ordered variable, then a causal d"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"a causal depth-wise residual attention read is exactly the same local operator as causal short sliding-window attention (ShortSWA), except written over depth rather than over sequence. This is the core residual stream duality behind Transformer².","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That treating layer index as an ordered variable and reinterpreting fixed residual addition as causal depth-wise attention produces a meaningful and actionable operator equivalence, even though the paper states operator-level duality does not imply systems-level symmetry.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Residual stream addition over depth is the same local operator as causal short sliding-window attention over sequence positions.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"The residual stream in Transformers is equivalent to causal short sliding-window attention when interpreted over layer depth instead of sequence positions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7bba0a1239f688fab6ad6ce316a67ff70ff0b793460260d6b6050aa8c8552f8a"},"source":{"id":"2603.16039","kind":"arxiv","version":2},"verdict":{"id":"a54e66b0-1119-4b93-b38d-c8eda3b2f181","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T09:43:05.665105Z","strongest_claim":"a causal depth-wise residual attention read is exactly the same local operator as causal short sliding-window attention (ShortSWA), except written over depth rather than over sequence. This is the core residual stream duality behind Transformer².","one_line_summary":"Residual stream addition over depth is the same local operator as causal short sliding-window attention over sequence positions.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That treating layer index as an ordered variable and reinterpreting fixed residual addition as causal depth-wise attention produces a meaningful and actionable operator equivalence, even though the paper states operator-level duality does not imply systems-level symmetry.","pith_extraction_headline":"The residual stream in Transformers is equivalent to causal short sliding-window attention when interpreted over layer depth instead of sequence positions."},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":1,"snapshot_sha256":"2619ecc2489f469597072803925cd132cf50d6318a7bdb97f6cfd7b949eedcc3"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"a54e66b0-1119-4b93-b38d-c8eda3b2f181"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:38:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j42JrDerkH2eLa2XLNfUifY67yUtdRlwv5IYIZdHcs0zWPb76/k54ugFcAj6bTDFP9IrveeuZ8LXE7Vg8huJCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-23T16:15:39.249558Z"},"content_sha256":"34490ca8488e34b5f71495fba6242242bba4df59de540c200e681ee2e840847b","schema_version":"1.0","event_id":"sha256:34490ca8488e34b5f71495fba6242242bba4df59de540c200e681ee2e840847b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QDRDPX6VG2XO2EQ7GT4NP2GWOH/bundle.json","state_url":"https://pith.science/pith/QDRDPX6VG2XO2EQ7GT4NP2GWOH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QDRDPX6VG2XO2EQ7GT4NP2GWOH/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":"2026-05-23T16:15:39Z","links":{"resolver":"https://pith.science/pith/QDRDPX6VG2XO2EQ7GT4NP2GWOH","bundle":"https://pith.science/pith/QDRDPX6VG2XO2EQ7GT4NP2GWOH/bundle.json","state":"https://pith.science/pith/QDRDPX6VG2XO2EQ7GT4NP2GWOH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QDRDPX6VG2XO2EQ7GT4NP2GWOH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QDRDPX6VG2XO2EQ7GT4NP2GWOH","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":"7effd2bd771efce4f30668994ead6c42326b4f138da9003c7778af433e90101c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T00:56:29Z","title_canon_sha256":"ed2e4cdef73dafbdc8737d75e9c4617db3fe6195084c68ffb224e6e5ca58a20c"},"schema_version":"1.0","source":{"id":"2603.16039","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.16039","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"arxiv_version","alias_value":"2603.16039v2","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.16039","created_at":"2026-05-17T23:38:59Z"},{"alias_kind":"pith_short_12","alias_value":"QDRDPX6VG2XO","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"QDRDPX6VG2XO2EQ7","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"QDRDPX6V","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:34490ca8488e34b5f71495fba6242242bba4df59de540c200e681ee2e840847b","target":"graph","created_at":"2026-05-17T23:38:59Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"a causal depth-wise residual attention read is exactly the same local operator as causal short sliding-window attention (ShortSWA), except written over depth rather than over sequence. This is the core residual stream duality behind Transformer²."