{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OUTCSWCON2JAOCS425E63DRCX3","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":"e4cf78ef8e575e37671321ce4d9a29d4948158b0c93ac59183138b9017001db7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-07T10:22:27Z","title_canon_sha256":"f43c62101eeaa0b12ffb0f20e8b74f47c74a899245a0b2b51915ae9be908fcfc"},"schema_version":"1.0","source":{"id":"2604.05673","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.05673","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"arxiv_version","alias_value":"2604.05673v3","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.05673","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"pith_short_12","alias_value":"OUTCSWCON2JA","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"pith_short_16","alias_value":"OUTCSWCON2JAOCS4","created_at":"2026-05-28T01:04:39Z"},{"alias_kind":"pith_short_8","alias_value":"OUTCSWCO","created_at":"2026-05-28T01:04:39Z"}],"graph_snapshots":[{"event_id":"sha256:e10503faf3628953d41f1094921d5e403c0eda9186c5a877b5c5ba50847b652a","target":"graph","created_at":"2026-05-28T01:04:39Z","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":"We prove two key results: (1) the conditional velocity field's functional form is invariant across the entire ε-spectrum (Velocity Structure Invariance), enabling a single network to serve all regularization strengths; and (2) reducing ε linearly decreases the conditional velocity variance, enabling more stable coarse-step ODE integration. Empirically, RSBM achieves over 94% cosine similarity and 92% success rate in merely 3 integration steps -- without distillation or multi-stage training."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The assumption that a learned conditional prior reliably shortens transport distance and that the velocity structure invariance holds in practice for high-dimensional visual navigation observations without requiring additional training or post-hoc adjustments."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RSBM exploits velocity field invariance across regularization levels to achieve over 94% cosine similarity and 92% success in visual navigation using only 3 integration steps."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A single velocity network works across all regularization strengths in Schrödinger Bridge policies, enabling 3-step visual navigation at 92% success."}],"snapshot_sha256":"e6d8dfa33b632b9adffbd44da9062e184fa8258080244a4a5a880c1115d36831"},"formal_canon":{"evidence_count":3,"snapshot_sha256":"44422574f46cd2a18bff46362a9dbbb56397eb9b78c6715daea0e0065538384d"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.05673/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual navigation is a core challenge in Embodied AI, requiring autonomous agents to translate high-dimensional sensory observations into continuous, long-horizon action trajectories. While generative policies based on diffusion models and Schr\\\"odinger Bridges (SB) effectively capture multimodal action distributions, they require dozens of integration steps due to high-variance stochastic transport, posing a critical barrier for real-time robotic control. We propose Rectified Schr\\\"odinger Bridge Matching (RSBM), a framework that exploits a shared velocity-field structure between standard Sch","authors_text":"Junhui Li, Rui Ma, Tieru Wu, Weiguang Zhao, Wenjian Zhang, Wuyang Luan","cross_cats":["cs.AI"],"headline":"A single velocity network works across all regularization strengths in Schrödinger Bridge policies, enabling 3-step visual navigation at 92% success.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-07T10:22:27Z","title":"Rectified Schr\\\"odinger Bridge Matching for Few-Step Visual Navigation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.05673","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T19:20:57.485599Z","id":"bc6e2d07-4020-4b3d-b4dd-2e3f14c01a1b","model_set":{"reader":"grok-4.3"},"one_line_summary":"RSBM exploits velocity field invariance across regularization levels to achieve over 94% cosine similarity and 92% success in visual navigation using only 3 integration steps.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A single velocity network works across all regularization strengths in Schrödinger Bridge policies, enabling 3-step visual navigation at 92% success.","strongest_claim":"We prove two key results: (1) the conditional velocity field's functional form is invariant across the entire ε-spectrum (Velocity Structure Invariance), enabling a single network to serve all regularization strengths; and (2) reducing ε linearly decreases the conditional velocity variance, enabling more stable coarse-step ODE integration. Empirically, RSBM achieves over 94% cosine similarity and 92% success rate in merely 3 integration steps -- without distillation or multi-stage training.","weakest_assumption":"The assumption that a learned conditional prior reliably shortens transport distance and that the velocity structure invariance holds in practice for high-dimensional visual navigation observations without requiring additional training or post-hoc adjustments."}},"verdict_id":"bc6e2d07-4020-4b3d-b4dd-2e3f14c01a1b"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:bd847cc57eedfb297104b4ce26ec40f43e73d39dbe7d0d860cbbb7da4873f7f2","target":"record","created_at":"2026-05-28T01:04:39Z","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":"e4cf78ef8e575e37671321ce4d9a29d4948158b0c93ac59183138b9017001db7","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-07T10:22:27Z","title_canon_sha256":"f43c62101eeaa0b12ffb0f20e8b74f47c74a899245a0b2b51915ae9be908fcfc"},"schema_version":"1.0","source":{"id":"2604.05673","kind":"arxiv","version":3}},"canonical_sha256":"752629584e6e92070a5cd749ed8e22becc6622a2bd322f48311c8e50137efe0f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"752629584e6e92070a5cd749ed8e22becc6622a2bd322f48311c8e50137efe0f","first_computed_at":"2026-05-28T01:04:39.606923Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T01:04:39.606923Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iPCad1KN6RAWQuLJbxWIE8fX3oupsNV+TfwULDKnmESxWsH0NZrcGrliS0SBLPpvRpR80yanFyQstwZvm/rlAg==","signature_status":"signed_v1","signed_at":"2026-05-28T01:04:39.607434Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.05673","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bd847cc57eedfb297104b4ce26ec40f43e73d39dbe7d0d860cbbb7da4873f7f2","sha256:e10503faf3628953d41f1094921d5e403c0eda9186c5a877b5c5ba50847b652a"],"state_sha256":"2632988f00a97517393fee7f7c148decc4bfec87a300a546fdb0ddce5f9a9586"}