{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:TYS274IMRA7HPMJV76DDP57I7O","short_pith_number":"pith:TYS274IM","canonical_record":{"source":{"id":"2509.00174","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T18:17:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5d8dcf5bbe88999a8b87e919c4928076ec3617f6808c6a2772dffbd9b633f6a0","abstract_canon_sha256":"3df5d850a868fd4f43b7e44e0f6581531bb5c38df31c37f05207206cd90431ea"},"schema_version":"1.0"},"canonical_sha256":"9e25aff10c883e77b135ff8637f7e8fbb47e44dd127f66d78f053d22191f27ee","source":{"kind":"arxiv","id":"2509.00174","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00174","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00174v2","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00174","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"TYS274IMRA7H","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"TYS274IMRA7HPMJV","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"TYS274IM","created_at":"2026-07-05T12:11:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:TYS274IMRA7HPMJV76DDP57I7O","target":"record","payload":{"canonical_record":{"source":{"id":"2509.00174","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T18:17:48Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5d8dcf5bbe88999a8b87e919c4928076ec3617f6808c6a2772dffbd9b633f6a0","abstract_canon_sha256":"3df5d850a868fd4f43b7e44e0f6581531bb5c38df31c37f05207206cd90431ea"},"schema_version":"1.0"},"canonical_sha256":"9e25aff10c883e77b135ff8637f7e8fbb47e44dd127f66d78f053d22191f27ee","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:20.219932Z","signature_b64":"0O5n8qxRkN3d+q7OL7lE4Q/7FWVG3SDhVMUmxmE4OorpwqKjpCALxFSz6YGE/GITnkVwjpgOQPvkSK5XVckBAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e25aff10c883e77b135ff8637f7e8fbb47e44dd127f66d78f053d22191f27ee","last_reissued_at":"2026-07-05T12:11:20.219523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:20.219523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2509.00174","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":"2026-07-05T12:11:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"EJqFljlPPUlJnOC9MklBNcXfbUvhTvsxfnfw5mTpunqLnVZP7u8D1/S38KudMLh7QKhzBj1RUHeZlQANXW0KBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:00:21.736113Z"},"content_sha256":"038aa810a89f2a22b61c40a444a4bc10e4348761044dda99ee917cbfd0b68f26","schema_version":"1.0","event_id":"sha256:038aa810a89f2a22b61c40a444a4bc10e4348761044dda99ee917cbfd0b68f26"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:TYS274IMRA7HPMJV76DDP57I7O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Principled Approximation Methods for Efficient and Scalable Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Pedro Savarese","submitted_at":"2025-08-29T18:17:48Z","abstract_excerpt":"Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep learning technologies. This thesis investigates principled approximation methods for improving the efficiency of deep learning systems, with a particular focus on settings that involve discrete constraints and non-differentiability.\n  We study three main approaches toward improved efficiency: architecture design, model compression, and optimization. For model c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00174","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/2509.00174/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":"2026-07-05T12:11:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fQebBZFrvaC0ikcNKIQFxfiG13pfaCOqgEDjc4WF4dtAhLTiKXZ864pN4KZTSEtiu8TJPmgOCEDa13a/SpB0DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T01:00:21.737620Z"},"content_sha256":"0b4111955aabc16f6a4f8f3e7afd86f7abc785c254080d52c6240a6e451dc61d","schema_version":"1.0","event_id":"sha256:0b4111955aabc16f6a4f8f3e7afd86f7abc785c254080d52c6240a6e451dc61d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TYS274IMRA7HPMJV76DDP57I7O/bundle.json","state_url":"https://pith.science/pith/TYS274IMRA7HPMJV76DDP57I7O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TYS274IMRA7HPMJV76DDP57I7O/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":"2026-08-06T01:00:21Z","links":{"resolver":"https://pith.science/pith/TYS274IMRA7HPMJV76DDP57I7O","bundle":"https://pith.science/pith/TYS274IMRA7HPMJV76DDP57I7O/bundle.json","state":"https://pith.science/pith/TYS274IMRA7HPMJV76DDP57I7O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TYS274IMRA7HPMJV76DDP57I7O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:TYS274IMRA7HPMJV76DDP57I7O","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":"3df5d850a868fd4f43b7e44e0f6581531bb5c38df31c37f05207206cd90431ea","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T18:17:48Z","title_canon_sha256":"5d8dcf5bbe88999a8b87e919c4928076ec3617f6808c6a2772dffbd9b633f6a0"},"schema_version":"1.0","source":{"id":"2509.00174","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.00174","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"arxiv_version","alias_value":"2509.00174v2","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.00174","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"pith_short_12","alias_value":"TYS274IMRA7H","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"pith_short_16","alias_value":"TYS274IMRA7HPMJV","created_at":"2026-07-05T12:11:20Z"},{"alias_kind":"pith_short_8","alias_value":"TYS274IM","created_at":"2026-07-05T12:11:20Z"}],"graph_snapshots":[{"event_id":"sha256:0b4111955aabc16f6a4f8f3e7afd86f7abc785c254080d52c6240a6e451dc61d","target":"graph","created_at":"2026-07-05T12:11:20Z","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/2509.00174/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in deep learning has been driven by increasingly larger models. However, their computational and energy demands have grown proportionally, creating significant barriers to their deployment and to a wider adoption of deep learning technologies. This thesis investigates principled approximation methods for improving the efficiency of deep learning systems, with a particular focus on settings that involve discrete constraints and non-differentiability.\n  We study three main approaches toward improved efficiency: architecture design, model compression, and optimization. For model c","authors_text":"Pedro Savarese","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T18:17:48Z","title":"Principled Approximation Methods for Efficient and Scalable Deep Learning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.00174","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":"sha256:038aa810a89f2a22b61c40a444a4bc10e4348761044dda99ee917cbfd0b68f26","target":"record","created_at":"2026-07-05T12:11:20Z","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":"3df5d850a868fd4f43b7e44e0f6581531bb5c38df31c37f05207206cd90431ea","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-08-29T18:17:48Z","title_canon_sha256":"5d8dcf5bbe88999a8b87e919c4928076ec3617f6808c6a2772dffbd9b633f6a0"},"schema_version":"1.0","source":{"id":"2509.00174","kind":"arxiv","version":2}},"canonical_sha256":"9e25aff10c883e77b135ff8637f7e8fbb47e44dd127f66d78f053d22191f27ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e25aff10c883e77b135ff8637f7e8fbb47e44dd127f66d78f053d22191f27ee","first_computed_at":"2026-07-05T12:11:20.219523Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:11:20.219523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0O5n8qxRkN3d+q7OL7lE4Q/7FWVG3SDhVMUmxmE4OorpwqKjpCALxFSz6YGE/GITnkVwjpgOQPvkSK5XVckBAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:11:20.219932Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.00174","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:038aa810a89f2a22b61c40a444a4bc10e4348761044dda99ee917cbfd0b68f26","sha256:0b4111955aabc16f6a4f8f3e7afd86f7abc785c254080d52c6240a6e451dc61d"],"state_sha256":"dbb451f8df6f1ea9a904389be138e51d37beb339902280eb91082ab265988652"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lqlx70F6/5d4CmURLeXhv+j1o937C9YCQ4Isk2JWP7uCgSWYfoxVf2ZE6Hu6ftiNerDL90yEaQ+fctC6G9O6Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T01:00:21.744846Z","bundle_sha256":"2ec20923b0893ba77febce36d54172adb40c52a5d5b9a93f24709ee10d25310c"}}