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That treating layer index as an ordered variable and reinterpreting fixed residual addition as causal depth-wise attention produces a meaningful and actionable operator equivalence, even though the paper states operator-level duality does not imply systems-level symmetry."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"Residual stream addition over depth is the same local operator as causal short sliding-window attention over sequence positions."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"The residual stream in Transformers is equivalent to causal short sliding-window attention when interpreted over layer depth instead of sequence positions."}],"snapshot_sha256":"7bba0a1239f688fab6ad6ce316a67ff70ff0b793460260d6b6050aa8c8552f8a"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"2619ecc2489f469597072803925cd132cf50d6318a7bdb97f6cfd7b949eedcc3"},"paper":{"abstract_excerpt":"Recent work has made clear that the residual pathway is not mere optimization plumbing; it is part of the model's representational machinery. We agree, but argue that the cleanest way to organize this design space is through a two-axis view of the Transformer. A decoder evolves information along two ordered dimensions: sequence position and layer depth. Self-attention already provides adaptive mixing along the sequence axis, whereas the residual stream usually performs fixed addition along the depth axis. If we fix a token position and treat layer index as the ordered variable, then a causal d","authors_text":"Yifan Zhang","cross_cats":["cs.AI","cs.CL"],"headline":"The residual stream in Transformers is equivalent to causal short sliding-window attention when interpreted over layer depth instead of sequence positions.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T00:56:29Z","title":"Residual Stream Duality in Modern Transformer Architectures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.16039","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-15T09:43:05.665105Z","id":"a54e66b0-1119-4b93-b38d-c8eda3b2f181","model_set":{"reader":"grok-4.3"},"one_line_summary":"Residual stream addition over depth is the same local operator as causal short sliding-window attention over sequence positions.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"The residual stream in Transformers is equivalent to causal short sliding-window attention when interpreted over layer depth instead of sequence positions.","strongest_claim":"a causal depth-wise residual attention read is exactly the same local operator as causal short sliding-window attention (ShortSWA), except written over depth rather than over sequence. This is the core residual stream duality behind Transformer².","weakest_assumption":"That treating layer index as an ordered variable and reinterpreting fixed residual addition as causal depth-wise attention produces a meaningful and actionable operator equivalence, even though the paper states operator-level duality does not imply systems-level symmetry."}},"verdict_id":"a54e66b0-1119-4b93-b38d-c8eda3b2f181"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:73815f4db062239eaf36504d672c833c491a3e1d03374313c2306881b9e46e17","target":"record","created_at":"2026-05-17T23:38:59Z","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":"7effd2bd771efce4f30668994ead6c42326b4f138da9003c7778af433e90101c","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-17T00:56:29Z","title_canon_sha256":"ed2e4cdef73dafbdc8737d75e9c4617db3fe6195084c68ffb224e6e5ca58a20c"},"schema_version":"1.0","source":{"id":"2603.16039","kind":"arxiv","version":2}},"canonical_sha256":"80e237dfd536aeed121f34f8d7e8d671f4b78230b02122d902ca88241561836d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80e237dfd536aeed121f34f8d7e8d671f4b78230b02122d902ca88241561836d","first_computed_at":"2026-05-17T23:38:59.635560Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:59.635560Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"e/dYgzar4CAaOvrLC9QN2F/rn2RDLOYOwhBfO4nRS9z9QZh5vobUj+uNkYKcZ8aN2LJ/w74MGLAVuPL4bLpLBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:59.636470Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.16039","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:73815f4db062239eaf36504d672c833c491a3e1d03374313c2306881b9e46e17","sha256:34490ca8488e34b5f71495fba6242242bba4df59de540c200e681ee2e840847b"],"state_sha256":"d8b729b2f02bf851fd39145c23698bc6d8b518ef38908b5d5b4aaaea4796975b"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"raESe786d70pHRFrp2R0rqEsVPvd5D9obZ8xkAs4nGGdQ71vxwPBathFTuqQNZa4oN8LDSp6EFSEidvQbS1zDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-23T16:15:39.255055Z","bundle_sha256":"add978cb7a26e3ea62462301e3519d865ce55f199b3bcac7ea3a3a6c02d853fd"}}